Merge branch 'master' into security/analysis-workflows-sandbox

feat(forge): Unbreak forge agent (#7196 )
Revert some changes to fix forge agent and enable components support. - Rename forge `Agent` to `ProtocolAgent` - Bring back and update `forge/app.py` and `forge/agent/forge_agent.py` - `ForgeAgent` inherits from `BaseAgent`, supports component execution and runs the same pipelines as autogpt Agent - Update forge version from 0.1.0 to 0.2.0 - Update code comments
2026-01-12 00:28:31 -05:00 · 2024-06-13 17:31:52 -05:00 · 2024-06-12 13:45:00 +01:00 · 2024-06-12 00:29:23 +07:00 · 2024-06-11 16:15:52 +02:00 · 2024-06-11 13:10:53 +02:00
985 changed files with 59724 additions and 69740 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -0,0 +1,28 @@
+# Ignore everything by default, selectively add things to context
+*
+
+# AutoGPT
+!autogpt/autogpt/
+!autogpt/pyproject.toml
+!autogpt/poetry.lock
+!autogpt/README.md
+!autogpt/tests/
+
+# Benchmark
+!benchmark/agbenchmark/
+!benchmark/pyproject.toml
+!benchmark/poetry.lock
+!benchmark/README.md
+
+# Forge
+!forge/forge/
+!forge/pyproject.toml
+!forge/poetry.lock
+!forge/README.md
+
+# Frontend
+!frontend/build/web/
+
+# Explicitly re-ignore some folders
+.*
+**/__pycache__
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,3 +1,5 @@
-frontend/build/* linguist-generated
+frontend/build/** linguist-generated

 **/poetry.lock linguist-generated
+
+docs/_javascript/** linguist-vendored
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@@ -1,5 +1,5 @@
 .github/workflows/  @Significant-Gravitas/devops
-autogpts/autogpt/   @Significant-Gravitas/maintainers
-autogpts/forge/     @Significant-Gravitas/forge-maintainers
+autogpt/   @Significant-Gravitas/maintainers
+forge/     @Significant-Gravitas/forge-maintainers
 benchmark/          @Significant-Gravitas/benchmark-maintainers
 frontend/           @Significant-Gravitas/frontend-maintainers
--- a/.github/ISSUE_TEMPLATE/1.bug.yml
+++ b/.github/ISSUE_TEMPLATE/1.bug.yml
@@ -16,7 +16,7 @@ body:
        [discussions]: https://github.com/Significant-Gravitas/AutoGPT/discussions
        [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184
        [existing issues]: https://github.com/Significant-Gravitas/AutoGPT/issues?q=is%3Aissue
-        [wiki page on Contributing]: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
+        [wiki page on Contributing]: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing

  - type: checkboxes
    attributes:
@@ -90,7 +90,7 @@ body:
    attributes:
      label: Do you use OpenAI GPT-3 or GPT-4?
      description: >
-        If you are using AutoGPT with `--gpt3only`, your problems may be caused by
+        If you are using AutoGPT with `SMART_LLM=gpt-3.5-turbo`, your problems may be caused by
        the [limitations](https://github.com/Significant-Gravitas/AutoGPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5.
      options:
        - GPT-3.5
--- a/.github/ISSUE_TEMPLATE/2.feature.yml
+++ b/.github/ISSUE_TEMPLATE/2.feature.yml
@@ -5,7 +5,7 @@ body:
  - type: markdown
    attributes:
      value: |
-        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Nexus/wiki/Contributing)
+        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing)
        Please provide a searchable summary of the issue in the title above ⬆️.
  - type: checkboxes
    attributes:
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -10,7 +10,7 @@

 <!--
 Check out our contribution guide:
-https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
+https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing

 1. Avoid duplicate work, issues, PRs etc.
 2. Also consider contributing something other than code; see the [contribution guide]
--- a/.github/labeler.yml
+++ b/.github/labeler.yml
@@ -1,10 +1,10 @@
 AutoGPT Agent:
 - changed-files:
-  - any-glob-to-any-file: autogpts/autogpt/**
+  - any-glob-to-any-file: autogpt/**

 Forge:
 - changed-files:
-  - any-glob-to-any-file: autogpts/forge/**
+  - any-glob-to-any-file: forge/**

 Benchmark:
 - changed-files:
@@ -14,10 +14,6 @@ Frontend:
 - changed-files:
  - any-glob-to-any-file: frontend/**

-Arena:
- changed-files:
-  - any-glob-to-any-file: arena/**
-
 documentation:
 - changed-files:
  - any-glob-to-any-file: docs/**
--- a/.github/workflows/arena-intake.yml
+++ b/.github/workflows/arena-intake.yml
@@ -1,169 +0,0 @@
-name: Arena intake
-
-on:
-  # We recommend `pull_request_target` so that github secrets are available.
-  # In `pull_request` we wouldn't be able to change labels of fork PRs
-  pull_request_target:
-    types: [ opened, synchronize ]
-    paths:
-      - 'arena/**'
-
-jobs:
-  check:
-    permissions:
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout PR
-      uses: actions/checkout@v4
-      with:
-        ref: ${{ github.event.pull_request.head.sha }}
-
-    - name: Check Arena entry
-      uses: actions/github-script@v7
-      with:
-        script: |
-          console.log('⚙️ Setting up...');
-
-          const fs = require('fs');
-          const path = require('path');
-
-          const pr = context.payload.pull_request;
-          const isFork = pr.head.repo.fork;
-
-          console.log('🔄️ Fetching PR diff metadata...');
-          const prFilesChanged = (await github.rest.pulls.listFiles({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            pull_number: pr.number,
-          })).data;
-          console.debug(prFilesChanged);
-          const arenaFilesChanged = prFilesChanged.filter(
-            ({ filename: file }) => file.startsWith('arena/') && file.endsWith('.json')
-          );
-          const hasChangesInAutogptsFolder = prFilesChanged.some(
-            ({ filename }) => filename.startsWith('autogpts/')
-          );
-
-          console.log(`🗒️ ${arenaFilesChanged.length} arena entries affected`);
-          console.debug(arenaFilesChanged);
-          if (arenaFilesChanged.length === 0) {
-            // If no files in `arena/` are changed, this job does not need to run.
-            return;
-          }
-
-          let close = false;
-          let flagForManualCheck = false;
-          let issues = [];
-
-          if (isFork) {
-            if (arenaFilesChanged.length > 1) {
-              // Impacting multiple entries in `arena/` is not allowed
-              issues.push('This pull request impacts multiple arena entries');
-            }
-            if (hasChangesInAutogptsFolder) {
-              // PRs that include the custom agent are generally not allowed
-              issues.push(
-                'This pull request includes changes in `autogpts/`.\n'
-                + 'Please make sure to only submit your arena entry (`arena/*.json`), '
-                + 'and not to accidentally include your custom agent itself.'
-              );
-            }
-          }
-
-          if (arenaFilesChanged.length === 1) {
-            const newArenaFile = arenaFilesChanged[0]
-            const newArenaFileName = path.basename(newArenaFile.filename)
-            console.log(`🗒️ Arena entry in PR: ${newArenaFile}`);
-
-            if (newArenaFile.status != 'added') {
-              flagForManualCheck = true;
-            }
-
-            if (pr.mergeable != false) {
-              const newArenaEntry = JSON.parse(fs.readFileSync(newArenaFile.filename));
-              const allArenaFiles = await (await glob.create('arena/*.json')).glob();
-              console.debug(newArenaEntry);
-
-              console.log(`➡️ Checking ${newArenaFileName} against existing entries...`);
-              for (const file of allArenaFiles) {
-                const existingEntryName = path.basename(file);
-
-                if (existingEntryName === newArenaFileName) {
-                  continue;
-                }
-
-                console.debug(`Checking against ${existingEntryName}...`);
-
-                const arenaEntry = JSON.parse(fs.readFileSync(file));
-                if (arenaEntry.github_repo_url === newArenaEntry.github_repo_url) {
-                  console.log(`⚠️ Duplicate detected: ${existingEntryName}`);
-                  issues.push(
-                    `The \`github_repo_url\` specified in __${newArenaFileName}__ `
-                    + `already exists in __${existingEntryName}__. `
-                    + `This PR will be closed as duplicate.`
-                  )
-                  close = true;
-                }
-              }
-            } else {
-              console.log('⚠️ PR has conflicts');
-              issues.push(
-                `__${newArenaFileName}__ conflicts with existing entry with the same name`
-              )
-              close = true;
-            }
-          }  // end if (arenaFilesChanged.length === 1)
-
-          console.log('🏁 Finished checking against existing entries');
-
-          if (issues.length == 0) {
-            console.log('✅ No issues detected');
-            if (flagForManualCheck) {
-              console.log('🤔 Requesting review from maintainers...');
-              await github.rest.pulls.requestReviewers({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: pr.number,
-                reviewers: ['Pwuts'],
-                // team_reviewers: ['maintainers'],  // doesn't work: https://stackoverflow.com/a/64977184/4751645
-              });
-            } else {
-              console.log('➡️ Approving PR...');
-              await github.rest.pulls.createReview({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: pr.number,
-                event: 'APPROVE',
-              });
-            }
-          } else {
-            console.log(`⚠️ ${issues.length} issues detected`);
-
-            console.log('➡️ Posting comment indicating issues...');
-            await github.rest.issues.createComment({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: pr.number,
-              body: `Our automation found one or more issues with this submission:\n`
-                + issues.map(i => `- ${i.replace('\n', '\n  ')}`).join('\n'),
-            });
-
-            console.log("➡️ Applying label 'invalid'...");
-            await github.rest.issues.addLabels({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: pr.number,
-              labels: ['invalid'],
-            });
-
-            if (close) {
-              console.log('➡️ Auto-closing PR...');
-              await github.rest.pulls.update({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: pr.number,
-                state: 'closed',
-              });
-            }
-          }
--- a/.github/workflows/autogpt-ci.yml
+++ b/.github/workflows/autogpt-ci.yml
@@ -1,18 +1,18 @@
-name: AutoGPT Python CI
+name: AutoGPT CI

 on:
  push:
    branches: [ master, development, ci-test* ]
    paths:
      - '.github/workflows/autogpt-ci.yml'
-      - 'autogpts/autogpt/**'
-      - '!autogpts/autogpt/tests/vcr_cassettes'
+      - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
  pull_request:
    branches: [ master, development, release-* ]
    paths:
      - '.github/workflows/autogpt-ci.yml'
-      - 'autogpts/autogpt/**'
-      - '!autogpts/autogpt/tests/vcr_cassettes'
+      - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'

 concurrency:
  group: ${{ format('autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -21,60 +21,9 @@ concurrency:
 defaults:
  run:
    shell: bash
-    working-directory: autogpts/autogpt
+    working-directory: autogpt

 jobs:
-  lint:
-    runs-on: ubuntu-latest
-    env:
-      min-python-version: "3.10"
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python ${{ env.min-python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.min-python-version }}
-
-      - id: get_date
-        name: Get date
-        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
-
-      - name: Set up Python dependency cache
-        uses: actions/cache@v4
-        with:
-          path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles('autogpts/autogpt/pyproject.toml') }}-${{ steps.get_date.outputs.date }}
-
-      - name: Install Python dependencies
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          poetry install
-
-      - name: Lint with flake8
-        run: poetry run flake8
-
-      - name: Check black formatting
-        run: poetry run black . --check
-        if: success() || failure()
-
-      - name: Check isort formatting
-        run: poetry run isort . --check
-        if: success() || failure()
-
-      # - name: Check mypy formatting
-      #   run: poetry run mypy
-      #   if: success() || failure()
-
-      # - name: Check for unused imports and pass statements
-      #   run: |
-      #     cmd="autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring autogpt tests"
-      #     poetry run $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)
-
  test:
    permissions:
      contents: read
@@ -170,7 +119,7 @@ jobs:
        uses: actions/cache@v4
        with:
          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('autogpts/autogpt/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt/poetry.lock') }}

      - name: Install Poetry (Unix)
        if: runner.os != 'Windows'
@@ -293,4 +242,4 @@ jobs:
        uses: actions/upload-artifact@v4
        with:
          name: test-logs
-          path: autogpts/autogpt/logs/
+          path: autogpt/logs/
--- a/.github/workflows/autogpt-docker-cache-clean.yml
+++ b/.github/workflows/autogpt-docker-cache-clean.yml
@@ -25,7 +25,7 @@ jobs:
      name: Build image
      uses: docker/build-push-action@v5
      with:
-        context: autogpts/autogpt
+        file: Dockerfile.autogpt
        build-args: BUILD_TYPE=${{ matrix.build-type }}
        load: true    # save to docker images
        # use GHA cache as read-only
--- a/.github/workflows/autogpt-docker-ci.yml
+++ b/.github/workflows/autogpt-docker-ci.yml
@@ -5,14 +5,14 @@ on:
    branches: [ master, development ]
    paths:
      - '.github/workflows/autogpt-docker-ci.yml'
-      - 'autogpts/autogpt/**'
-      - '!autogpts/autogpt/tests/vcr_cassettes'
+      - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
  pull_request:
    branches: [ master, development, release-* ]
    paths:
      - '.github/workflows/autogpt-docker-ci.yml'
-      - 'autogpts/autogpt/**'
-      - '!autogpts/autogpt/tests/vcr_cassettes'
+      - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'

 concurrency:
  group: ${{ format('autogpt-docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
@@ -20,7 +20,7 @@ concurrency:

 defaults:
  run:
-    working-directory: autogpts/autogpt
+    working-directory: autogpt

 env:
  IMAGE_NAME: auto-gpt
@@ -49,7 +49,7 @@ jobs:
      name: Build image
      uses: docker/build-push-action@v5
      with:
-        context: autogpts/autogpt
+        file: Dockerfile.autogpt
        build-args: BUILD_TYPE=${{ matrix.build-type }}
        tags: ${{ env.IMAGE_NAME }}
        labels: GIT_REVISION=${{ github.sha }}
@@ -84,7 +84,6 @@ jobs:
        vars_json: ${{ toJSON(vars) }}

      run: .github/workflows/scripts/docker-ci-summary.sh >> $GITHUB_STEP_SUMMARY
-      working-directory: ./
      continue-on-error: true

  test:
@@ -119,7 +118,7 @@ jobs:
        name: Build image
        uses: docker/build-push-action@v5
        with:
-          context: autogpts/autogpt
+          file: Dockerfile.autogpt
          build-args: BUILD_TYPE=dev  # include pytest
          tags: >
            ${{ env.IMAGE_NAME }},
--- a/.github/workflows/autogpt-docker-release.yml
+++ b/.github/workflows/autogpt-docker-release.yml
@@ -10,10 +10,6 @@ on:
        type: boolean
        description: 'Build from scratch, without using cached layers'

-defaults:
-  run:
-    working-directory: autogpts/autogpt
-
 env:
  IMAGE_NAME: auto-gpt
  DEPLOY_IMAGE_NAME: ${{ secrets.DOCKER_USER }}/auto-gpt
@@ -48,7 +44,7 @@ jobs:
      name: Build image
      uses: docker/build-push-action@v5
      with:
-        context: autogpts/autogpt
+        file: Dockerfile.autogpt
        build-args: BUILD_TYPE=release
        load: true    # save to docker images
        # push: true  # TODO: uncomment when this issue is fixed: https://github.com/moby/buildkit/issues/1555
@@ -87,5 +83,4 @@ jobs:
        vars_json: ${{ toJSON(vars) }}

      run: .github/workflows/scripts/docker-release-summary.sh >> $GITHUB_STEP_SUMMARY
-      working-directory: ./
      continue-on-error: true
--- a/.github/workflows/autogpt-server-ci.yml
+++ b/.github/workflows/autogpt-server-ci.yml
@@ -0,0 +1,268 @@
+name: AutoGPT Server CI
+
+on:
+  push:
+    branches: [master, development, ci-test*]
+    paths:
+      - ".github/workflows/autogpt-server-ci.yml"
+      - "rnd/autogpt_server/**"
+      - "!autogpt/tests/vcr_cassettes"
+  pull_request:
+    branches: [master, development, release-*]
+    paths:
+      - ".github/workflows/autogpt-server-ci.yml"
+      - "rnd/autogpt_server/**"
+      - "!autogpt/tests/vcr_cassettes"
+
+concurrency:
+  group: ${{ format('autogpt-server-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
+
+defaults:
+  run:
+    shell: bash
+    working-directory: rnd/autogpt_server
+
+jobs:
+  test:
+    permissions:
+      contents: read
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
+
+    steps:
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
+        working-directory: "."
+        run: |
+          docker pull minio/minio:edge-cicd
+          docker run -d -p 9000:9000 minio/minio:edge-cicd
+
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('rnd/autogpt_server/poetry.lock') }}
+
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+
+      - name: Install Python dependencies
+        run: poetry install
+
+      - name: Generate Prisma Client
+        run: poetry run prisma generate
+
+      - name: Run Database Migrations
+        run: poetry run prisma migrate dev --name updates
+
+      - name: Run pytest with coverage
+        run: |
+          poetry run pytest -vv \
+            test
+        env:
+          CI: true
+          PLAIN_OUTPUT: True
+
+      # - name: Upload coverage reports to Codecov
+      #   uses: codecov/codecov-action@v4
+      #   with:
+      #     token: ${{ secrets.CODECOV_TOKEN }}
+      #     flags: autogpt-server,${{ runner.os }}
+
+  build:
+    permissions:
+      contents: read
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('rnd/autogpt_server/poetry.lock') }}
+
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+
+      - name: Install Python dependencies
+        run: poetry install
+
+      - name: Generate Prisma Client
+        run: poetry run prisma generate
+
+      - name: Run Database Migrations
+        run: poetry run prisma migrate dev --name updates
+
+      - name: install rpm
+        if: matrix.platform-os == 'ubuntu'
+        run: sudo apt-get install -y alien fakeroot rpm
+
+      - name: Build distribution
+        run: |
+          case "${{ matrix.platform-os }}" in
+            "macos" | "macos-arm64")
+              ${MAC_COMMAND}
+              ;;
+            "windows")
+              ${WINDOWS_COMMAND}
+              ;;
+            *)
+              ${LINUX_COMMAND}
+              ;;
+          esac
+        env:
+          MAC_COMMAND: "poetry run poe dist_dmg"
+          WINDOWS_COMMAND: "poetry run poe dist_msi"
+          LINUX_COMMAND: "poetry run poe dist_appimage"
+
+      # break this into seperate steps each with their own name that matches the file
+      - name: Upload App artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-app-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.app
+
+      - name: Upload dmg artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-dmg-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/AutoGPTServer.dmg
+
+      - name: Upload msi artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-msi-${{ matrix.platform-os }}
+          path: D:\a\AutoGPT\AutoGPT\rnd\autogpt_server\dist\*.msi
+
+      - name: Upload deb artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-deb-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.deb
+
+      - name: Upload rpm artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-rpm-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.rpm
+
+      - name: Upload tar.gz artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-tar.gz-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.tar.gz
+
+      - name: Upload zip artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-zip-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.zip
+
+      - name: Upload pkg artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-pkg-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.pkg
+
+      - name: Upload AppImage artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: autogptserver-AppImage-${{ matrix.platform-os }}
+          path: /Users/runner/work/AutoGPT/AutoGPT/rnd/autogpt_server/build/*.AppImage
--- a/.github/workflows/autogpts-benchmark.yml
+++ b/.github/workflows/autogpts-benchmark.yml
@@ -42,7 +42,7 @@ jobs:
      - name: Benchmark ${{ matrix.agent-name }}
        run: |
          ./run agent start ${{ matrix.agent-name }}
-          cd autogpts/${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}

          set +e  # Do not quit on non-zero exit codes
          poetry run agbenchmark run -N 3 \
--- a/.github/workflows/autogpts-ci.yml
+++ b/.github/workflows/autogpts-ci.yml
@@ -1,4 +1,4 @@
-name: AutoGPTs smoke test CI
+name: Agent smoke tests

 on:
  workflow_dispatch:
@@ -8,7 +8,8 @@ on:
    branches: [ master, development, ci-test* ]
    paths:
      - '.github/workflows/autogpts-ci.yml'
-      - 'autogpts/**'
+      - 'autogpt/**'
+      - 'forge/**'
      - 'benchmark/**'
      - 'run'
      - 'cli.py'
@@ -18,7 +19,8 @@ on:
    branches: [ master, development, release-* ]
    paths:
      - '.github/workflows/autogpts-ci.yml'
-      - 'autogpts/**'
+      - 'autogpt/**'
+      - 'forge/**'
      - 'benchmark/**'
      - 'run'
      - 'cli.py'
@@ -26,11 +28,11 @@ on:
      - '!**/*.md'

 jobs:
-  run-tests:
+  serve-agent-protocol:
    runs-on: ubuntu-latest
    strategy:
      matrix:
-        agent-name: [ autogpt, forge ]
+        agent-name: [ autogpt ]
      fail-fast: false
    timeout-minutes: 20
    env:
@@ -48,14 +50,14 @@ jobs:
          python-version: ${{ env.min-python-version }}

      - name: Install Poetry
-        working-directory: ./autogpts/${{ matrix.agent-name }}/
+        working-directory: ./${{ matrix.agent-name }}/
        run: |
          curl -sSL https://install.python-poetry.org | python -

      - name: Run regression tests
        run: |
          ./run agent start ${{ matrix.agent-name }}
-          cd autogpts/${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}
          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
          poetry run agbenchmark --test=WriteFile
        env:
--- a/.github/workflows/benchmark-ci.yml
+++ b/.github/workflows/benchmark-ci.yml
@@ -1,4 +1,4 @@
-name: Benchmark CI
+name: AGBenchmark CI

 on:
  push:
@@ -14,62 +14,91 @@ on:
      - '!benchmark/reports/**'
      - .github/workflows/benchmark-ci.yml

+concurrency:
+  group: ${{ format('benchmark-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
+
+defaults:
+  run:
+    shell: bash
+
 env:
  min-python-version: '3.10'

 jobs:
-  lint:
-    runs-on: ubuntu-latest
-
+  test:
+    permissions:
+      contents: read
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
+    defaults:
+      run:
+        shell: bash
+        working-directory: benchmark
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
+          submodules: true

-      - name: Set up Python ${{ env.min-python-version }}
+      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
-          python-version: ${{ env.min-python-version }}
+          python-version: ${{ matrix.python-version }}

-      - id: get_date
-        name: Get date
-        working-directory: ./benchmark/
-        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+      - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('benchmark/poetry.lock') }}

-      - name: Install Poetry
-        working-directory: ./benchmark/
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
        run: |
-          curl -sSL https://install.python-poetry.org | python -
+          curl -sSL https://install.python-poetry.org | python3 -

-      - name: Install dependencies
-        working-directory: ./benchmark/
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
        run: |
-          export POETRY_VIRTUALENVS_IN_PROJECT=true
-          poetry install -vvv
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -

-      - name: Lint with flake8
-        working-directory: ./benchmark/
-        run: poetry run flake8
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH

-      - name: Check black formatting
-        working-directory: ./benchmark/
-        run: poetry run  black . --exclude test.py --check
-        if: success() || failure()
+      - name: Install Python dependencies
+        run: poetry install

-      - name: Check isort formatting
-        working-directory: ./benchmark/
-        run: poetry run  isort . --check
-        if: success() || failure()
-
-      - name: Check for unused imports and pass statements
-        working-directory: ./benchmark/
+      - name: Run pytest with coverage
        run: |
-          cmd="poetry run autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring agbenchmark"
-          $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)
-        if: success() || failure()
+          poetry run pytest -vv \
+            --cov=agbenchmark --cov-branch --cov-report term-missing --cov-report xml \
+            --durations=10 \
+            tests
+        env:
+          CI: true
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

-  tests-agbenchmark:
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: agbenchmark,${{ runner.os }}
+
+  self-test-with-agent:
    runs-on: ubuntu-latest
    strategy:
      matrix:
@@ -89,14 +118,14 @@ jobs:
          python-version: ${{ env.min-python-version }}

      - name: Install Poetry
-        working-directory: ./autogpts/${{ matrix.agent-name }}/
        run: |
          curl -sSL https://install.python-poetry.org | python -

      - name: Run regression tests
+        working-directory: .
        run: |
          ./run agent start ${{ matrix.agent-name }}
-          cd autogpts/${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}

          set +e # Ignore non-zero exit codes and continue execution
          echo "Running the following command: poetry run agbenchmark --maintain --mock"
@@ -119,13 +148,12 @@ jobs:

          echo "Running the following command: poetry run agbenchmark --test=WriteFile"
          poetry run agbenchmark --test=WriteFile
-          cd ../../benchmark
+          cd ../benchmark
          poetry install
          echo "Adding the BUILD_SKILL_TREE environment variable. This will attempt to add new elements in the skill tree. If new elements are added, the CI fails because they should have been pushed"
          export BUILD_SKILL_TREE=true

          poetry run agbenchmark --mock
-          poetry run pytest -vv -s tests

          CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../frontend/assets)') || echo "No diffs"
          if [ ! -z "$CHANGED" ]; then
--- a/.github/workflows/forge-ci.yml
+++ b/.github/workflows/forge-ci.yml
@@ -0,0 +1,129 @@
+name: Forge CI
+
+on:
+  push:
+    branches: [ master, development, ci-test* ]
+    paths:
+      - '.github/workflows/forge-ci.yml'
+      - 'forge/**'
+  pull_request:
+    branches: [ master, development, release-* ]
+    paths:
+      - '.github/workflows/forge-ci.yml'
+      - 'forge/**'
+
+concurrency:
+  group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
+
+defaults:
+  run:
+    shell: bash
+    working-directory: forge
+
+jobs:
+  test:
+    permissions:
+      contents: read
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
+
+    steps:
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
+        working-directory: '.'
+        run: |
+          docker pull minio/minio:edge-cicd
+          docker run -d -p 9000:9000 minio/minio:edge-cicd
+
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('forge/poetry.lock') }}
+
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+
+      - name: Install Python dependencies
+        run: poetry install
+
+      - name: Run pytest with coverage
+        run: |
+          poetry run pytest -vv \
+            --cov=forge --cov-branch --cov-report term-missing --cov-report xml \
+            --durations=10 \
+            forge
+        env:
+          CI: true
+          PLAIN_OUTPUT: True
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
+          AWS_ACCESS_KEY_ID: minioadmin
+          AWS_SECRET_ACCESS_KEY: minioadmin
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: forge,${{ runner.os }}
+
+      - name: Upload logs to artifact
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-logs
+          path: forge/logs/
--- a/.github/workflows/hackathon.yml
+++ b/.github/workflows/hackathon.yml
@@ -117,7 +117,7 @@ jobs:
          branch=$(jq -r '.["branch_to_benchmark"]' arena/$AGENT_NAME.json)
          git clone "$link" -b "$branch" "$AGENT_NAME"
          cd $AGENT_NAME
-          cp ./autogpts/$AGENT_NAME/.env.example ./autogpts/$AGENT_NAME/.env || echo "file not found"
+          cp ./$AGENT_NAME/.env.example ./$AGENT_NAME/.env || echo "file not found"
          ./run agent start $AGENT_NAME
          cd ../benchmark
          poetry install
--- a/.github/workflows/ossf-scorecard.yml
+++ b/.github/workflows/ossf-scorecard.yml
@@ -0,0 +1,68 @@
+name: "Security - OSSF Scorecard"
+on:
+  # For Branch-Protection check. Only the default branch is supported. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#branch-protection
+  branch_protection_rule:
+  # To guarantee Maintained check is occasionally updated. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#maintained
+  schedule:
+    - cron: '28 12 * * 2'
+  push:
+    branches: [ "master" ]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Needed to publish results and get a badge (see publish_results below).
+      id-token: write
+      # Uncomment the permissions below if installing in a private repository.
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v3.1.0
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/scorecard-action@e38b1902ae4f44df626f11ba0734b14fb91f8f86 # v2.1.2
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          # (Optional) "write" PAT token. Uncomment the `repo_token` line below if:
+          # - you want to enable the Branch-Protection check on a *public* repository, or
+          # - you are installing Scorecard on a *private* repository
+          # To create the PAT, follow the steps in https://github.com/ossf/scorecard-action#authentication-with-pat.
+          # repo_token: ${{ secrets.SCORECARD_TOKEN }}
+
+          # Public repositories:
+          #   - Publish results to OpenSSF REST API for easy access by consumers
+          #   - Allows the repository to include the Scorecard badge.
+          #   - See https://github.com/ossf/scorecard-action#publishing-results.
+          # For private repositories:
+          #   - `publish_results` will always be set to `false`, regardless
+          #     of the value entered here.
+          publish_results: true
+
+      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
+      # format to the repository Actions tab.
+      - name: "Upload artifact"
+        uses: actions/upload-artifact@3cea5372237819ed00197afe530f5a7ea3e805c8 # v3.1.0
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      # Upload the results to GitHub's code scanning dashboard.
+      - name: "Upload to code-scanning"
+        uses: github/codeql-action/upload-sarif@17573ee1cc1b9d061760f3a006fc4aac4f944fd5 # v2.2.4
+        with:
+          sarif_file: results.sarif
--- a/.github/workflows/pr-label.yml
+++ b/.github/workflows/pr-label.yml
@@ -5,7 +5,7 @@ on:
  push:
    branches: [ master, development, release-* ]
    paths-ignore:
-      - 'autogpts/autogpt/tests/vcr_cassettes'
+      - 'autogpt/tests/vcr_cassettes'
      - 'benchmark/reports/**'
  # So that the `dirtyLabel` is removed if conflicts are resolve
  # We recommend `pull_request_target` so that github secrets are available.
--- a/.github/workflows/python-checks.yml
+++ b/.github/workflows/python-checks.yml
@@ -0,0 +1,151 @@
+name: Python checks
+
+on:
+  push:
+    branches: [ master, development, ci-test* ]
+    paths:
+      - '.github/workflows/lint-ci.yml'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
+      - '**.py'
+      - '!autogpt/tests/vcr_cassettes'
+  pull_request:
+    branches: [ master, development, release-* ]
+    paths:
+      - '.github/workflows/lint-ci.yml'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
+      - '**.py'
+      - '!autogpt/tests/vcr_cassettes'
+
+concurrency:
+  group: ${{ format('lint-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  get-changed-parts:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - id: changes-in
+        name: Determine affected subprojects
+        uses: dorny/paths-filter@v3
+        with:
+          filters: |
+            autogpt:
+              - autogpt/autogpt/**
+              - autogpt/tests/**
+              - autogpt/poetry.lock
+            forge:
+              - forge/forge/**
+              - forge/tests/**
+              - forge/poetry.lock
+            benchmark:
+              - benchmark/agbenchmark/**
+              - benchmark/tests/**
+              - benchmark/poetry.lock
+    outputs:
+      changed-parts: ${{ steps.changes-in.outputs.changes }}
+
+  lint:
+    needs: get-changed-parts
+    runs-on: ubuntu-latest
+    env:
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+
+      - name: Install Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
+
+      # Install dependencies
+
+      - name: Install Python dependencies
+        run: poetry -C ${{ matrix.sub-package }} install
+
+      # Lint
+
+      - name: Lint (isort)
+        run: poetry run isort --check .
+        working-directory: ${{ matrix.sub-package }}
+
+      - name: Lint (Black)
+        if: success() || failure()
+        run: poetry run black --check .
+        working-directory: ${{ matrix.sub-package }}
+
+      - name: Lint (Flake8)
+        if: success() || failure()
+        run: poetry run flake8 .
+        working-directory: ${{ matrix.sub-package }}
+
+  types:
+    needs: get-changed-parts
+    runs-on: ubuntu-latest
+    env:
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+
+      - name: Install Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
+
+      # Install dependencies
+
+      - name: Install Python dependencies
+        run: poetry -C ${{ matrix.sub-package }} install
+
+      # Typecheck
+
+      - name: Typecheck
+        if: success() || failure()
+        run: poetry run pyright
+        working-directory: ${{ matrix.sub-package }}
--- a/.gitignore
+++ b/.gitignore
@@ -6,8 +6,6 @@ auto_gpt_workspace/*
 *.mpeg
 .env
 azure.yaml
-ai_settings.yaml
-last_run_ai_settings.yaml
 .vscode
 .idea/*
 auto-gpt.json
@@ -172,8 +170,3 @@ pri*
 # ignore
 ig*
 .github_access_token
-arena/TestAgent.json
-
-# evo.ninja
-autogpts/evo.ninja/*
-!autogpts/evo.ninja/setup
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,3 +1,3 @@
-[submodule "autogpts/autogpt/tests/vcr_cassettes"]
-	path = autogpts/autogpt/tests/vcr_cassettes
+[submodule "autogpt/tests/vcr_cassettes"]
+	path = autogpt/tests/vcr_cassettes
 	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,127 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-added-large-files
+        args: ["--maxkb=500"]
+      - id: fix-byte-order-marker
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: debug-statements
+
+  - repo: local
+    # isort needs the context of which packages are installed to function, so we
+    # can't use a vendored isort pre-commit hook (which runs in its own isolated venv).
+    hooks:
+      - id: isort-autogpt
+        name: Lint (isort) - AutoGPT
+        entry: poetry -C autogpt run isort
+        files: ^autogpt/
+        types: [file, python]
+        language: system
+
+      - id: isort-forge
+        name: Lint (isort) - Forge
+        entry: poetry -C forge run isort
+        files: ^forge/
+        types: [file, python]
+        language: system
+
+      - id: isort-benchmark
+        name: Lint (isort) - Benchmark
+        entry: poetry -C benchmark run isort
+        files: ^benchmark/
+        types: [file, python]
+        language: system
+
+  - repo: https://github.com/psf/black
+    rev: 23.12.1
+    # Black has sensible defaults, doesn't need package context, and ignores
+    # everything in .gitignore, so it works fine without any config or arguments.
+    hooks:
+      - id: black
+        name: Lint (Black)
+        language_version: python3.10
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 7.0.0
+    # To have flake8 load the config of the individual subprojects, we have to call
+    # them separately.
+    hooks:
+      - id: flake8
+        name: Lint (Flake8) - AutoGPT
+        alias: flake8-autogpt
+        files: ^autogpt/(autogpt|scripts|tests)/
+        args: [--config=autogpt/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Forge
+        alias: flake8-forge
+        files: ^forge/(forge|tests)/
+        args: [--config=forge/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Benchmark
+        alias: flake8-benchmark
+        files: ^benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
+        args: [--config=benchmark/.flake8]
+
+  - repo: local
+    # To have watertight type checking, we check *all* the files in an affected
+    # project. To trigger on poetry.lock we also reset the file `types` filter.
+    hooks:
+      - id: pyright
+        name: Typecheck - AutoGPT
+        alias: pyright-autogpt
+        entry: poetry -C autogpt run pyright
+        args: [-p, autogpt, autogpt]
+        # include forge source (since it's a path dependency) but exclude *_test.py files:
+        files: ^(autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Forge
+        alias: pyright-forge
+        entry: poetry -C forge run pyright
+        args: [-p, forge, forge]
+        files: ^forge/(forge/|poetry\.lock$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Benchmark
+        alias: pyright-benchmark
+        entry: poetry -C benchmark run pyright
+        args: [-p, benchmark, benchmark]
+        files: ^benchmark/(agbenchmark|tests)/
+        types: [file]
+        language: system
+        pass_filenames: false
+
+  - repo: local
+    hooks:
+      - id: pytest-autogpt
+        name: Run tests - AutoGPT (excl. slow tests)
+        entry: bash -c 'cd autogpt && poetry run pytest --cov=autogpt -m "not slow" tests/unit tests/integration'
+        # include forge source (since it's a path dependency) but exclude *_test.py files:
+        files: ^(autogpt/((autogpt|tests)/|poetry\.lock$)|forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
+        language: system
+        pass_filenames: false
+
+      - id: pytest-forge
+        name: Run tests - Forge (excl. slow tests)
+        entry: bash -c 'cd forge && poetry run pytest --cov=forge -m "not slow"'
+        files: ^forge/(forge/|tests/|poetry\.lock$)
+        language: system
+        pass_filenames: false
+
+      - id: pytest-benchmark
+        name: Run tests - Benchmark
+        entry: bash -c 'cd benchmark && poetry run pytest --cov=benchmark'
+        files: ^benchmark/(agbenchmark/|tests/|poetry\.lock$)
+        language: system
+        pass_filenames: false
--- a/CLI-USAGE.md
+++ b/CLI-USAGE.md
@@ -74,7 +74,7 @@ Lists all the available agents.
 **Output**:

 ```
-🎉 New agent 'my_agent' created and switched to the new directory in autogpts folder.
+🎉 New agent 'my_agent' created and switched to the new directory in agents folder.
 ```

 Creates a new agent named 'my_agent'.
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1,34 +1,36 @@
 # AutoGPT Contribution Guide
 If you are reading this, you are probably looking for our **[contribution guide]**,
-which is part of our [knowledge base].
+which is part of our [wiki].

-You can find our immediate priorities and their progress on our public [kanban board].
+Also check out our [🚀 Roadmap][roadmap] for information about our priorities and associated tasks.
+<!-- You can find our immediate priorities and their progress on our public [kanban board]. -->

-[contribution guide]: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
-[knowledge base]: https://github.com/Significant-Gravitas/Nexus/wiki
+[contribution guide]: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing
+[wiki]: https://github.com/Significant-Gravitas/AutoGPT/wiki
+[roadmap]: https://github.com/Significant-Gravitas/AutoGPT/discussions/6971
 [kanban board]: https://github.com/orgs/Significant-Gravitas/projects/1

 ## In short
 1. Avoid duplicate work, issues, PRs etc.
 2. We encourage you to collaborate with fellow community members on some of our bigger
-   [todo's][kanban board]!
+   [todo's][roadmap]!
   * We highly recommend to post your idea and discuss it in the [dev channel].
 4. Create a draft PR when starting work on bigger changes.
 3. Please also consider contributing something other than code; see the
   [contribution guide] for options.
 5. Clearly explain your changes when submitting a PR.
-6. Don't submit stuff that's broken.
+6. Don't submit broken code: test/validate your changes.
 7. Avoid making unnecessary changes, especially if they're purely based on your personal
   preferences. Doing so is the maintainers' job. ;-)

 [dev channel]: https://discord.com/channels/1092243196446249134/1095817829405704305

 If you wish to involve with the project (beyond just contributing PRs), please read the
-wiki [catalyzing](https://github.com/Significant-Gravitas/Nexus/wiki/Catalyzing) page.
+wiki page about [Catalyzing](https://github.com/Significant-Gravitas/AutoGPT/wiki/Catalyzing).

 In fact, why not just look through the whole wiki (it's only a few pages) and
 hop on our Discord. See you there! :-)

-❤️ & 🔆  
-The team @ AutoGPT  
+❤️ & 🔆
+The team @ AutoGPT
 https://discord.gg/autogpt
--- a/autogpts/autogpt/Dockerfile
+++ b/autogpts/autogpt/Dockerfile
@@ -28,8 +28,14 @@ RUN curl -sSL https://install.python-poetry.org | python3 -
 ENV PATH="$POETRY_HOME/bin:$PATH"
 RUN poetry config installer.max-workers 10

-WORKDIR /app
-COPY pyproject.toml poetry.lock ./
+WORKDIR /app/autogpt
+COPY autogpt/pyproject.toml autogpt/poetry.lock ./
+
+# Include forge so it can be used as a path dependency
+COPY forge/ ../forge
+
+# Include frontend
+COPY frontend/ ../frontend

 # Set the entrypoint
 ENTRYPOINT ["poetry", "run", "autogpt"]
@@ -39,17 +45,16 @@ CMD []
 FROM autogpt-base as autogpt-dev
 RUN poetry install --no-cache --no-root \
    && rm -rf $(poetry env info --path)/src
-ONBUILD COPY . ./
+ONBUILD COPY autogpt/ ./

 # release build -> include bare minimum
 FROM autogpt-base as autogpt-release
 RUN poetry install --no-cache --no-root --without dev \
    && rm -rf $(poetry env info --path)/src
-ONBUILD COPY autogpt/ ./autogpt
-ONBUILD COPY scripts/ ./scripts
-ONBUILD COPY plugins/ ./plugins
-ONBUILD COPY prompt_settings.yaml ./prompt_settings.yaml
-ONBUILD COPY README.md ./README.md
+ONBUILD COPY autogpt/autogpt/ ./autogpt
+ONBUILD COPY autogpt/scripts/ ./scripts
+ONBUILD COPY autogpt/plugins/ ./plugins
+ONBUILD COPY autogpt/README.md ./README.md
 ONBUILD RUN mkdir ./data

 FROM autogpt-${BUILD_TYPE} AS autogpt
--- a/QUICKSTART.md
+++ b/QUICKSTART.md
@@ -39,9 +39,6 @@ This project supports Linux (Debian based), Mac, and Windows Subsystem for Linux

    The first command you need to use is `./run setup` This will guide you through the process of setting up your system.
    Initially you will get instructions for installing flutter, chrome and setting up your github access token like the following image:
-
-    > Note: for advanced users. The github access token is only needed for the ./run arena enter command so the system can automatically create a PR
-
    
    ![Setup the Project](docs/content/imgs/quickstart/005_setup.png)

@@ -92,39 +89,15 @@ Tips for naming your agent:
 * Give it its own unique name, or name it after yourself
 * Include an important aspect of your agent in the name, such as its purpose

-Examples: `SwiftyosAssistant`, `PwutsPRAgent`, `Narvis`, `evo.ninja`
+Examples: `SwiftyosAssistant`, `PwutsPRAgent`, `MySuperAgent`

 ![Create an Agent](docs/content/imgs/quickstart/007_create_agent.png)

-### Optional: Entering the Arena
-
-Entering the Arena is an optional step intended for those who wish to actively participate in the agent leaderboard. If you decide to participate, you can enter the Arena by running `./run arena enter YOUR_AGENT_NAME`. This step is not mandatory for the development or testing of your agent.
-
-Entries with names like `agent`, `ExampleAgent`, `test_agent` or `MyExampleGPT` will NOT be merged. We also don't accept copycat entries that use the name of other projects, like `AutoGPT` or `evo.ninja`.
-
-![Enter the Arena](docs/content/imgs/quickstart/008_enter_arena.png)
-
-> **Note**  
-> For advanced users, create a new branch and create a file called YOUR_AGENT_NAME.json in the arena directory. Then commit this and create a PR to merge into the main repo. Only single file entries will be permitted. The json file needs the following format:
-> ```json
-> {
->   "github_repo_url": "https://github.com/Swiftyos/YourAgentName",
->   "timestamp": "2023-09-18T10:03:38.051498",
->   "commit_hash_to_benchmark": "ac36f7bfc7f23ad8800339fa55943c1405d80d5e",
->   "branch_to_benchmark": "master"
-> }
-> ```
-> - `github_repo_url`: the url to your fork
-> - `timestamp`: timestamp of the last update of this file
-> - `commit_hash_to_benchmark`: the commit hash of your entry. You update each time you have an something ready to be officially entered into the hackathon
-> - `branch_to_benchmark`: the branch you are using to develop your agent on, default is master.
-
-
 ## Running your Agent

-Your agent can started using the `./run agent start YOUR_AGENT_NAME`
+Your agent can be started using the command: `./run agent start YOUR_AGENT_NAME`

-This start the agent on `http://localhost:8000/`
+This starts the agent on the URL: `http://localhost:8000/`

 ![Start the Agent](docs/content/imgs/quickstart/009_start_agent.png)

--- a/README.md
+++ b/README.md
@@ -4,7 +4,15 @@
 [![Twitter Follow](https://img.shields.io/twitter/follow/Auto_GPT?style=social)](https://twitter.com/Auto_GPT) &ensp;
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

-**AutoGPT** is the vision of the power of AI accessible to everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters:
+**AutoGPT** is a generalist LLM based AI agent that can autonomously accomplish minor tasks. 
+
+**Examples**:
+
+- Look up and summarize this research paper
+- Write a marketing for food supplements
+- Write a blog post detailing the news in AI
+
+Our mission is to provide the tools, so that you can focus on what matters:

 - 🏗️ **Building** - Lay the foundation for something amazing.
 - 🧪 **Testing** - Fine-tune your agent to perfection.
@@ -18,23 +26,16 @@ Be part of the revolution! **AutoGPT** is here to stay, at the forefront of AI i
 &ensp;|&ensp;
 **🛠️ [Build your own Agent - Quickstart](QUICKSTART.md)**

-## 🥇 Current Best Agent: evo.ninja
-[Current Best Agent]: #-current-best-agent-evoninja
-
-The AutoGPT Arena Hackathon saw [**evo.ninja**](https://github.com/polywrap/evo.ninja) earn the top spot on our Arena Leaderboard, proving itself as the best open-source generalist agent. Try it now at https://evo.ninja!
-
-📈 To challenge evo.ninja, AutoGPT, and others, submit your benchmark run to the [Leaderboard](#-leaderboard), and maybe your agent will be up here next!
-
 ## 🧱 Building blocks

 ### 🏗️ Forge

-**Forge your own agent!** &ndash; Forge is a ready-to-go template for your agent application. All the boilerplate code is already handled, letting you channel all your creativity into the things that set *your* agent apart. All tutorials are located [here](https://medium.com/@aiedge/autogpt-forge-e3de53cc58ec). Components from the [`forge.sdk`](/autogpts/forge/forge/sdk) can also be used individually to speed up development and reduce boilerplate in your agent project.
+**Forge your own agent!** &ndash; Forge is a ready-to-go template for your agent application. All the boilerplate code is already handled, letting you channel all your creativity into the things that set *your* agent apart. All tutorials are located [here](https://medium.com/@aiedge/autogpt-forge-e3de53cc58ec). Components from the [`forge.sdk`](/forge/forge/sdk) can also be used individually to speed up development and reduce boilerplate in your agent project.

-🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpts/forge/tutorials/001_getting_started.md) &ndash;
+🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/forge/tutorials/001_getting_started.md) &ndash;
 This guide will walk you through the process of creating your own agent and using the benchmark and user interface.

-📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpts/forge) about Forge
+📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/forge) about Forge

 ### 🎯 Benchmark

@@ -46,18 +47,11 @@ This guide will walk you through the process of creating your own agent and usin
 &ensp;|&ensp;
 📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/blob/master/benchmark) about the Benchmark

-#### 🏆 [Leaderboard][leaderboard]
-[leaderboard]: https://leaderboard.agpt.co
-
-Submit your benchmark run through the UI and claim your place on the AutoGPT Arena Leaderboard! The best scoring general agent earns the title of **[Current Best Agent]**, and will be adopted into our repo so people can easily run it through the [CLI].
-
-[![Screenshot of the AutoGPT Arena leaderboard](https://github.com/Significant-Gravitas/AutoGPT/assets/12185583/60813392-9ddb-4cca-bb44-b477dbae225d)][leaderboard]
-
 ### 💻 UI

 **Makes agents easy to use!** The `frontend` gives you a user-friendly interface to control and monitor your agents. It connects to agents through the [agent protocol](#-agent-protocol), ensuring compatibility with many agents from both inside and outside of our ecosystem.

-<!-- TODO: instert screenshot of front end -->
+<!-- TODO: insert screenshot of front end -->

 The frontend works out-of-the-box with all agents in the repo. Just use the [CLI] to run your agent of choice!

@@ -78,7 +72,6 @@ Options:

 Commands:
  agent      Commands to create, start and stop agents
-  arena      Commands to enter the arena
  benchmark  Commands to start the benchmark and list tests and categories
  setup      Installs dependencies needed for your system.
 ```
--- a/arena/480bot.json
+++ b/arena/480bot.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/480/AutoGPT",
-    "timestamp": "2023-10-22T06:49:52.536177",
-    "commit_hash_to_benchmark": "16e266c65fb4620a1b1397532c503fa426ec191d",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AGENT_GORDON.json
+++ b/arena/AGENT_GORDON.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/filipjakubowski/AutoGPT",
-    "timestamp": "2023-11-01T17:13:24.272333",
-    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AGENT_JARVIS.json
+++ b/arena/AGENT_JARVIS.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/filipjakubowski/AutoGPT",
-    "timestamp": "2023-11-04T10:13:11.039444",
-    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AI.json
+++ b/arena/AI.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/QingquanBao/AutoGPT",
-    "timestamp": "2023-11-01T16:20:51.086235",
-    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AKBAgent.json
+++ b/arena/AKBAgent.json
@@ -1,7 +0,0 @@
-{
-  "github_repo_url": "https://github.com/imakb/AKBAgent",
-  "timestamp": "2023-10-31T00:03:23.000000",
-  "commit_hash_to_benchmark": "c65b71d51d8f849663172c5a128953b4ca92b2b0",
-  "branch_to_benchmark": "AKBAgent"
-}
-
--- a/arena/ASSISTANT.json
+++ b/arena/ASSISTANT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/hongzzz/AutoGPT",
-    "timestamp": "2023-10-13T03:22:59.347424",
-    "commit_hash_to_benchmark": "38790a27ed2c1b63a301b6a67e7590f2d30de53e",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AUTO_ENGINEER.json
+++ b/arena/AUTO_ENGINEER.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/kaiomagalhaes/AutoGPT",
-    "timestamp": "2023-10-04T15:25:30.458687",
-    "commit_hash_to_benchmark": "1bd85cbc09473c0252928fb849ae8373607d6065",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AUTO_GPT_JON001.json
+++ b/arena/AUTO_GPT_JON001.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/Jonobinsoftware/AutoGPT-Tutorial",
-    "timestamp": "2023-10-10T06:01:23.439061",
-    "commit_hash_to_benchmark": "c77ade5b2f62c5373fc7573e5c45581f003c77a3",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Adtractive_Agent.json
+++ b/arena/Adtractive_Agent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/aivaras-mazylis/AutoGPT",
-    "timestamp": "2023-10-17T13:16:16.327237",
-    "commit_hash_to_benchmark": "1eadc64dc0a693c7c9de77ddaef857f3a36f7950",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AgGPT.json
+++ b/arena/AgGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/althaf004/AutoGPT",
-    "timestamp": "2023-09-26T03:40:03.658369",
-    "commit_hash_to_benchmark": "4a8da53d85d466f2eb325c745a2c03cf88792e7d",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AgentJPark.json
+++ b/arena/AgentJPark.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/againeureka/AutoGPT",
-    "timestamp": "2023-10-12T02:20:01.005361",
-    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AgentKD.json
+++ b/arena/AgentKD.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/kitdesai/AgentKD",
-    "timestamp": "2023-10-14T02:35:09.979434",
-    "commit_hash_to_benchmark": "93e3ec36ed6cd9e5e60585f016ad3bef4e1c52cb",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Ahmad.json
+++ b/arena/Ahmad.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/JawadAbu/AutoGPT.git",
-    "timestamp": "2023-11-05T12:35:35.352028",
-    "commit_hash_to_benchmark": "a1d60878141116641ea864ef6de7ca6142e9534c",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Alfred.json
+++ b/arena/Alfred.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/Shadowless422/Alfred",
-    "timestamp": "2023-10-03T10:42:45.473477",
-    "commit_hash_to_benchmark": "949ab477a87cfb7a3668d7961e9443922081e098",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AlphaCISO.json
+++ b/arena/AlphaCISO.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/alphaciso/AutoGPT",
-    "timestamp": "2023-10-21T08:26:41.961187",
-    "commit_hash_to_benchmark": "415b4ceed1417d0b21d87d7d4ea0cd38943e264f",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AndersLensway.json
+++ b/arena/AndersLensway.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/4nd3rs/AutoGPT",
-    "timestamp": "2023-10-11T11:00:08.150159",
-    "commit_hash_to_benchmark": "57bcbdf45c6c1493a4e5f6a4e72594ea13c10f93",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AntlerTestGPT.json
+++ b/arena/AntlerTestGPT.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/pjw1/AntlerAI", "timestamp": "2023-10-07T11:46:39Z", "commit_hash_to_benchmark": "f81e086e5647370854ec639c531c900775a99207", "branch_to_benchmark": "master"}
--- a/arena/AppleGPT.json
+++ b/arena/AppleGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/Nimit3-droid/AutoGPT",
-    "timestamp": "2023-10-03T11:59:15.495902",
-    "commit_hash_to_benchmark": "d8d7fc4858a8d13407f6d7da360c6b5d398f2175",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AquaAgent.json
+++ b/arena/AquaAgent.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/somnistudio/SomniGPT", "timestamp": "2023-10-06T16:40:14Z", "commit_hash_to_benchmark": "47eb5124fa97187d7f3fa4036e422cd771cf0ae7", "branch_to_benchmark": "master"}
--- a/arena/ArtistManagerGPT.json
+++ b/arena/ArtistManagerGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/AmahAjavon/AutoGPT",
-    "timestamp": "2023-10-28T20:32:15.845741",
-    "commit_hash_to_benchmark": "2bd05827f97e471af798b8c2f04e8772dad101d3",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AskOpie.json
+++ b/arena/AskOpie.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/arunqa/AutoGPT",
-    "timestamp": "2023-09-26T05:13:24.466017",
-    "commit_hash_to_benchmark": "4a8da53d85d466f2eb325c745a2c03cf88792e7d",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Auto.json
+++ b/arena/Auto.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/Nikhil8652/AutoGPT",
-    "timestamp": "2023-10-16T09:12:17.452121",
-    "commit_hash_to_benchmark": "2f79caa6b901d006a78c1ac9e69db4465c0f971a",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AutoGPT-ariel.json
+++ b/arena/AutoGPT-ariel.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/RedTachyon/AutoGPT",
-    "timestamp": "2023-10-21T22:31:30.871023",
-    "commit_hash_to_benchmark": "eda21d51921899756bf866cf5c4d0f2dcd3e2e23",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AutoGPT2.json
+++ b/arena/AutoGPT2.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/SarahGrevy/AutoGPT", "timestamp": "2023-10-20T17:21:22Z", "commit_hash_to_benchmark": "32300906c9aafea8c550fa2f9edcc113fbfc512c", "branch_to_benchmark": "master"}
--- a/arena/AutoGenius.json
+++ b/arena/AutoGenius.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/JasonDRZ/AutoGPT",
-    "timestamp": "2023-10-26T13:27:58.805270",
-    "commit_hash_to_benchmark": "ab2a61833584c42ededa805cbac50718c72aa5ae",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AutoTDD.json
+++ b/arena/AutoTDD.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/vshneer/AutoTDD",
-    "timestamp": "2023-10-11T19:14:30.939747",
-    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AutoTestGenerator.json
+++ b/arena/AutoTestGenerator.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/cagdasbas/AutoGPT",
-    "timestamp": "2023-10-15T08:43:40.193080",
-    "commit_hash_to_benchmark": "74ee69daf1c0a2603f19bdb1edcfdf1f4e06bcff",
-    "branch_to_benchmark": "master"
-}
--- a/arena/AwareAgent.json
+++ b/arena/AwareAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/LuisLechugaRuiz/AwareAgent",
-    "timestamp": "2023-10-26T10:10:01.481205",
-    "commit_hash_to_benchmark": "c180063dde49af02ed95ec4c019611da0a5540d7",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Bagi_agent.json
+++ b/arena/Bagi_agent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/xpineda/AutoGPT_xabyvng.git",
-    "timestamp": "2023-10-20T09:21:48.837635",
-    "commit_hash_to_benchmark": "2187f66149ffa4bb99f9ca6a11b592fe4d683791",
-    "branch_to_benchmark": "master"
-}
--- a/arena/BanglaSgAgent.json
+++ b/arena/BanglaSgAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/aniruddha-adhikary/AutoGPT",
-    "timestamp": "2023-09-27T15:32:24.056105",
-    "commit_hash_to_benchmark": "6f289e6dfa8246f8993b76c933527f3707b8d7e5",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Baptiste.json
+++ b/arena/Baptiste.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/Baptistecaille/AutoGPT",
-    "timestamp": "2023-10-01T19:44:23.416591",
-    "commit_hash_to_benchmark": "3da29eae45683457131ee8736bedae7e2a74fbba",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Bravo06.json
+++ b/arena/Bravo06.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/jafar-albadarneh/Bravo06GPT", "timestamp": "2023-10-04T23:01:27Z", "commit_hash_to_benchmark": "f8c177b4b0e4ca45a3a104011b866c0415c648f1", "branch_to_benchmark": "master"}
--- a/arena/Brillante-AI.json
+++ b/arena/Brillante-AI.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/dabeer021/Brillante-AI", "timestamp": "2023-10-02T19:05:04Z", "commit_hash_to_benchmark": "163ab75379e1ee7792f50d4d70a1f482ca9cb6a1", "branch_to_benchmark": "master"}
--- a/arena/Bunny.json
+++ b/arena/Bunny.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/razorhasbeen/AutoGPT",
-    "timestamp": "2023-10-03T11:50:56.725628",
-    "commit_hash_to_benchmark": "d8d7fc4858a8d13407f6d7da360c6b5d398f2175",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CCAgent.json
+++ b/arena/CCAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/ccsnow127/AutoGPT",
-    "timestamp": "2023-10-21T13:57:15.131761",
-    "commit_hash_to_benchmark": "e9b64adae9fce180a392c726457e150177e746fb",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CES-GPT.json
+++ b/arena/CES-GPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/ces-sonnguyen/CES-GPT",
-    "timestamp": "2023-10-30T07:45:07.337258",
-    "commit_hash_to_benchmark": "2bd05827f97e471af798b8c2f04e8772dad101d3",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CISLERK.json
+++ b/arena/CISLERK.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/cislerk/AutoGPT",
-    "timestamp": "2023-10-10T18:40:50.718850",
-    "commit_hash_to_benchmark": "c77ade5b2f62c5373fc7573e5c45581f003c77a3",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CONNECTBOT.json
+++ b/arena/CONNECTBOT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/myncow/DocumentAgent.git",
-    "timestamp": "2023-10-31T21:21:28.951345",
-    "commit_hash_to_benchmark": "c65b71d51d8f849663172c5a128953b4ca92b2b0",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CYNO_AGENT.json
+++ b/arena/CYNO_AGENT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/dr1yl/AutoGPT",
-    "timestamp": "2023-10-09T20:01:05.041446",
-    "commit_hash_to_benchmark": "c77ade5b2f62c5373fc7573e5c45581f003c77a3",
-    "branch_to_benchmark": "master"
-}
--- a/arena/ChadGPT.json
+++ b/arena/ChadGPT.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/Ahmad-Alaziz/ChadGPT", "timestamp": "2023-10-26T09:39:35Z", "commit_hash_to_benchmark": "84dd029c011379791a6fec8b148b2982a2ef159e", "branch_to_benchmark": "master"}
--- a/arena/ChrisGPT.json
+++ b/arena/ChrisGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/darkcyber-ninja/AutoGPT",
-    "timestamp": "2023-10-31T17:55:41.458834",
-    "commit_hash_to_benchmark": "c65b71d51d8f849663172c5a128953b4ca92b2b0",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CodeAutoGPT.json
+++ b/arena/CodeAutoGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/hugomastromauro/AutoGPT",
-    "timestamp": "2023-11-01T13:21:42.624202",
-    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
-    "branch_to_benchmark": "master"
-}
--- a/arena/CreaitorMarketing.json
+++ b/arena/CreaitorMarketing.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/simonfunk/Auto-GPT", "timestamp": "2023-10-08T02:10:18Z", "commit_hash_to_benchmark": "e99e9b6181f091a9625ef9b922dac15dd5f0a885", "branch_to_benchmark": "master"}
--- a/arena/CurieAssistant.json
+++ b/arena/CurieAssistant.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/HMDCrew/AutoGPT",
-    "timestamp": "2023-10-06T20:41:26.293944",
-    "commit_hash_to_benchmark": "9e353e09b5df39d4d410bef57cf17387331e96f6",
-    "branch_to_benchmark": "master"
-}
--- a/arena/DE.json
+++ b/arena/DE.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/wic0144/AutoGPT",
-    "timestamp": "2023-10-26T09:05:21.013962",
-    "commit_hash_to_benchmark": "89d333f3bb422495f21e04bdd2bba3cb8c1a34ae",
-    "branch_to_benchmark": "master"
-}
--- a/arena/DavidsAgent.json
+++ b/arena/DavidsAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/beisdog/AutoGPT",
-    "timestamp": "2023-09-29T22:06:18.846082",
-    "commit_hash_to_benchmark": "d6abb27db61142a70defd0c75b53985ea9a71fce",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Derpmaster.json
+++ b/arena/Derpmaster.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/schumacher-m/Derpmaster",
-    "timestamp": "2023-10-30T21:10:27.407732",
-    "commit_hash_to_benchmark": "d9fbd26b8563e5f59d705623bae0d5cf9c9499c7",
-    "branch_to_benchmark": "master"
-}
--- a/arena/DevOpsAgent.json
+++ b/arena/DevOpsAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/rahuldotar/AutoGPT",
-    "timestamp": "2023-10-02T11:34:29.870077",
-    "commit_hash_to_benchmark": "062d286c239dc863ede4ad475d7348698722f5fa",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Drench.json
+++ b/arena/Drench.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/MohamedBasueny/AutoGPT-Drench",
-    "timestamp": "2023-10-27T01:28:13.869318",
-    "commit_hash_to_benchmark": "21b809794a90cf6f9a6aa41f179f420045becadc",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Eduardo.json
+++ b/arena/Eduardo.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/MuriloEduardo/AutoGPT.git",
-    "timestamp": "2023-09-25T03:18:20.659056",
-    "commit_hash_to_benchmark": "ffa76c3a192c36827669335de4390262da5fd972",
-    "branch_to_benchmark": "master"
-}
--- a/arena/EmbeddedAg.json
+++ b/arena/EmbeddedAg.json
@@ -1 +0,0 @@
-{"github_repo_url": "https://github.com/Significant-Gravitas/AutoGPT", "timestamp": "2023-10-26T09:15:50Z", "commit_hash_to_benchmark": "6c9152a95c8994898c47c85ea90ba58e0cc02c28", "branch_to_benchmark": "master"}
--- a/arena/EnglishTestpaperAgent.json
+++ b/arena/EnglishTestpaperAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/kyannai/AutoGPT",
-    "timestamp": "2023-09-29T03:05:45.504690",
-    "commit_hash_to_benchmark": "1f367618edf903f38dff4dd064f96e611ffc5242",
-    "branch_to_benchmark": "master"
-}
--- a/arena/ExampleAgent.json
+++ b/arena/ExampleAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/janekdijkstra/AutoGPT",
-    "timestamp": "2023-10-16T12:12:54.998033",
-    "commit_hash_to_benchmark": "2f79caa6b901d006a78c1ac9e69db4465c0f971a",
-    "branch_to_benchmark": "master"
-}
--- a/arena/FLASH.json
+++ b/arena/FLASH.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/flashdumper/AutoGPT",
-    "timestamp": "2023-10-30T23:02:13.653861",
-    "commit_hash_to_benchmark": "d9fbd26b8563e5f59d705623bae0d5cf9c9499c7",
-    "branch_to_benchmark": "master"
-}
--- a/arena/FactoryGPT.json
+++ b/arena/FactoryGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/neilmartindev/FactoryGPT",
-    "timestamp": "2023-10-04T16:24:58.525870",
-    "commit_hash_to_benchmark": "1bd85cbc09473c0252928fb849ae8373607d6065",
-    "branch_to_benchmark": "master"
-}
--- a/arena/FcsummerGPT.json
+++ b/arena/FcsummerGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/fbk111/FcsummerGPT",
-    "timestamp": "2023-10-25T09:58:39.801277",
-    "commit_hash_to_benchmark": "ab362f96c3255052350e8e8081b363c7b97ffd6f",
-    "branch_to_benchmark": "master"
-}
--- a/arena/FynAgent.json
+++ b/arena/FynAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/tomkat-cr/AutoGPT.git",
-    "timestamp": "2023-10-18T09:41:21.282992",
-    "commit_hash_to_benchmark": "e9b64adae9fce180a392c726457e150177e746fb",
-    "branch_to_benchmark": "master"
-}
--- a/arena/GG.json
+++ b/arena/GG.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/IgorCIs/AutoGPT",
-    "timestamp": "2023-09-27T14:01:20.964953",
-    "commit_hash_to_benchmark": "a14aadd91493886663232bfd23c0412609f2a2fc",
-    "branch_to_benchmark": "master"
-}
--- a/arena/GPTTest.json
+++ b/arena/GPTTest.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/h3llix/GPTTest.git",
-    "timestamp": "2023-11-02T10:56:53.142288",
-    "commit_hash_to_benchmark": "d9ec0ac3ad7b48eb44e6403e88d2dc5696fd4950",
-    "branch_to_benchmark": "master"
-}
--- a/arena/GameSoundGPT.json
+++ b/arena/GameSoundGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/mordvinov/AutoGPT",
-    "timestamp": "2023-10-13T14:48:02.852293",
-    "commit_hash_to_benchmark": "93e3ec36ed6cd9e5e60585f016ad3bef4e1c52cb",
-    "branch_to_benchmark": "master"
-}
--- a/arena/GeorgeGPT.json
+++ b/arena/GeorgeGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/norn93/GeorgeGPT",
-    "timestamp": "2023-10-17T14:38:41.051458",
-    "commit_hash_to_benchmark": "1eadc64dc0a693c7c9de77ddaef857f3a36f7950",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Granger.json
+++ b/arena/Granger.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/balloch/AutoGPTProblemSolver",
-    "timestamp": "2023-09-29T15:11:44.876627",
-    "commit_hash_to_benchmark": "9fb6d5bbbd6928402a5718b8c249811c6f682a88",
-    "branch_to_benchmark": "master"
-}
--- a/arena/HACKATHON.json
+++ b/arena/HACKATHON.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/manuel-soria/AutoGPT",
-    "timestamp": "2023-10-07T16:55:38.741776",
-    "commit_hash_to_benchmark": "a00d880a3fd62373f53a0b0a45c9dcfdb45968e4",
-    "branch_to_benchmark": "master"
-}
--- a/arena/HMD2.json
+++ b/arena/HMD2.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/HMDCrew/AutoGPT",
-    "timestamp": "2023-10-09T08:46:37.457740",
-    "commit_hash_to_benchmark": "9e353e09b5df39d4d410bef57cf17387331e96f6",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Heisenberg.json
+++ b/arena/Heisenberg.json
@@ -1,6 +0,0 @@
-{
- "github_repo_url": "https://github.com/georgehaws/Heisenberg",
- "timestamp": "2023-10-02T16:07:18-07:00",
- "commit_hash_to_benchmark": "949ab477a87cfb7a3668d7961e9443922081e098",
- "branch_to_benchmark": "master"
-}
--- a/arena/HekolcuAutoGPT.json
+++ b/arena/HekolcuAutoGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/hekolcu/AutoGPT",
-    "timestamp": "2023-09-30T17:31:20.979122",
-    "commit_hash_to_benchmark": "a0fba5d1f13d35a1c4a8b7718550677bf62b5101",
-    "branch_to_benchmark": "master"
-}
--- a/arena/HuitzilAiAgent.json
+++ b/arena/HuitzilAiAgent.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/codetitlan/AutoGPT-CDTHB",
-    "timestamp": "2023-10-03T15:04:54.856291",
-    "commit_hash_to_benchmark": "3374fd181852d489e51ee33a25d12a064a0bb55d",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Hypeman.json
+++ b/arena/Hypeman.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/kennyu/KenGPT",
-    "timestamp": "2023-09-27T19:50:31.443494",
-    "commit_hash_to_benchmark": "cf630e4f2cee04fd935612f95308322cd9eb1df7",
-    "branch_to_benchmark": "master"
-}
--- a/arena/IncredibubbleTea.json
+++ b/arena/IncredibubbleTea.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/mariepop13/AutoGPT",
-    "timestamp": "2023-10-25T18:38:32.012583",
-    "commit_hash_to_benchmark": "ab362f96c3255052350e8e8081b363c7b97ffd6f",
-    "branch_to_benchmark": "master"
-}
--- a/arena/JackGPT.json
+++ b/arena/JackGPT.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/JackDance/AutoGPT",
-    "timestamp": "2023-10-09T08:26:35.181112",
-    "commit_hash_to_benchmark": "f77d383a9f5e66a35d6008bd43cab4d93999cb61",
-    "branch_to_benchmark": "master"
-}
--- a/arena/Jarvis.json
+++ b/arena/Jarvis.json
@@ -1,6 +0,0 @@
-{
-    "github_repo_url": "https://github.com/elynch303/AutoGPT",
-    "timestamp": "2023-10-12T14:15:17.014333",
-    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
-    "branch_to_benchmark": "master"
-}
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				`{"github_repo_url": "https://github.com/pjw1/AntlerAI", "timestamp": "2023-10-07T11:46:39Z", "commit_hash_to_benchmark": "f81e086e5647370854ec639c531c900775a99207", "branch_to_benchmark": "master"}`