Merge branch 'master' into bringing-in-the-benchmark

- Added GAIA_1 category to existing categories in data_types.py
- Added GAIA_2 category to existing categories in data_types.py
- Added GAIA_3 category to existing categories in data_types.py

.dockerignore

@@ -1,28 +0,0 @@
-# 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__

.gitattributes

@@ -1,5 +1,3 @@
-frontend/build/** linguist-generated
+frontend/build/* linguist-generated
 
 **/poetry.lock linguist-generated
-
-docs/_javascript/** linguist-vendored

.github/CODEOWNERS

@@ -1,5 +1,5 @@
-.github/workflows/  @Significant-Gravitas/devops
-autogpt/   @Significant-Gravitas/maintainers
-forge/     @Significant-Gravitas/forge-maintainers
-benchmark/          @Significant-Gravitas/benchmark-maintainers
-frontend/           @Significant-Gravitas/frontend-maintainers
+.github/workflows/  @Significant-Gravitas/maintainers
+autogpts/autogpt/   @Pwuts
+benchmark/  @Significant-Gravitas/benchmarkers
+forge/      @Swiftyos
+frontend/   @hunteraraujo

.github/ISSUE_TEMPLATE/1.bug.yml

@@ -90,7 +90,7 @@ body:
     attributes:
       label: Do you use OpenAI GPT-3 or GPT-4?
       description: >
-        If you are using AutoGPT with `SMART_LLM=gpt-3.5-turbo`, your problems may be caused by
+        If you are using AutoGPT with `--gpt3only`, 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

.github/labeler.yml

@@ -1,19 +0,0 @@
-AutoGPT Agent:
-- changed-files:
-  - any-glob-to-any-file: autogpt/**
-
-Forge:
-- changed-files:
-  - any-glob-to-any-file: forge/**
-
-Benchmark:
-- changed-files:
-  - any-glob-to-any-file: benchmark/**
-
-Frontend:
-- changed-files:
-  - any-glob-to-any-file: frontend/**
-
-documentation:
-- changed-files:
-  - any-glob-to-any-file: docs/**

.github/workflows/autogpt-ci.yml

@@ -1,18 +1,18 @@
-name: AutoGPT CI
+name: AutoGPT Python CI
 
 on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
       - '.github/workflows/autogpt-ci.yml'
-      - 'autogpt/**'
-      - '!autogpt/tests/vcr_cassettes'
+      - 'autogpts/autogpt/**'
+      - '!autogpts/autogpt/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/autogpt-ci.yml'
-      - 'autogpt/**'
-      - '!autogpt/tests/vcr_cassettes'
+      - 'autogpts/autogpt/**'
+      - '!autogpts/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) }}
@@ -20,50 +20,81 @@ concurrency:
 
 defaults:
   run:
-    shell: bash
-    working-directory: autogpt
+    working-directory: autogpts/autogpt
 
 jobs:
+  lint:
+    runs-on: ubuntu-latest
+    env:
+      min-python-version: "3.10"
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v4
+        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@v3
+        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
+    runs-on: ubuntu-latest
     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' }}
+
+    services:
+      minio:
+        image: minio/minio:edge-cicd
+        ports:
+          - 9000:9000
+        options: >
+          --health-interval=10s --health-timeout=5s --health-retries=3
+          --health-cmd="curl -f http://localhost:9000/minio/health/live"
 
     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
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
           submodules: true
@@ -105,7 +136,7 @@ jobs:
           fi
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -114,34 +145,15 @@ jobs:
         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
+        uses: actions/cache@v3
         with:
-          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt/poetry.lock') }}
-
-      - name: Install Poetry (Unix)
-        if: runner.os != 'Windows'
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-
-          if [ "${{ 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
+          path: ~/.cache/pypoetry
+          key: ${{ runner.os }}-poetry-${{ hashFiles('autogpts/autogpt/pyproject.toml') }}-${{ steps.get_date.outputs.date }}
 
       - name: Install Python dependencies
-        run: poetry install
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+          poetry install
 
       - name: Run pytest with coverage
         run: |
@@ -153,15 +165,12 @@ jobs:
           CI: true
           PLAIN_OUTPUT: True
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
+          S3_ENDPOINT_URL: http://localhost:9000
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v4
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: autogpt-agent,${{ runner.os }}
+        uses: codecov/codecov-action@v3
 
       - id: setup_git_auth
         name: Set up git token authentication
@@ -169,11 +178,7 @@ jobs:
         if: success() || failure()
         run: |
           config_key="http.${{ github.server_url }}/.extraheader"
-          if [ "${{ runner.os }}" = 'macOS' ]; then
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
-          else
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
-          fi
+          base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
 
           git config "$config_key" \
             "Authorization: Basic $base64_pat"
@@ -234,12 +239,12 @@ jobs:
             echo "Adding label and comment..."
             echo $TOKEN | gh auth login --with-token
             gh issue edit $PR_NUMBER --add-label "behaviour change"
-            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
           fi
 
       - name: Upload logs to artifact
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: test-logs
-          path: autogpt/logs/
+          path: autogpts/autogpt/logs/

.github/workflows/autogpt-docker-cache-clean.yml

@@ -16,16 +16,16 @@ jobs:
         build-type: [release, dev]
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v2
 
     - id: build
       name: Build image
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v3
       with:
-        file: Dockerfile.autogpt
+        context: autogpts/autogpt
         build-args: BUILD_TYPE=${{ matrix.build-type }}
         load: true    # save to docker images
         # use GHA cache as read-only

.github/workflows/autogpt-docker-ci.yml

@@ -5,14 +5,14 @@ on:
     branches: [ master, development ]
     paths:
       - '.github/workflows/autogpt-docker-ci.yml'
-      - 'autogpt/**'
-      - '!autogpt/tests/vcr_cassettes'
+      - 'autogpts/autogpt/**'
+      - '!autogpts/autogpt/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/autogpt-docker-ci.yml'
-      - 'autogpt/**'
-      - '!autogpt/tests/vcr_cassettes'
+      - 'autogpts/autogpt/**'
+      - '!autogpts/autogpt/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('autogpt-docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
@@ -20,11 +20,11 @@ concurrency:
 
 defaults:
   run:
-    working-directory: autogpt
+    working-directory: autogpts/autogpt
 
 env:
   IMAGE_NAME: auto-gpt
-  DEPLOY_IMAGE_NAME: ${{ secrets.DOCKER_USER && format('{0}/', secrets.DOCKER_USER) || '' }}auto-gpt
+  DEPLOY_IMAGE_NAME: ${{ secrets.DOCKER_USER }}/auto-gpt
   DEV_IMAGE_TAG: latest-dev
 
 jobs:
@@ -35,10 +35,10 @@ jobs:
         build-type: [release, dev]
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v2
 
     - if: runner.debug
       run: |
@@ -47,12 +47,11 @@ jobs:
 
     - id: build
       name: Build image
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v3
       with:
-        file: Dockerfile.autogpt
+        context: autogpts/autogpt
         build-args: BUILD_TYPE=${{ matrix.build-type }}
         tags: ${{ env.IMAGE_NAME }}
-        labels: GIT_REVISION=${{ github.sha }}
         load: true    # save to docker images
         # cache layers in GitHub Actions cache to speed up builds
         cache-from: type=gha,scope=autogpt-docker-${{ matrix.build-type }}
@@ -84,6 +83,7 @@ jobs:
         vars_json: ${{ toJSON(vars) }}
 
       run: .github/workflows/scripts/docker-ci-summary.sh >> $GITHUB_STEP_SUMMARY
+      working-directory: ./
       continue-on-error: true
 
   test:
@@ -100,30 +100,28 @@ jobs:
 
     steps:
       - name: Check out repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           submodules: true
 
-      - if: github.event_name == 'push'
-        name: Log in to Docker hub
-        uses: docker/login-action@v3
+      - name: Log in to Docker hub
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKER_USER }}
           password: ${{ secrets.DOCKER_PASSWORD }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v2
 
       - id: build
         name: Build image
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v3
         with:
-          file: Dockerfile.autogpt
+          context: autogpts/autogpt
           build-args: BUILD_TYPE=dev  # include pytest
           tags: >
             ${{ env.IMAGE_NAME }},
             ${{ env.DEPLOY_IMAGE_NAME }}:${{ env.DEV_IMAGE_TAG }}
-          labels: GIT_REVISION=${{ github.sha }}
           load: true                  # save to docker images
           # cache layers in GitHub Actions cache to speed up builds
           cache-from: type=gha,scope=autogpt-docker-dev

.github/workflows/autogpt-docker-release.yml

@@ -10,6 +10,10 @@ 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
@@ -20,16 +24,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
 
     - name: Log in to Docker hub
-      uses: docker/login-action@v3
+      uses: docker/login-action@v2
       with:
         username: ${{ secrets.DOCKER_USER }}
         password: ${{ secrets.DOCKER_PASSWORD }}
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v2
 
       # slashes are not allowed in image tags, but can appear in git branch or tag names
     - id: sanitize_tag
@@ -42,9 +46,9 @@ jobs:
 
     - id: build
       name: Build image
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v3
       with:
-        file: Dockerfile.autogpt
+        context: autogpts/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
@@ -52,7 +56,6 @@ jobs:
           ${{ env.IMAGE_NAME }},
           ${{ env.DEPLOY_IMAGE_NAME }}:latest,
           ${{ env.DEPLOY_IMAGE_NAME }}:${{ steps.sanitize_tag.outputs.tag }}
-        labels: GIT_REVISION=${{ github.sha }}
 
         # cache layers in GitHub Actions cache to speed up builds
         cache-from: ${{ !inputs.no_cache && 'type=gha' || '' }},scope=autogpt-docker-release
@@ -83,4 +86,5 @@ jobs:
         vars_json: ${{ toJSON(vars) }}
 
       run: .github/workflows/scripts/docker-release-summary.sh >> $GITHUB_STEP_SUMMARY
+      working-directory: ./
       continue-on-error: true

.github/workflows/autogpts-benchmark.yml

@@ -1,97 +0,0 @@
-name: AutoGPTs Nightly Benchmark
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: '0 2 * * *'
-
-jobs:
-  benchmark:
-    permissions:
-      contents: write
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        agent-name: [ autogpt ]
-      fail-fast: false
-    timeout-minutes: 120
-    env:
-      min-python-version: '3.10'
-      REPORTS_BRANCH: data/benchmark-reports
-      REPORTS_FOLDER: ${{ format('benchmark/reports/{0}', matrix.agent-name) }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          submodules: true
-
-      - name: Set up Python ${{ env.min-python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.min-python-version }}
-
-      - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python -
-
-      - name: Prepare reports folder
-        run: mkdir -p ${{ env.REPORTS_FOLDER }}
-
-      - run: poetry -C benchmark install
-
-      - name: Benchmark ${{ matrix.agent-name }}
-        run: |
-          ./run agent start ${{ matrix.agent-name }}
-          cd ${{ matrix.agent-name }}
-
-          set +e  # Do not quit on non-zero exit codes
-          poetry run agbenchmark run -N 3 \
-            --test=ReadFile \
-            --test=BasicRetrieval --test=RevenueRetrieval2 \
-            --test=CombineCsv --test=LabelCsv --test=AnswerQuestionCombineCsv \
-            --test=UrlShortener --test=TicTacToe --test=Battleship \
-            --test=WebArenaTask_0 --test=WebArenaTask_21 --test=WebArenaTask_124 \
-            --test=WebArenaTask_134 --test=WebArenaTask_163
-
-            # Convert exit code 1 (some challenges failed) to exit code 0
-            if [ $? -eq 0 ] || [ $? -eq 1 ]; then
-              exit 0
-            else
-              exit $?
-            fi
-        env:
-          AGENT_NAME: ${{ matrix.agent-name }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
-          REPORTS_FOLDER: ${{ format('../../{0}', env.REPORTS_FOLDER) }}  # account for changed workdir
-
-          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}
-
-      - name: Push reports to data branch
-        run: |
-          # BODGE: Remove success_rate.json and regression_tests.json to avoid conflicts on checkout
-          rm ${{ env.REPORTS_FOLDER }}/*.json
-
-          # Find folder with newest (untracked) report in it
-          report_subfolder=$(find ${{ env.REPORTS_FOLDER }} -type f -name 'report.json' \
-            | xargs -I {} dirname {} \
-            | xargs -I {} git ls-files --others --exclude-standard {} \
-            | xargs -I {} dirname {} \
-            | sort -u)
-          json_report_file="$report_subfolder/report.json"
-
-          # Convert JSON report to Markdown
-          markdown_report_file="$report_subfolder/report.md"
-          poetry -C benchmark run benchmark/reports/format.py "$json_report_file" > "$markdown_report_file"
-          cat "$markdown_report_file" >> $GITHUB_STEP_SUMMARY
-
-          git config --global user.name 'GitHub Actions'
-          git config --global user.email 'github-actions@agpt.co'
-          git fetch origin ${{ env.REPORTS_BRANCH }}:${{ env.REPORTS_BRANCH }} \
-            && git checkout ${{ env.REPORTS_BRANCH }} \
-            || git checkout --orphan ${{ env.REPORTS_BRANCH }}
-          git reset --hard
-          git add ${{ env.REPORTS_FOLDER }}
-          git commit -m "Benchmark report for ${{ matrix.agent-name }} @ $(date +'%Y-%m-%d')" \
-            && git push origin ${{ env.REPORTS_BRANCH }}

.github/workflows/autogpts-ci.yml

@@ -1,4 +1,4 @@
-name: Agent smoke tests
+name: AutoGPTs smoke test CI
 
 on:
   workflow_dispatch:
@@ -8,8 +8,7 @@ on:
     branches: [ master, development, ci-test* ]
     paths:
       - '.github/workflows/autogpts-ci.yml'
-      - 'autogpt/**'
-      - 'forge/**'
+      - 'autogpts/**'
       - 'benchmark/**'
       - 'run'
       - 'cli.py'
@@ -19,8 +18,7 @@ on:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/autogpts-ci.yml'
-      - 'autogpt/**'
-      - 'forge/**'
+      - 'autogpts/**'
       - 'benchmark/**'
       - 'run'
       - 'cli.py'
@@ -28,44 +26,43 @@ on:
       - '!**/*.md'
 
 jobs:
-  serve-agent-protocol:
+  run-tests:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        agent-name: [ autogpt ]
+        agent-name: [ autogpt, forge ]
       fail-fast: false
     timeout-minutes: 20
     env:
       min-python-version: '3.10'
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
           submodules: true
 
       - name: Set up Python ${{ env.min-python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v2
         with:
           python-version: ${{ env.min-python-version }}
 
       - name: Install Poetry
-        working-directory: ./${{ matrix.agent-name }}/
+        working-directory: ./autogpts/${{ matrix.agent-name }}/
         run: |
           curl -sSL https://install.python-poetry.org | python -
 
       - name: Run regression tests
         run: |
           ./run agent start ${{ matrix.agent-name }}
-          cd ${{ matrix.agent-name }}
-          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
+          cd autogpts/${{ matrix.agent-name }}
+          poetry run agbenchmark --mock
           poetry run agbenchmark --test=WriteFile
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           AGENT_NAME: ${{ matrix.agent-name }}
+          HELICONE_API_KEY: ${{ secrets.HELICONE_API_KEY }}
           REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
           HELICONE_CACHE_ENABLED: false
           HELICONE_PROPERTY_AGENT: ${{ matrix.agent-name }}
-          REPORTS_FOLDER: ${{ format('../../reports/{0}', matrix.agent-name) }}
-          TELEMETRY_ENVIRONMENT: autogpt-ci
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}
+          REPORT_LOCATION: ${{ format('../../reports/{0}', matrix.agent-name) }}

.github/workflows/benchmark-ci.yml

@@ -1,4 +1,4 @@
-name: AGBenchmark CI
+name: Benchmark CI
 
 on:
   push:
@@ -14,91 +14,62 @@ 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:
-  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
+  lint:
+    runs-on: ubuntu-latest
+
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
-          submodules: true
 
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v2
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ env.min-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 }}-${{ hashFiles('benchmark/poetry.lock') }}
+      - id: get_date
+        name: Get date
+        working-directory: ./benchmark/
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
-      - name: Install Poetry (Unix)
-        if: runner.os != 'Windows'
+      - name: Install Poetry
+        working-directory: ./benchmark/
         run: |
-          curl -sSL https://install.python-poetry.org | python3 -
+          curl -sSL https://install.python-poetry.org | python -
 
-          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
+      - name: Install dependencies
+        working-directory: ./benchmark/
         run: |
-          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+          export POETRY_VIRTUALENVS_IN_PROJECT=true
+          poetry install -vvv
 
-          $env:PATH += ";$env:APPDATA\Python\Scripts"
-          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+      - name: Lint with flake8
+        working-directory: ./benchmark/
+        run: poetry run flake8
 
-      - name: Install Python dependencies
-        run: poetry install
+      - name: Check black formatting
+        working-directory: ./benchmark/
+        run: poetry run  black . --exclude test.py --check
+        if: success() || failure()
 
-      - name: Run pytest with coverage
+      - 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/
         run: |
-          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 }}
+          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()
 
-      - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v4
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: agbenchmark,${{ runner.os }}
-
-  self-test-with-agent:
+  tests-agbenchmark:
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -107,28 +78,29 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
           submodules: true
 
       - name: Set up Python ${{ env.min-python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v2
         with:
           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 ${{ matrix.agent-name }}
-
+          sleep 10
+          cd autogpts/${{ matrix.agent-name }}
           set +e # Ignore non-zero exit codes and continue execution
           echo "Running the following command: poetry run agbenchmark --maintain --mock"
+
           poetry run agbenchmark --maintain --mock
           EXIT_CODE=$?
           set -e  # Stop ignoring non-zero exit codes
@@ -148,13 +120,14 @@ 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
             echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
@@ -165,5 +138,3 @@ jobs:
           fi
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/benchmark_publish_package.yml

@@ -10,13 +10,13 @@ jobs:
       contents: write
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v2
       with:
         submodules: true
         fetch-depth: 0
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v2
       with:
         python-version: 3.8
 

.github/workflows/build-frontend.yml

@@ -0,0 +1,46 @@
+name: Build and Commit Frontend
+
+on:
+  push:
+    branches:
+      - master
+      - development
+      - 'ci-test*' # This will match any branch that starts with "ci-test"
+    paths:
+      - 'frontend/**'
+
+jobs:
+  build:
+    permissions:
+      contents: write
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout Repo
+      uses: actions/checkout@v2
+    - name: Setup Flutter
+      uses: subosito/flutter-action@v1
+      with:
+        flutter-version: '3.13.2'
+    - name: Build Flutter Web
+      run: |
+        cd frontend
+        flutter build web --base-href /app/
+    - name: Set branch name
+      id: vars
+      run: echo "::set-output name=branch::frontend_build_${GITHUB_SHA}"
+    - name: Commit and Push
+      run: |
+        git config --local user.email "action@github.com"
+        git config --local user.name "GitHub Action"
+        git add frontend/build/web
+        git commit -m "Update frontend build" -a
+        git checkout -b ${{ steps.vars.outputs.branch }}
+        echo "Commit hash: ${GITHUB_SHA}"
+        git push origin ${{ steps.vars.outputs.branch }}
+    # - name: Create Pull Request
+    #   uses: peter-evans/create-pull-request@v3
+    #   with:
+    #     title: "Update frontend build"
+    #     body: "This PR updates the frontend build."
+    #     branch: ${{ steps.vars.outputs.branch }}
+    #     base: "master"

.github/workflows/close-stale-issues.yml

@@ -11,7 +11,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v9
+      - uses: actions/stale@v8
         with:
           # operations-per-run: 5000
           stale-issue-message: >

.github/workflows/forge-ci.yml

@@ -1,129 +0,0 @@
-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/

.github/workflows/frontend-ci.yml

@@ -1,60 +0,0 @@
-name: Frontend CI/CD
-
-on:
-  push:
-    branches:
-      - master
-      - development
-      - 'ci-test*' # This will match any branch that starts with "ci-test"
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/frontend-ci.yml'
-  pull_request:
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/frontend-ci.yml'
-
-jobs:
-  build:
-    permissions:
-      contents: write
-      pull-requests: write
-    runs-on: ubuntu-latest
-    env:
-      BUILD_BRANCH: ${{ format('frontend-build/{0}', github.ref_name) }}
-
-    steps:
-    - name: Checkout Repo
-      uses: actions/checkout@v4
-
-    - name: Setup Flutter
-      uses: subosito/flutter-action@v2
-      with:
-        flutter-version: '3.13.2'
-
-    - name: Build Flutter to Web
-      run: |
-        cd frontend
-        flutter build web --base-href /app/
-
-    # - name: Commit and Push to ${{ env.BUILD_BRANCH }}
-    #   if: github.event_name == 'push'
-    #   run: |
-    #     git config --local user.email "action@github.com"
-    #     git config --local user.name "GitHub Action"
-    #     git add frontend/build/web
-    #     git checkout -B ${{ env.BUILD_BRANCH }}
-    #     git commit -m "Update frontend build to ${GITHUB_SHA:0:7}" -a
-    #     git push -f origin ${{ env.BUILD_BRANCH }}
-
-    - name: Create PR ${{ env.BUILD_BRANCH }} -> ${{ github.ref_name }}
-      if: github.event_name == 'push'
-      uses: peter-evans/create-pull-request@v6
-      with:
-        add-paths: frontend/build/web
-        base: ${{ github.ref_name }}
-        branch: ${{ env.BUILD_BRANCH }}
-        delete-branch: true
-        title: "Update frontend build in `${{ github.ref_name }}`"
-        body: "This PR updates the frontend build based on commit ${{ github.sha }}."
-        commit-message: "Update frontend build based on commit ${{ github.sha }}"

.github/workflows/hackathon.yml

@@ -88,13 +88,13 @@ jobs:
         run: docker ps
 
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
           submodules: true
 
       - name: Set up Python ${{ env.min-python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v2
         with:
           python-version: ${{ env.min-python-version }}
 
@@ -107,7 +107,7 @@ jobs:
           curl -sSL https://install.python-poetry.org | python -
 
       - name: Install Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v1
         with:
           node-version: v18.15
 
@@ -117,7 +117,7 @@ jobs:
           branch=$(jq -r '.["branch_to_benchmark"]' arena/$AGENT_NAME.json)
           git clone "$link" -b "$branch" "$AGENT_NAME"
           cd $AGENT_NAME
-          cp ./$AGENT_NAME/.env.example ./$AGENT_NAME/.env || echo "file not found"
+          cp ./autogpts/$AGENT_NAME/.env.example ./autogpts/$AGENT_NAME/.env || echo "file not found"
           ./run agent start $AGENT_NAME
           cd ../benchmark
           poetry install

.github/workflows/pr-label.yml

@@ -5,7 +5,7 @@ on:
   push:
     branches: [ master, development, release-* ]
     paths-ignore:
-      - 'autogpt/tests/vcr_cassettes'
+      - 'autogpts/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.
@@ -52,15 +52,6 @@ jobs:
           l_label: 'size/l'
           l_max_size: 500
           xl_label: 'size/xl'
-          message_if_xl:
-
-  scope:
-    if: ${{ github.event_name == 'pull_request_target' }}
-    permissions:
-      contents: read
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/labeler@v5
-        with:
-          sync-labels: true
+          message_if_xl: >
+            This PR exceeds the recommended size of 500 lines.
+            Please make sure you are NOT addressing multiple issues with one PR.

.github/workflows/python-checks.yml

@@ -1,151 +0,0 @@
-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 }}

.gitignore

@@ -6,6 +6,8 @@ auto_gpt_workspace/*
 *.mpeg
 .env
 azure.yaml
+ai_settings.yaml
+last_run_ai_settings.yaml
 .vscode
 .idea/*
 auto-gpt.json
@@ -170,3 +172,8 @@ pri*
 # ignore
 ig*
 .github_access_token
+arena/TestAgent.json
+
+# evo.ninja
+autogpts/evo.ninja/*
+!autogpts/evo.ninja/setup

.gitmodules

@@ -1,3 +1,3 @@
-[submodule "autogpt/tests/vcr_cassettes"]
-	path = autogpt/tests/vcr_cassettes
+[submodule "autogpts/autogpt/tests/vcr_cassettes"]
+	path = autogpts/autogpt/tests/vcr_cassettes
 	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

.pr_agent.toml

@@ -1,6 +0,0 @@
-[pr_reviewer]
-num_code_suggestions=0
-
-[pr_code_suggestions]
-commitable_code_suggestions=false
-num_code_suggestions=0

.pre-commit-config.yaml

@@ -1,127 +0,0 @@
-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

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

QUICKSTART.md

@@ -39,6 +39,9 @@ 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)
 
@@ -74,30 +77,44 @@ After executing the above commands, running `./run setup` should work successful
 
 #### Store Project Files within the WSL File System
 If you continue to experience issues, consider storing your project files within the WSL file system instead of the Windows file system. This method avoids issues related to path translations and permissions and provides a more consistent development environment.
+    
+    You can keep running the command to get feedback on where you are up to with your setup. 
+    When setup has been completed, the command will return an output like this:
 
-You can keep running the command to get feedback on where you are up to with your setup. 
-When setup has been completed, the command will return an output like this:
-
-![Setup Complete](docs/content/imgs/quickstart/006_setup_complete.png)
+   ![Setup Complete](docs/content/imgs/quickstart/006_setup_complete.png)
 
 ## Creating Your Agent
 
-After completing the setup, the next step is to create your agent template.
-Execute the command `./run agent create YOUR_AGENT_NAME`, where `YOUR_AGENT_NAME` should be replaced with a name of your choosing.
+    Now setup has been completed its time to create your agent template. 
+    Do so by running the `./run agent create YOUR_AGENT_NAME` replacing YOUR_AGENT_NAME with a name of your choice. Examples of valid names: swiftyosgpt or SwiftyosAgent or swiftyos_agent
 
-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
+   ![Create an Agent](docs/content/imgs/quickstart/007_create_agent.png)
 
-Examples: `SwiftyosAssistant`, `PwutsPRAgent`, `MySuperAgent`
+    Upon creating your agent its time to officially enter the Arena!
+    Do so by running `./run arena enter YOUR_AGENT_NAME`
+
+   ![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.
 
-![Create an Agent](docs/content/imgs/quickstart/007_create_agent.png)
 
 ## Running your Agent
 
-Your agent can be started using the command: `./run agent start YOUR_AGENT_NAME`
+Your agent can started using the `./run agent start YOUR_AGENT_NAME`
 
-This starts the agent on the URL: `http://localhost:8000/`
+This start the agent on `http://localhost:8000/`
 
 ![Start the Agent](docs/content/imgs/quickstart/009_start_agent.png)
 

README.md

@@ -18,16 +18,23 @@ Be part of the revolution! **AutoGPT** is here to stay, at the forefront of AI i
  | 
 **🛠️ [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!** – 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.
+**Forge your own agent!** – 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.
 
-🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/forge/tutorials/001_getting_started.md) –
+🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpts/forge/tutorials/001_getting_started.md) –
 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/forge) about Forge
+📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpts/forge) about Forge
 
 ### 🎯 Benchmark
 
@@ -39,11 +46,18 @@ This guide will walk you through the process of creating your own agent and usin
  | 
 📘 [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: insert screenshot of front end -->
+<!-- TODO: instert 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!
 
@@ -64,6 +78,7 @@ 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.
 ```
@@ -87,11 +102,7 @@ To maintain a uniform standard and ensure seamless compatibility with many curre
 ---
 
 <p align="center">
-<a href="https://star-history.com/#Significant-Gravitas/AutoGPT">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=Significant-Gravitas/AutoGPT&type=Date&theme=dark" />
-    <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Significant-Gravitas/AutoGPT&type=Date" />
-    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=Significant-Gravitas/AutoGPT&type=Date" />
-  </picture>
-</a>
+  <a href="https://star-history.com/#Significant-Gravitas/AutoGPT&Date">
+    <img src="https://api.star-history.com/svg?repos=Significant-Gravitas/AutoGPT&type=Date" alt="Star History Chart">
+  </a>
 </p>

SECURITY.md

@@ -1,66 +0,0 @@
-# Security Policy
-
- - [**Using AutoGPT Securely**](#using-AutoGPT-securely)
-   - [Restrict Workspace](#restrict-workspace)
-   - [Untrusted inputs](#untrusted-inputs)
-   - [Data privacy](#data-privacy)
-   - [Untrusted environments or networks](#untrusted-environments-or-networks)
-   - [Multi-Tenant environments](#multi-tenant-environments)
- - [**Reporting a Vulnerability**](#reporting-a-vulnerability)
-
-## Using AutoGPT Securely
-
-### Restrict Workspace
-
-Since agents can read and write files, it is important to keep them restricted to a specific workspace. This happens by default *unless* RESTRICT_TO_WORKSPACE is set to False.
-
-Disabling RESTRICT_TO_WORKSPACE can increase security risks. However, if you still need to disable it, consider running AutoGPT inside a [sandbox](https://developers.google.com/code-sandboxing), to mitigate some of these risks.
-
-### Untrusted inputs
-
-When handling untrusted inputs, it's crucial to isolate the execution and carefully pre-process inputs to mitigate script injection risks.
-
-For maximum security when handling untrusted inputs, you may need to employ the following:
-
-* Sandboxing: Isolate the process.
-* Updates: Keep your libraries (including AutoGPT) updated with the latest security patches.
-* Input Sanitation: Before feeding data to the model, sanitize inputs rigorously. This involves techniques such as:
-    * Validation: Enforce strict rules on allowed characters and data types.
-    * Filtering: Remove potentially malicious scripts or code fragments.
-    * Encoding: Convert special characters into safe representations.
-    * Verification: Run tooling that identifies potential script injections (e.g. [models that detect prompt injection attempts](https://python.langchain.com/docs/guides/safety/hugging_face_prompt_injection)). 
-
-### Data privacy
-
-To protect sensitive data from potential leaks or unauthorized access, it is crucial to sandbox the agent execution. This means running it in a secure, isolated environment, which helps mitigate many attack vectors.
-
-### Untrusted environments or networks
-
-Since AutoGPT performs network calls to the OpenAI API, it is important to always run it with trusted environments and networks. Running it on untrusted environments can expose your API KEY to attackers.
-Additionally, running it on an untrusted network can expose your data to potential network attacks. 
-
-However, even when running on trusted networks, it is important to always encrypt sensitive data while sending it over the network.
-
-### Multi-Tenant environments
-
-If you intend to run multiple AutoGPT brains in parallel, it is your responsibility to ensure the models do not interact or access each other's data.
-
-The primary areas of concern are tenant isolation, resource allocation, model sharing and hardware attacks.
-
-- Tenant Isolation: you must make sure that the tenants run separately to prevent unwanted access to the data from other tenants. Keeping model network traffic separate is also important because you not only prevent unauthorized access to data, but also prevent malicious users or tenants sending prompts to execute under another tenant’s identity.
-
-- Resource Allocation: a denial of service caused by one tenant can affect the overall system health. Implement safeguards like rate limits, access controls, and health monitoring.
-
-- Data Sharing: in a multi-tenant design with data sharing, ensure tenants and users understand the security risks and sandbox agent execution to mitigate risks.
-
-- Hardware Attacks: the hardware (GPUs or TPUs) can also be attacked. [Research](https://scholar.google.com/scholar?q=gpu+side+channel) has shown that side channel attacks on GPUs are possible, which can make data leak from other brains or processes running on the same system at the same time.
-
-## Reporting a Vulnerability
-
-Beware that none of the topics under [Using AutoGPT Securely](#using-AutoGPT-securely) are considered vulnerabilities on AutoGPT.
-
-However, If you have discovered a security vulnerability in this project, please report it privately. **Do not disclose it as a public issue.** This gives us time to work with you to fix the issue before public exposure, reducing the chance that the exploit will be used before a patch is released.
-
-Please disclose it as a private [security advisory](https://github.com/Significant-Gravitas/AutoGPT/security/advisories/new).
-
-A team of volunteers on a reasonable-effort basis maintains this project. As such, please give us at least 90 days to work on a fix before public exposure.

arena/480bot.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/480/AutoGPT",
+    "timestamp": "2023-10-22T06:49:52.536177",
+    "commit_hash_to_benchmark": "16e266c65fb4620a1b1397532c503fa426ec191d",
+    "branch_to_benchmark": "master"
+}

arena/AGENT_GORDON.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/filipjakubowski/AutoGPT",
+    "timestamp": "2023-11-01T17:13:24.272333",
+    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
+    "branch_to_benchmark": "master"
+}

arena/AGENT_JARVIS.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/filipjakubowski/AutoGPT",
+    "timestamp": "2023-11-04T10:13:11.039444",
+    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
+    "branch_to_benchmark": "master"
+}

arena/AI.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/QingquanBao/AutoGPT",
+    "timestamp": "2023-11-01T16:20:51.086235",
+    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
+    "branch_to_benchmark": "master"
+}

arena/AKBAgent.json

@@ -0,0 +1,7 @@
+{
+  "github_repo_url": "https://github.com/imakb/AKBAgent",
+  "timestamp": "2023-10-31T00:03:23.000000",
+  "commit_hash_to_benchmark": "c65b71d51d8f849663172c5a128953b4ca92b2b0",
+  "branch_to_benchmark": "AKBAgent"
+}
+

arena/ASSISTANT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/hongzzz/AutoGPT",
+    "timestamp": "2023-10-13T03:22:59.347424",
+    "commit_hash_to_benchmark": "38790a27ed2c1b63a301b6a67e7590f2d30de53e",
+    "branch_to_benchmark": "master"
+}

arena/AUTO_ENGINEER.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/kaiomagalhaes/AutoGPT",
+    "timestamp": "2023-10-04T15:25:30.458687",
+    "commit_hash_to_benchmark": "1bd85cbc09473c0252928fb849ae8373607d6065",
+    "branch_to_benchmark": "master"
+}

arena/AUTO_GPT_JON001.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/Adtractive_Agent.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/AgGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/althaf004/AutoGPT",
+    "timestamp": "2023-09-26T03:40:03.658369",
+    "commit_hash_to_benchmark": "4a8da53d85d466f2eb325c745a2c03cf88792e7d",
+    "branch_to_benchmark": "master"
+}

arena/AgentJPark.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/againeureka/AutoGPT",
+    "timestamp": "2023-10-12T02:20:01.005361",
+    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
+    "branch_to_benchmark": "master"
+}

arena/AgentKD.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/kitdesai/AgentKD",
+    "timestamp": "2023-10-14T02:35:09.979434",
+    "commit_hash_to_benchmark": "93e3ec36ed6cd9e5e60585f016ad3bef4e1c52cb",
+    "branch_to_benchmark": "master"
+}

arena/Ahmad.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/Alfred.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/Shadowless422/Alfred",
+    "timestamp": "2023-10-03T10:42:45.473477",
+    "commit_hash_to_benchmark": "949ab477a87cfb7a3668d7961e9443922081e098",
+    "branch_to_benchmark": "master"
+}

arena/AlphaCISO.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/alphaciso/AutoGPT",
+    "timestamp": "2023-10-21T08:26:41.961187",
+    "commit_hash_to_benchmark": "415b4ceed1417d0b21d87d7d4ea0cd38943e264f",
+    "branch_to_benchmark": "master"
+}

arena/AndersLensway.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/4nd3rs/AutoGPT",
+    "timestamp": "2023-10-11T11:00:08.150159",
+    "commit_hash_to_benchmark": "57bcbdf45c6c1493a4e5f6a4e72594ea13c10f93",
+    "branch_to_benchmark": "master"
+}

arena/AntlerTestGPT.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/pjw1/AntlerAI", "timestamp": "2023-10-07T11:46:39Z", "commit_hash_to_benchmark": "f81e086e5647370854ec639c531c900775a99207", "branch_to_benchmark": "master"}

arena/AppleGPT.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/AquaAgent.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/somnistudio/SomniGPT", "timestamp": "2023-10-06T16:40:14Z", "commit_hash_to_benchmark": "47eb5124fa97187d7f3fa4036e422cd771cf0ae7", "branch_to_benchmark": "master"}

arena/ArtistManagerGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/AmahAjavon/AutoGPT",
+    "timestamp": "2023-10-28T20:32:15.845741",
+    "commit_hash_to_benchmark": "2bd05827f97e471af798b8c2f04e8772dad101d3",
+    "branch_to_benchmark": "master"
+}

arena/AskOpie.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/arunqa/AutoGPT",
+    "timestamp": "2023-09-26T05:13:24.466017",
+    "commit_hash_to_benchmark": "4a8da53d85d466f2eb325c745a2c03cf88792e7d",
+    "branch_to_benchmark": "master"
+}

arena/Auto.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/Nikhil8652/AutoGPT",
+    "timestamp": "2023-10-16T09:12:17.452121",
+    "commit_hash_to_benchmark": "2f79caa6b901d006a78c1ac9e69db4465c0f971a",
+    "branch_to_benchmark": "master"
+}

arena/AutoGPT-ariel.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/RedTachyon/AutoGPT",
+    "timestamp": "2023-10-21T22:31:30.871023",
+    "commit_hash_to_benchmark": "eda21d51921899756bf866cf5c4d0f2dcd3e2e23",
+    "branch_to_benchmark": "master"
+}

arena/AutoGPT2.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/SarahGrevy/AutoGPT", "timestamp": "2023-10-20T17:21:22Z", "commit_hash_to_benchmark": "32300906c9aafea8c550fa2f9edcc113fbfc512c", "branch_to_benchmark": "master"}

arena/AutoGenius.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/JasonDRZ/AutoGPT",
+    "timestamp": "2023-10-26T13:27:58.805270",
+    "commit_hash_to_benchmark": "ab2a61833584c42ededa805cbac50718c72aa5ae",
+    "branch_to_benchmark": "master"
+}

arena/AutoTDD.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/vshneer/AutoTDD",
+    "timestamp": "2023-10-11T19:14:30.939747",
+    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
+    "branch_to_benchmark": "master"
+}

arena/AutoTestGenerator.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/cagdasbas/AutoGPT",
+    "timestamp": "2023-10-15T08:43:40.193080",
+    "commit_hash_to_benchmark": "74ee69daf1c0a2603f19bdb1edcfdf1f4e06bcff",
+    "branch_to_benchmark": "master"
+}

arena/AwareAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/LuisLechugaRuiz/AwareAgent",
+    "timestamp": "2023-10-26T10:10:01.481205",
+    "commit_hash_to_benchmark": "c180063dde49af02ed95ec4c019611da0a5540d7",
+    "branch_to_benchmark": "master"
+}

arena/Bagi_agent.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/BanglaSgAgent.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/Baptiste.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/Baptistecaille/AutoGPT",
+    "timestamp": "2023-10-01T19:44:23.416591",
+    "commit_hash_to_benchmark": "3da29eae45683457131ee8736bedae7e2a74fbba",
+    "branch_to_benchmark": "master"
+}

arena/Bravo06.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/jafar-albadarneh/Bravo06GPT", "timestamp": "2023-10-04T23:01:27Z", "commit_hash_to_benchmark": "f8c177b4b0e4ca45a3a104011b866c0415c648f1", "branch_to_benchmark": "master"}

arena/Brillante-AI.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/dabeer021/Brillante-AI", "timestamp": "2023-10-02T19:05:04Z", "commit_hash_to_benchmark": "163ab75379e1ee7792f50d4d70a1f482ca9cb6a1", "branch_to_benchmark": "master"}

arena/Bunny.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/razorhasbeen/AutoGPT",
+    "timestamp": "2023-10-03T11:50:56.725628",
+    "commit_hash_to_benchmark": "d8d7fc4858a8d13407f6d7da360c6b5d398f2175",
+    "branch_to_benchmark": "master"
+}

arena/CCAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/ccsnow127/AutoGPT",
+    "timestamp": "2023-10-21T13:57:15.131761",
+    "commit_hash_to_benchmark": "e9b64adae9fce180a392c726457e150177e746fb",
+    "branch_to_benchmark": "master"
+}

arena/CES-GPT.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/CISLERK.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/cislerk/AutoGPT",
+    "timestamp": "2023-10-10T18:40:50.718850",
+    "commit_hash_to_benchmark": "c77ade5b2f62c5373fc7573e5c45581f003c77a3",
+    "branch_to_benchmark": "master"
+}

arena/CONNECTBOT.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/CYNO_AGENT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/dr1yl/AutoGPT",
+    "timestamp": "2023-10-09T20:01:05.041446",
+    "commit_hash_to_benchmark": "c77ade5b2f62c5373fc7573e5c45581f003c77a3",
+    "branch_to_benchmark": "master"
+}

arena/ChadGPT.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/Ahmad-Alaziz/ChadGPT", "timestamp": "2023-10-26T09:39:35Z", "commit_hash_to_benchmark": "84dd029c011379791a6fec8b148b2982a2ef159e", "branch_to_benchmark": "master"}

arena/ChrisGPT.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/CodeAutoGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/hugomastromauro/AutoGPT",
+    "timestamp": "2023-11-01T13:21:42.624202",
+    "commit_hash_to_benchmark": "78e92234d63a69b5471da0c0e62ce820a9109dd4",
+    "branch_to_benchmark": "master"
+}

arena/CreaitorMarketing.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/simonfunk/Auto-GPT", "timestamp": "2023-10-08T02:10:18Z", "commit_hash_to_benchmark": "e99e9b6181f091a9625ef9b922dac15dd5f0a885", "branch_to_benchmark": "master"}

arena/CurieAssistant.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/HMDCrew/AutoGPT",
+    "timestamp": "2023-10-06T20:41:26.293944",
+    "commit_hash_to_benchmark": "9e353e09b5df39d4d410bef57cf17387331e96f6",
+    "branch_to_benchmark": "master"
+}

arena/DE.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/wic0144/AutoGPT",
+    "timestamp": "2023-10-26T09:05:21.013962",
+    "commit_hash_to_benchmark": "89d333f3bb422495f21e04bdd2bba3cb8c1a34ae",
+    "branch_to_benchmark": "master"
+}

arena/DavidsAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/beisdog/AutoGPT",
+    "timestamp": "2023-09-29T22:06:18.846082",
+    "commit_hash_to_benchmark": "d6abb27db61142a70defd0c75b53985ea9a71fce",
+    "branch_to_benchmark": "master"
+}

arena/Derpmaster.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/DevOpsAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/rahuldotar/AutoGPT",
+    "timestamp": "2023-10-02T11:34:29.870077",
+    "commit_hash_to_benchmark": "062d286c239dc863ede4ad475d7348698722f5fa",
+    "branch_to_benchmark": "master"
+}

arena/Drench.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/Eduardo.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/EmbeddedAg.json

@@ -0,0 +1 @@
+{"github_repo_url": "https://github.com/Significant-Gravitas/AutoGPT", "timestamp": "2023-10-26T09:15:50Z", "commit_hash_to_benchmark": "6c9152a95c8994898c47c85ea90ba58e0cc02c28", "branch_to_benchmark": "master"}

arena/EnglishTestpaperAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/kyannai/AutoGPT",
+    "timestamp": "2023-09-29T03:05:45.504690",
+    "commit_hash_to_benchmark": "1f367618edf903f38dff4dd064f96e611ffc5242",
+    "branch_to_benchmark": "master"
+}

arena/ExampleAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/janekdijkstra/AutoGPT",
+    "timestamp": "2023-10-16T12:12:54.998033",
+    "commit_hash_to_benchmark": "2f79caa6b901d006a78c1ac9e69db4465c0f971a",
+    "branch_to_benchmark": "master"
+}

arena/FLASH.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/flashdumper/AutoGPT",
+    "timestamp": "2023-10-30T23:02:13.653861",
+    "commit_hash_to_benchmark": "d9fbd26b8563e5f59d705623bae0d5cf9c9499c7",
+    "branch_to_benchmark": "master"
+}

arena/FactoryGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/neilmartindev/FactoryGPT",
+    "timestamp": "2023-10-04T16:24:58.525870",
+    "commit_hash_to_benchmark": "1bd85cbc09473c0252928fb849ae8373607d6065",
+    "branch_to_benchmark": "master"
+}

arena/FcsummerGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/fbk111/FcsummerGPT",
+    "timestamp": "2023-10-25T09:58:39.801277",
+    "commit_hash_to_benchmark": "ab362f96c3255052350e8e8081b363c7b97ffd6f",
+    "branch_to_benchmark": "master"
+}

arena/FynAgent.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/GG.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/IgorCIs/AutoGPT",
+    "timestamp": "2023-09-27T14:01:20.964953",
+    "commit_hash_to_benchmark": "a14aadd91493886663232bfd23c0412609f2a2fc",
+    "branch_to_benchmark": "master"
+}

arena/GPTTest.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/GameSoundGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/mordvinov/AutoGPT",
+    "timestamp": "2023-10-13T14:48:02.852293",
+    "commit_hash_to_benchmark": "93e3ec36ed6cd9e5e60585f016ad3bef4e1c52cb",
+    "branch_to_benchmark": "master"
+}

arena/GeorgeGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/norn93/GeorgeGPT",
+    "timestamp": "2023-10-17T14:38:41.051458",
+    "commit_hash_to_benchmark": "1eadc64dc0a693c7c9de77ddaef857f3a36f7950",
+    "branch_to_benchmark": "master"
+}

arena/Granger.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/balloch/AutoGPTProblemSolver",
+    "timestamp": "2023-09-29T15:11:44.876627",
+    "commit_hash_to_benchmark": "9fb6d5bbbd6928402a5718b8c249811c6f682a88",
+    "branch_to_benchmark": "master"
+}

arena/HACKATHON.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/HMD2.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/HMDCrew/AutoGPT",
+    "timestamp": "2023-10-09T08:46:37.457740",
+    "commit_hash_to_benchmark": "9e353e09b5df39d4d410bef57cf17387331e96f6",
+    "branch_to_benchmark": "master"
+}

arena/Heisenberg.json

@@ -0,0 +1,6 @@
+{
+ "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"
+}

arena/HekolcuAutoGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/hekolcu/AutoGPT",
+    "timestamp": "2023-09-30T17:31:20.979122",
+    "commit_hash_to_benchmark": "a0fba5d1f13d35a1c4a8b7718550677bf62b5101",
+    "branch_to_benchmark": "master"
+}

arena/HuitzilAiAgent.json

@@ -0,0 +1,6 @@
+{
+    "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"
+}

arena/Hypeman.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/kennyu/KenGPT",
+    "timestamp": "2023-09-27T19:50:31.443494",
+    "commit_hash_to_benchmark": "cf630e4f2cee04fd935612f95308322cd9eb1df7",
+    "branch_to_benchmark": "master"
+}

arena/IncredibubbleTea.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/mariepop13/AutoGPT",
+    "timestamp": "2023-10-25T18:38:32.012583",
+    "commit_hash_to_benchmark": "ab362f96c3255052350e8e8081b363c7b97ffd6f",
+    "branch_to_benchmark": "master"
+}

arena/JackGPT.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/JackDance/AutoGPT",
+    "timestamp": "2023-10-09T08:26:35.181112",
+    "commit_hash_to_benchmark": "f77d383a9f5e66a35d6008bd43cab4d93999cb61",
+    "branch_to_benchmark": "master"
+}

arena/Jarvis.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/elynch303/AutoGPT",
+    "timestamp": "2023-10-12T14:15:17.014333",
+    "commit_hash_to_benchmark": "766796ae1e8c07cf2a03b607621c3da6e1f01a31",
+    "branch_to_benchmark": "master"
+}

arena/JarvisAgent.json

@@ -0,0 +1,6 @@
+{
+    "github_repo_url": "https://github.com/JadeCong/AutoGPT",
+    "timestamp": "2023-10-17T18:49:16.489653",
+    "commit_hash_to_benchmark": "0bd5d4420ec168194d5a93f62d890d33ab7d9940",
+    "branch_to_benchmark": "master"
+}