github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-04-08 03:00:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

docs: Streamline documentation for getting started (#6335)

Browse Source 
* README.md
  - Mark evo.ninja as hackathon winner and new Current Best Agent.
  - Remove hackathon banner.
  - Rewrite sections about Forge, Benchmark, UI, Agent Protocol.
  - Add sections about Leaderboard and CLI.
  - Add quick links for improved user navigation, including links to documentation, contributing guidelines, and quickstart guide.
  - Remove Quickstart.

* docs.agpt.co
  - Removed links to outdated pages from navbar.
  - Added quick links to several pages.
  - Refactored and updated titles in docs site navbar for better readability and consistency.
  - Rewrite intros on homepage to be more clear and professional and less cringe-worthy.
  - Fix broken links.
  - Rewrote setup and usage guides for AutoGPT Agent.
    - Removed mentions of Azure support, except in the Docker guide.
  - Added page with general information about AutoGPT.

* CONTRIBUTING.md
  - Make CONTRIBUTING.md more friendly and accessible: added link to public kanban board, encouraged collaboration, removed section about net-negative PRs.

* autogpt/README.md
  - Update description of AutoGPT to mention "modern Large Language Models" instead of GPT-4.
  - Add quick links for improved user navigation, including links to documentation and contributing guidelines.
  - Add features and setup guide: Agent Protocol, UI features, setup instructions, configuration options, Quickstart, CLI instructions, Agent Protocol server instructions, additional resources (wiki, project board, roadmap), and a note on sustainable development.
  - Update links: documentation, setup instructions.
  - Remove outdated Twitter accounts section.
This commit is contained in:
Reinier van der Leer
2023-11-23 14:59:17 +01:00
committed by GitHub
parent 84afbf6b45
commit 24008e8741
18 changed files with 578 additions and 508 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
docs/content/AutoGPT/Setups/Git-setup.md
View File

@@ -1,81 +0,0 @@
### Set up with Git
!!! important
Make sure you have [Git](https://git-scm.com/downloads) installed for your OS.
!!! info "Executing commands"
To execute the given commands, open a CMD, Bash, or Powershell window.
On Windows: press ++win+x++ and pick *Terminal*, or ++win+r++ and enter `cmd`
1. Clone the repository
```shell
git clone -b stable https://github.com/Significant-Gravitas/AutoGPT.git
```
2. Navigate to the directory where you downloaded the repository
```shell
cd AutoGPT/autogpts/autogpt
```
### Configuration
1. Find the file named `.env.template` in the main `Auto-GPT` folder. This file may
be hidden by default in some operating systems due to the dot prefix. To reveal
hidden files, follow the instructions for your specific operating system:
[Windows][show hidden files/Windows] and [macOS][show hidden files/macOS].
2. Create a copy of `.env.template` and call it `.env`;
if you're already in a command prompt/terminal window:
```shell
cp .env.template .env
```
3. Open the `.env` file in a text editor.
4. Find the line that says `OPENAI_API_KEY=`.
5. Insert your OpenAI API Key directly after = without quotes or spaces..
```yaml
OPENAI_API_KEY=sk-qwertykeys123456
```
6. Enter any other API keys or tokens for services you would like to use.
!!! note
To activate and adjust a setting, remove the `# ` prefix.
7. Save and close the `.env` file.
!!! info "Using a GPT Azure-instance"
If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and
make an Azure configuration file:
- Rename `azure.yaml.template` to `azure.yaml` and provide the relevant `azure_api_base`, `azure_api_version` and all the deployment IDs for the relevant models in the `azure_model_map` section:
- `fast_llm_deployment_id`: your gpt-3.5-turbo or gpt-4 deployment ID
- `smart_llm_deployment_id`: your gpt-4 deployment ID
- `embedding_model_deployment_id`: your text-embedding-ada-002 v2 deployment ID
Example:
```yaml
# Please specify all of these values as double-quoted strings
# Replace string in angled brackets (<>) to your own deployment Name
azure_model_map:
fast_llm_deployment_id: "<auto-gpt-deployment>"
...
```
Details can be found in the [openai-python docs], and in the [Azure OpenAI docs] for the embedding model.
If you're on Windows you may need to install an [MSVC library](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170).
[show hidden files/Windows]: https://support.microsoft.com/en-us/windows/view-hidden-files-and-folders-in-windows-97fbc472-c603-9d90-91d0-1166d1d9f4b5
[show hidden files/macOS]: https://www.pcmag.com/how-to/how-to-access-your-macs-hidden-files
[openai-python docs]: https://github.com/openai/openai-python#microsoft-azure-endpoints
[Azure OpenAI docs]: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/tutorials/embeddings?tabs=command-line
## Running AutoGPT
### Run with Dev Container
1. Install the [Remote - Containers](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) extension in VS Code.
2. Open command palette with ++f1++ and type `Dev Containers: Open Folder in Container`.
3. Run `./run.sh`.

86
docs/content/AutoGPT/Setups/nogit-setup.md
View File

@@ -1,86 +0,0 @@
### Setting Up without Git/Docker
!!! warning
We recommend to use Git or Docker, to make updating easier. Also note that some features such as Python execution will only work inside docker for security reasons.
1. Download `Source code (zip)` from the [latest stable release](https://github.com/Significant-Gravitas/AutoGPT/releases/latest)
2. Extract the zip-file into a folder
### Configuration
1. Find the file named `.env.template` in the main `Auto-GPT` folder. This file may
be hidden by default in some operating systems due to the dot prefix. To reveal
hidden files, follow the instructions for your specific operating system:
[Windows][show hidden files/Windows], [macOS][show hidden files/macOS].
2. Create a copy of `.env.template` and call it `.env`;
if you're already in a command prompt/terminal window: `cp .env.template .env`.
3. Open the `.env` file in a text editor.
4. Find the line that says `OPENAI_API_KEY=`.
5. After the `=`, enter your unique OpenAI API Key *without any quotes or spaces*.
6. Enter any other API keys or tokens for services you would like to use.
!!! note
To activate and adjust a setting, remove the `# ` prefix.
7. Save and close the `.env` file.
!!! info "Using a GPT Azure-instance"
If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and
make an Azure configuration file:
- Rename `azure.yaml.template` to `azure.yaml` and provide the relevant `azure_api_base`, `azure_api_version` and all the deployment IDs for the relevant models in the `azure_model_map` section:
- `fast_llm_deployment_id`: your gpt-3.5-turbo or gpt-4 deployment ID
- `smart_llm_deployment_id`: your gpt-4 deployment ID
- `embedding_model_deployment_id`: your text-embedding-ada-002 v2 deployment ID
Example:
```yaml
# Please specify all of these values as double-quoted strings
# Replace string in angled brackets (<>) to your own deployment Name
azure_model_map:
fast_llm_deployment_id: "<auto-gpt-deployment>"
...
```
Details can be found in the [openai-python docs], and in the [Azure OpenAI docs] for the embedding model.
If you're on Windows you may need to install an [MSVC library](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170).
[show hidden files/Windows]: https://support.microsoft.com/en-us/windows/view-hidden-files-and-folders-in-windows-97fbc472-c603-9d90-91d0-1166d1d9f4b5
[show hidden files/macOS]: https://www.pcmag.com/how-to/how-to-access-your-macs-hidden-files
[openai-python docs]: https://github.com/openai/openai-python#microsoft-azure-endpoints
[Azure OpenAI docs]: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/tutorials/embeddings?tabs=command-line
### Start AutoGPT In A Virtual Environment
First we need to create a virtual environment to run in.
```shell
pip3 install poetry
python -m venv .venv
source .venv/bin/activate
poetry install
```
!!! warning
Due to security reasons, certain features (like Python execution) will by default be disabled when running without docker. So, even if you want to run the program outside a docker container, you currently still need docker to actually run scripts.
Simply run the startup script in your terminal. This will install any necessary Python
packages and launch AutoGPT.
- On Linux/MacOS:
```shell
./run.sh
```
- On Windows:
```shell
.\run.bat
```
If this gives errors, make sure you have a compatible Python version installed. See also
the [requirements](/autogpt/setup/#requirements).

29
docs/content/AutoGPT/index.md Normal file
View File

@@ -0,0 +1,29 @@
# AutoGPT Agent
[🔧 **Setup**](./setup)
&ensp;|&ensp;
[💻 **User guide**](./usage.md)
&ensp;|&ensp;
[🐙 **GitHub**](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpts/autogpt)
**Location:** `autogpts/autogpt/` in the GitHub repo
AutoGPT was conceived when OpenAI published their GPT-4 model accompanied by a paper
outlining the advanced reasoning and task-solving abilities of the model. The concept
was (and still is) fairly simple: let an LLM decide what to do over and over, while
feeding the results of its actions back into the prompt. This allows the program to
iteratively and incrementally work towards its objective.
The fact that this program is able to execute actions on behalf of its user makes
it an **agent**. In the case of AutoGPT, the user still has to authorize every action,
but as the project progresses we'll be able to give the agent more autonomy and only
require consent for select actions.
AutoGPT is a **generalist agent**, meaning it is not designed with a specific task in
mind. Instead, it is designed to be able to execute a wide range of tasks across many
disciplines, as long as it can be done on a computer.
## Coming soon
* How does AutoGPT work?
* What can I use AutoGPT for?
* What does the future of AutoGPT look like?

49
docs/content/AutoGPT/setup.md
View File

@@ -1,49 +0,0 @@
# Setting up AutoGPT
## 📋 Requirements
Choose an environment to run AutoGPT in (pick one):
- [Docker](https://docs.docker.com/get-docker/) (*recommended*)
- Python 3.10 or later (instructions: [for Windows](https://www.tutorialspoint.com/how-to-install-python-in-windows))
- [VSCode + devcontainer](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers)
## 🗝️ Getting an API key
Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys).
!!! attention
To use the OpenAI API with AutoGPT, we strongly recommend **setting up billing**
(AKA paid account). Free accounts are [limited][openai/api limits] to 3 API calls per
minute, which can cause the application to crash.
You can set up a paid account at [Manage account > Billing > Overview](https://platform.openai.com/account/billing/overview).
[openai/api limits]: https://platform.openai.com/docs/guides/rate-limits/overview#:~:text=Free%20trial%20users,RPM%0A40%2C000%20TPM
!!! important
It's highly recommended that you keep track of your API costs on [the Usage page](https://platform.openai.com/account/usage).
You can also set limits on how much you spend on [the Usage limits page](https://platform.openai.com/account/billing/limits).
![For OpenAI API key to work, set up paid account at OpenAI API > Billing](/imgs/openai-api-key-billing-paid-account.png)
## Setting up AutoGPT
### If you plan to use Docker please follow this setup.
!!! important "Docker Setup Issue"
We are addressing a known issue with the Docker setup related to Poetry.
[**We have an open PR if you'd like to take a look**](https://github.com/python-poetry/poetry/issues/8548)
Please keep this in mind. We apologize for any inconvenience, and thank you for your patience.
[Docker Install Here.](Setups/Docker-setup.md)
### If you plan to use Git please follow this setup.
[Git Setup Here.](Setups/Git-setup.md)
### If you dont want to use git or docker for the setup follow here.
[No Git Or Docker Setup Here.](Setups/nogit-setup.md)

4
docs/content/AutoGPT/Setups/Docker-setup.md → docs/content/AutoGPT/setup/docker.md
View File

@@ -1,4 +1,4 @@
### Set up with Docker
# Run AutoGPT in Docker
!!! important "Docker Setup Issue"
We are addressing a known issue with the Docker setup related to Poetry.
@@ -150,4 +150,4 @@ docker run -it --env-file=.env -v $PWD:/app auto-gpt
docker run -it --env-file=.env -v $PWD:/app --rm auto-gpt --gpt3only --continuous
```
[Docker Compose file]: https://github.com/Significant-Gravitas/AutoGPT/blob/stable/docker-compose.yml
[Docker Compose file]: https://github.com/Significant-Gravitas/AutoGPT/blob/stable/docker-compose.yml

1
docs/content/AutoGPT/setup/for-developers.md Normal file
View File

@@ -0,0 +1 @@
Coming soon...

BIN
docs/content/AutoGPT/setup/get-repo-dialog.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 68 KiB

104
docs/content/AutoGPT/setup/index.md Normal file
View File

@@ -0,0 +1,104 @@
# AutoGPT Agent setup
[🐋 **Set up & Run with Docker**](./docker.md)
&ensp;|&ensp;
[👷🏼 **For Developers**](./for-developers.md)
## 📋 Requirements
### Linux / macOS
- Python 3.10 or later
- Poetry ([instructions](https://python-poetry.org/docs/#installation))
### Windows (WSL)
- WSL 2
- See also the [requirements for Linux](#linux--macos)
- [Docker Desktop](https://docs.docker.com/desktop/install/windows-install/)
### Windows
!!! attention
We recommend setting up AutoGPT with WSL. Some things don't work exactly the same on
Windows and we currently can't provide specialized instructions for all those cases.
- Python 3.10 or later ([instructions](https://www.tutorialspoint.com/how-to-install-python-in-windows))
- Poetry ([instructions](https://python-poetry.org/docs/#installation))
- [Docker Desktop](https://docs.docker.com/desktop/install/windows-install/)
### 🗝️ Getting an OpenAI API key
Get your OpenAI API key from: https://platform.openai.com/account/api-keys.
!!! attention
To use the OpenAI API with AutoGPT, we strongly recommend **setting up billing**
(AKA paid account). Free accounts are [limited][openai/api limits] to 3 API calls per
minute, which can cause the application to crash.
You can set up a paid account at [Manage account > Billing > Overview](https://platform.openai.com/account/billing/overview).
[openai/api limits]: https://platform.openai.com/docs/guides/rate-limits/free-tier-rate-limits
!!! important
It's highly recommended that you keep track of your API costs on [the Usage page](https://platform.openai.com/account/usage).
You can also set limits on how much you spend on [the Usage limits page](https://platform.openai.com/account/billing/limits).
![For OpenAI API key to work, set up paid account at OpenAI API > Billing](/imgs/openai-api-key-billing-paid-account.png)
## Setting up AutoGPT
### Getting AutoGPT
Since we don't ship AutoGPT as a desktop application, you'll need to download the
[project] from GitHub and give it a place on your computer.
![Screenshot of the dialog to clone or download the repo](get-repo-dialog.png)
* To get the latest bleeding edge version, use `master`.
* If you're looking for more stability, check out the latest AutoGPT [release][releases].
[project]: https://github.com/Significant-Gravitas/AutoGPT
[releases]: https://github.com/Significant-Gravitas/AutoGPT/releases
!!! note
These instructions don't apply if you're looking to run AutoGPT as a docker image.
Instead, check out the [Docker setup](./docker.md) guide.
### Completing the Setup
Once you have cloned or downloaded the project, you can find the AutoGPT Agent in the
`autogpts/autogpt/` folder. In this folder:
1. Find the file named `.env.template` in the main `Auto-GPT` folder. This file may
be hidden by default in some operating systems due to the dot prefix. To reveal
hidden files, follow the instructions for your specific operating system:
[Windows][show hidden files/Windows] and [macOS][show hidden files/macOS].
2. Create a copy of `.env.template` and call it `.env`;
if you're already in a command prompt/terminal window:
```shell
cp .env.template .env
```
3. Open the `.env` file in a text editor.
4. Find the line that says `OPENAI_API_KEY=`.
5. Insert your OpenAI API Key directly after = without quotes or spaces..
```yaml
OPENAI_API_KEY=sk-qwertykeys123456
```
6. Enter any other API keys or tokens for services you would like to use.
!!! note
To activate and adjust a setting, remove the `# ` prefix.
7. Save and close the `.env` file.
8. _Optional: run `poetry install` to install all required dependencies._ The
application also checks for and installs any required dependencies when it starts.
You should now be able to explore the CLI (`./run.sh --help`) and run the application.
See the [user guide](../usage.md) for further instructions.
[show hidden files/Windows]: https://support.microsoft.com/en-us/windows/view-hidden-files-and-folders-in-windows-97fbc472-c603-9d90-91d0-1166d1d9f4b5
[show hidden files/macOS]: https://www.pcmag.com/how-to/how-to-access-your-macs-hidden-files

205
docs/content/AutoGPT/usage.md
View File

@@ -1,15 +1,27 @@
# Usage
# AutoGPT Agent User Guide
## Command Line Arguments
Running with `--help` lists all the possible command line arguments you can pass:
## Command Line Interface
Running `./run.sh` (or any of its subcommands) with `--help` lists all the possible
sub-commands and arguments you can use:
```shell
./run.sh --help # on Linux / macOS
$ ./run.sh --help
Usage: python -m autogpt [OPTIONS] COMMAND [ARGS]...
.\run.bat --help # on Windows
Options:
--help Show this message and exit.
Commands:
run Sets up and runs an agent, based on the task specified by the...
serve Starts an Agent Protocol compliant AutoGPT server, which creates...
```
!!! info
!!! important "For Windows users"
On Windows, use `.\run.bat` instead of `./run.sh`.
Everything else (subcommands, arguments) should work the same.
!!! info "Usage with Docker"
For use with Docker, replace the script in the examples with
`docker compose run --rm auto-gpt`:
@@ -18,42 +30,72 @@ Running with `--help` lists all the possible command line arguments you can pass
docker compose run --rm auto-gpt --ai-settings <filename>
```
!!! note
Replace anything in angled brackets (<>) to a value you want to specify
### `run` &ndash; CLI mode
Here are some common arguments you can use when running AutoGPT:
The `run` sub-command starts AutoGPT with the legacy CLI interface.
* Run AutoGPT with a different AI Settings file
<details>
<summary>
<code>./run.sh run --help</code>
</summary>
```shell
./run.sh --ai-settings <filename>
$ ./run.sh run --help
Usage: python -m autogpt run [OPTIONS]
Sets up and runs an agent, based on the task specified by the user, or
resumes an existing agent.
Options:
-c, --continuous Enable Continuous Mode
-y, --skip-reprompt Skips the re-prompting messages at the
beginning of the script
-C, --ai-settings FILE Specifies which ai_settings.yaml file to
use, relative to the AutoGPT root directory.
Will also automatically skip the re-prompt.
-P, --prompt-settings FILE Specifies which prompt_settings.yaml file to
use.
-l, --continuous-limit INTEGER Defines the number of times to run in
continuous mode
--speak Enable Speak Mode
--debug Enable Debug Mode
--gpt3only Enable GPT3.5 Only Mode
--gpt4only Enable GPT4 Only Mode
-b, --browser-name TEXT Specifies which web-browser to use when
using selenium to scrape the web.
--allow-downloads Dangerous: Allows AutoGPT to download files
natively.
--skip-news Specifies whether to suppress the output of
latest news on startup.
--install-plugin-deps Installs external dependencies for 3rd party
plugins.
--ai-name TEXT AI name override
--ai-role TEXT AI role override
--constraint TEXT Add or override AI constraints to include in
the prompt; may be used multiple times to
pass multiple constraints
--resource TEXT Add or override AI resources to include in
the prompt; may be used multiple times to
pass multiple resources
--best-practice TEXT Add or override AI best practices to include
in the prompt; may be used multiple times to
pass multiple best practices
--override-directives If specified, --constraint, --resource and
--best-practice will override the AI's
directives instead of being appended to them
--help Show this message and exit.
```
</details>
* Run AutoGPT with a different Prompt Settings file
```shell
./run.sh --prompt-settings <filename>
```
* Specify a memory backend
```shell
./run.sh --use-memory <memory-backend>
```
This mode allows running a single agent, and saves the agent's state when terminated.
This means you can *resume* agents at a later time. See also [agent state].
!!! note
There are shorthands for some of these flags, for example `-m` for `--use-memory`.
Use `./run.sh --help` for more information.
For legacy reasons, the CLI will default to the `run` subcommand when none is
specified: running `./run.sh run [OPTIONS]` does the same as `./run.sh [OPTIONS]`,
but this may change in the future.
### Speak Mode
Enter this command to use TTS _(Text-to-Speech)_ for AutoGPT
```shell
./run.sh --speak
```
### 💀 Continuous Mode ⚠️
#### 💀 Continuous Mode ⚠️
Run the AI **without** user authorization, 100% automated.
Continuous mode is NOT recommended.
@@ -66,57 +108,106 @@ Use at your own risk.
To exit the program, press ++ctrl+c++
### ♻️ Self-Feedback Mode ⚠️
### `serve` &ndash; Agent Protocol mode with UI
Running Self-Feedback will **INCREASE** token use and thus cost more. This feature enables the agent to provide self-feedback by verifying its own actions and checking if they align with its current goals. If not, it will provide better feedback for the next loop. To enable this feature for the current loop, input `S` into the input field.
With `serve`, the application exposes an Agent Protocol compliant API and serves a
frontend, by default on `http://localhost:8000`.
### GPT-3.5 ONLY Mode
If you don't have access to GPT-4, this mode allows you to use AutoGPT!
<details>
<summary>
<code>./run.sh serve --help</code>
</summary>
```shell
./run.sh --gpt3only
$ ./run.sh serve --help
Usage: python -m autogpt serve [OPTIONS]
Starts an Agent Protocol compliant AutoGPT server, which creates a custom
agent for every task.
Options:
-P, --prompt-settings FILE Specifies which prompt_settings.yaml file to
use.
--debug Enable Debug Mode
--gpt3only Enable GPT3.5 Only Mode
--gpt4only Enable GPT4 Only Mode
-b, --browser-name TEXT Specifies which web-browser to use when using
selenium to scrape the web.
--allow-downloads Dangerous: Allows AutoGPT to download files
natively.
--install-plugin-deps Installs external dependencies for 3rd party
plugins.
--help Show this message and exit.
```
</details>
You can achieve the same by setting `SMART_LLM` in `.env` to `gpt-3.5-turbo`.
For more information about the API of the application, see [agentprotocol.ai](https://agentprotocol.ai).
### GPT-4 ONLY Mode
<!-- TODO: add guide/manual for frontend -->
If you have access to GPT-4, this mode allows you to use AutoGPT solely with GPT-4.
This may give your bot increased intelligence.
### Arguments
```shell
./run.sh --gpt4only
```
!!! attention
Most arguments are equivalent to configuration options. See [`.env.template`] for
all available configuration options.
!!! warning
Since GPT-4 is more expensive to use, running AutoGPT in GPT-4-only mode will
increase your API costs.
!!! note
Replace anything in angled brackets (<>) to a value you want to specify
Here are some common arguments you can use when running AutoGPT:
* Run AutoGPT with a different AI Settings file
```shell
./run.sh --ai-settings <filename>
```
* Run AutoGPT with a different Prompt Settings file
```shell
./run.sh --prompt-settings <filename>
```
!!! note
There are shorthands for some of these flags, for example `-P` for `--prompt-settings`.
Use `./run.sh --help` for more information.
[`.env.template`]: https://github.com/Significant-Gravitas/AutoGPT/tree/docs/streamline-getting-started/autogpts/autogpt/.env.template
## Agent State
[agent state]: #agent-state
The state of individual agents is stored in the `data/agents` folder. You can use this
in various ways:
* Resume your agent at a later time.
* Create "checkpoints" for your agent so you can always go back to specific points in
its history.
* Share your agent!
## Logs
Activity, Error, and Debug logs are located in `./logs`
Activity, Error, and Debug logs are located in `logs`.
!!! tip
!!! tip
Do you notice weird behavior with your agent? Do you have an interesting use case? Do you have a bug you want to report?
Follow the step below to enable your logs. You can include these logs when making an issue report or discussing an issue with us.
To print out debug logs:
```shell
./run.sh --debug # on Linux / macOS
.\run.bat --debug # on Windows
docker-compose run --rm auto-gpt --debug # in Docker
./run.sh --debug
```
## Disabling Command Categories
If you want to selectively disable some command groups, you can use the `DISABLED_COMMAND_CATEGORIES` config in your `.env`. You can find the list of categories in your `.env.template`
If you want to selectively disable some command groups, you can use the
`DISABLED_COMMAND_CATEGORIES` config in your `.env`. You can find the list of available
categories [here][command categories].
For example, to disable coding related features, set it to the value below:
```ini
DISABLED_COMMAND_CATEGORIES=autogpt.commands.execute_code
```
[command categories]: https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpts/autogpt/autogpt/commands/__init__.py

25
docs/content/benchmarks/benchmark.md
View File

@@ -1,25 +0,0 @@
# Auto-GPT Benchmarks
Built for the purpose of benchmarking the performance of agents regardless of how they work.
Objectively know how well your agent is performing in categories like code, retrieval, memory, and safety.
Save time and money while doing it through smart dependencies. The best part? It's all automated.
## Scores:
<img width="733" alt="Screenshot 2023-07-25 at 10 35 01 AM" src="https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/assets/9652976/98963e0b-18b9-4b17-9a6a-4d3e4418af70">
## Ranking overall:
- 1- [Beebot](https://github.com/AutoPackAI/beebot)
- 2- [mini-agi](https://github.com/muellerberndt/mini-agi)
- 3- [Auto-GPT](https://github.com/Significant-Gravitas/AutoGPT)
## Detailed results:
<img width="733" alt="Screenshot 2023-07-25 at 10 42 15 AM" src="https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/assets/9652976/39be464c-c842-4437-b28a-07d878542a83">
[Click here to see the results and the raw data!](https://docs.google.com/spreadsheets/d/1WXm16P2AHNbKpkOI0LYBpcsGG0O7D8HYTG5Uj0PaJjA/edit#gid=203558751)!
More agents coming soon !

16
docs/content/forge/get-started.md
View File

@@ -1,12 +1,12 @@
# **AutoGPT-Forge**: Build Your Own AutoGPT Agent!
# AutoGPT Forge
### 🌌 Dive into the Universe of AutoGPT Creation! 🌌
### 🛠️ Build your own Agent 🛠️
Ever dreamt of becoming the genius behind an AI agent? Dive into the *Forge*, where **you** become the creator!
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.
---
### 🛠️ **Why AutoGPT-Forge?**
### 🛠️ **Why AutoGPT Forge?**
- 💤 **No More Boilerplate!** - Don't let the mundane tasks stop you. Fork and build without the headache of starting from scratch!
- 🧠 **Brain-centric Development!** - All the tools you need so you can spend 100% of your time on what matters - crafting the brain of your AI!
- 🛠️ **Tooling ecosystem!** - We work with the best in class tools to bring you the best experience possible!
@@ -25,7 +25,7 @@ The getting started [tutorial series](https://aiedge.medium.com/autogpt-forge-e3
Coming soon:
3. Interacting with and Benchmarking your Agent
4. Abilities
5. The Planning Loop
6. Memories
5. Interacting with and Benchmarking your Agent
6. Abilities
7. The Planning Loop
8. Memories

62
docs/content/front-end/the-ui.md
View File

@@ -1,62 +0,0 @@
# AutoGPT Flutter Client
## Description
This repository contains the Flutter client for the AutoGPT project. The application facilitates users in discussing various tasks with a single agent. The app is built to be cross-platform and runs on Web, Android, iOS, Windows, and Mac.
## Features
- List and manage multiple tasks.
- Engage in chat conversations related to selected tasks.
## Design document
The design document for this project provides a detailed outline of the architecture, components, and other important aspects of this application. Please note that this is a living, growing document and it is subject to change as the project evolves.
You can access the design document [here](https://docs.google.com/document/d/1S-o2np1gq5JwFq40wPHDUVLi-mylz4WMvCB8psOUjc8/).
## Requirements
- Flutter 3.x
- Dart 3.x
Flutter comes with Dart, to install Flutter, follow the instructions here: https://docs.flutter.dev/get-started/install
## Installation
1. **Clone the repo:**
```
git clone https://github.com/Significant-Gravitas/AutoGPT.git
```
2. **Navigate to the project directory:**
```
cd AutoGPT/frontend
```
3. **Get Flutter packages:**
```
flutter pub get
```
4. **Run the app:**
```
flutter run -d chrome --web-port 5000
```
## Project Structure
- `lib/`: Contains the main source code for the application.
- `models/`: Data models that define the structure of the objects used in the app.
- `views/`: The UI components of the application.
- `viewmodels/`: The business logic and data handling for the views.
- `services/`: Contains the service classes that handle communication with backend APIs and other external data sources. These services are used to fetch and update data that the app uses, and they are consumed by the ViewModels.
- `test/`: Contains the test files for unit and widget tests.
## Responsive Design
The app features a responsive design that adapts to different screen sizes and orientations. On larger screens (Web, Windows, Mac), views are displayed side by side horizontally. On smaller screens (Android, iOS), views are displayed in a tab bar controller layout.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

56
docs/content/index.md
View File

@@ -1,14 +1,27 @@
# AutoGPT docs
# AutoGPT Documentation
Welcome to the AutoGPT Docs.
Welcome to the AutoGPT Documentation.
The AutoGPT project has been divided into four distinct sections: [Agents](#welcome-to-the-heart-of-autogpt), [Benchmarks](#autogpt-benchmarks), [Forge](#autogpt-forge), and [Frontend](#frontend)
The AutoGPT project consists of four main components:
* The [Agent](#-agent) &ndash; also known as just "AutoGPT"
* The [Benchmark](#-benchmark) &ndash; AKA `agbenchmark`
* The [Forge](#-forge)
* The [Frontend](#-frontend)
To tie these together, we also have a CLI at the root of the project.
---
## [Welcome to the heart of AutoGPT](AutoGPT/setup.md)
## 🤖 Agent
Welcome to the heart of AutoGPT, the project that kicked it all off: a semi-autonomous agent powered by LLMs to execute any task for you*.
**[📖 About AutoGPT](AutoGPT/index.md)**
&ensp;|&ensp;
**[🔧 Setup](AutoGPT/setup/index.md)**
&ensp;|&ensp;
**[💻 Usage](AutoGPT/usage.md)**
The heart of AutoGPT, and the project that kicked it all off: a semi-autonomous agent powered by LLMs to execute any task for you*.
We continue to develop this project with the goal of providing access to AI assistance to the masses, and building the future transparently and together.
@@ -20,27 +33,39 @@ We continue to develop this project with the goal of providing access to AI assi
---
## [AutoGPT-Benchmarks](benchmarks/benchmark.md)
## 🎯 Benchmark
Test to impress with AutoGPT Benchmarks! Our benchmarking system offers a stringent testing environment to evaluate your agents objectively.
**[🗒️ Readme](https://github.com/Significant-Gravitas/AutoGPT/blob/master/benchmark/README.md)**
- 📈 **Top Performance** - Among our currently benchmarked agents, AutoGPT consistently scores the best. The top-performing generalist agent will earn its position as the primary AutoGPT post-hackathon.
Measure your agent's performance! The `agbenchmark` can be used with any agent that supports the agent protocol, and the integration with the project's CLI makes it even easier to use with AutoGPT and forge-based agents. The benchmark offers a stringent testing environment. Our framework allows for autonomous, objective performance evaluations, ensuring your agents are primed for real-world action.
- 🔌 **Agent Protocol Standardization** - AutoGPT uses the agent protocol from the AI Engineer Foundation to ensure seamless compatibility.
<!-- TODO: insert visual demonstrating the benchmark -->
- 📦 [**`agbenchmark`**](https://pypi.org/project/agbenchmark/) on Pypi
- 🔌 **Agent Protocol Standardization** - AutoGPT uses the agent protocol from the AI Engineer Foundation to ensure compatibility with many agents, both from within and outside the project.
---
## [AutoGPT-Forge](forge/get-started.md)
## 🏗️ Forge
Forge your future with AutoGPT! The Forge is your innovation lab.
**[📖 Introduction](forge/get-started.md)**
&ensp;|&ensp;
**[🚀 Quickstart](https://github.com/Significant-Gravitas/AutoGPT/blob/master/QUICKSTART.md)**
- 🏗️ **Building with Ease** - We've set the groundwork so you can focus on your agent's personality and capabilities. Comprehensive tutorials are available [Here](https://aiedge.medium.com/autogpt-forge-e3de53cc58ec).
<!-- TODO: have the guides all in one place -->
Forge your own agent! The 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.
- 🛠️ **Building with Ease** - We've set the groundwork so you can focus on your agent's personality and capabilities. Comprehensive tutorials are available [here](https://aiedge.medium.com/autogpt-forge-e3de53cc58ec).
---
## [Frontend](front-end/the-ui.md)
## 💻 Frontend
Harness your AI journey with the AutoGPT FrontEnd.
**[🗒️ Readme](https://github.com/Significant-Gravitas/AutoGPT/blob/master/frontend/README.md)**
An easy-to-use and open source frontend for any Agent Protocol-compliant agent.
- 🎮 **User-Friendly Interface** - Manage your agents effortlessly.
@@ -48,7 +73,8 @@ Harness your AI journey with the AutoGPT FrontEnd.
---
[Join the AutoGPT Discord server for any queries](discord.gg/autogpt)
🤔 Join the AutoGPT Discord server for any queries:
[discord.gg/autogpt](https://discord.gg/autogpt)
### Glossary of Terms

63
docs/mkdocs.yml
View File

@@ -6,49 +6,48 @@ nav:
- Home: index.md
- AutoGPT Agent:
- Agent-setup:
- Setting up AutoGPT: AutoGPT/setup.md
- Docker-setup: AutoGPT/Setups/Docker-setup.md
- Git-setup: AutoGPT/Setups/Git-setup.md
- No Git/Docker-setup: AutoGPT/Setups/nogit-setup.md
- Introduction: AutoGPT/index.md
- Setup:
- Setting up AutoGPT: AutoGPT/setup/index.md
- Set up with Docker: AutoGPT/setup/docker.md
- Usage: AutoGPT/usage.md
- Plugins: AutoGPT/plugins.md
- Configuration:
- Options: AutoGPT/configuration/options.md
- Search: AutoGPT/configuration/search.md
- Memory: AutoGPT/configuration/memory.md
- Voice: AutoGPT/configuration/voice.md
- Image Generation: AutoGPT/configuration/imagegen.md
# - Configuration:
# - Options: AutoGPT/configuration/options.md
# - Search: AutoGPT/configuration/search.md
# - Memory: AutoGPT/configuration/memory.md
# - Voice: AutoGPT/configuration/voice.md
# - Image Generation: AutoGPT/configuration/imagegen.md
- Help us improve AutoGPT:
- Share your debug logs with us: AutoGPT/share-your-logs.md
- Contribution guide: contributing.md
- Running tests: AutoGPT/testing.md
- Code of Conduct: code-of-conduct.md
- AutoGPT-Benchmarks:
- Benchmarks: benchmarks/benchmark.md
- Benchmark:
- Readme: https://github.com/Significant-Gravitas/AutoGPT/blob/master/benchmark/README.md
- AutoGPT-Forge:
- Forge-setup: forge/get-started.md
- Forge:
- Introduction: forge/get-started.md
- Frontend:
- Flutter-setup: front-end/the-ui.md
- Readme: https://github.com/Significant-Gravitas/AutoGPT/blob/frontend/README.md
- Challenges:
- Introduction: challenges/introduction.md
- List of Challenges:
- Memory:
- Introduction: challenges/memory/introduction.md
- Memory Challenge A: challenges/memory/challenge_a.md
- Memory Challenge B: challenges/memory/challenge_b.md
- Memory Challenge C: challenges/memory/challenge_c.md
- Memory Challenge D: challenges/memory/challenge_d.md
- Information retrieval:
- Introduction: challenges/information_retrieval/introduction.md
- Information Retrieval Challenge A: challenges/information_retrieval/challenge_a.md
- Information Retrieval Challenge B: challenges/information_retrieval/challenge_b.md
- Submit a Challenge: challenges/submit.md
- Beat a Challenge: challenges/beat.md
# - Challenges:
# - Introduction: challenges/introduction.md
# - List of Challenges:
# - Memory:
# - Introduction: challenges/memory/introduction.md
# - Memory Challenge A: challenges/memory/challenge_a.md
# - Memory Challenge B: challenges/memory/challenge_b.md
# - Memory Challenge C: challenges/memory/challenge_c.md
# - Memory Challenge D: challenges/memory/challenge_d.md
# - Information retrieval:
# - Introduction: challenges/information_retrieval/introduction.md
# - Information Retrieval Challenge A: challenges/information_retrieval/challenge_a.md
# - Information Retrieval Challenge B: challenges/information_retrieval/challenge_b.md
# - Submit a Challenge: challenges/submit.md
# - Beat a Challenge: challenges/beat.md
- License: https://github.com/Significant-Gravitas/AutoGPT/blob/master/LICENSE
@@ -129,4 +128,4 @@ extra_javascript:
- _javascript/tablesort.js
- _javascript/mathjax.js
- https://polyfill.io/v3/polyfill.min.js?features=es6
- https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js
- https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js