agentx - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #llm #android #machine-learning #rust #linux #macos #awesome #vue #awesome-list #pytorch #mcp #open-source

agentx

(★ 100)

AgentX is an experiment to develop autonomous agents so you can automate everything! This project is inspired by Auto-GPT, babyagi, SuperAGI, and other agents.

파일 탐색기

최종 버전 다운로드 (.zip)

- - linting-and-testing.yml
- - __init__.py
  - faiss.py
- __init__.py
- autogpt.py
- baby_agi_with_tools.py
- python-minifier.py
- - __init__.py
- __init__.py
- conftest.py
.env.example
.flake8
.gitignore
LICENSE
poetry.lock
pyproject.toml
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/slavakurilyak/agentx

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd agentx

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

poetry install

pyproject.toml에 명시된 라이브러리를 설치합니다.

source $(poetry env info --path)/bin/activate

이 명령어를 터미널에 그대로 입력해 실행하세요.

poetry run python agentx/agents/autogpt/main.py

파이썬 스크립트(또는 모듈)를 실행합니다.

poetry run python agentx/agents/babyagi/main.py

파이썬 스크립트(또는 모듈)를 실행합니다.

poetry run python agentx/autogpt.py

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# AgentX

AgentX is an experiment to develop an autonomous agent that delegates well to Auto-GPT, babyagi, and other agents using LangChain. It is a LangChain-powered agent that delegates tasks to other AI agents until user's objective is complete. It aims to assist users in completing objectives using agent retrieval, whereby objectives are outsources to other AI agents (Auto-GPT, babyagi, HuggingFace) in parallel.

## Requirements

AgentX requires [Python 3.8](https://www.python.org/downloads/) and [Poetry](https://python-poetry.org/docs/#installation) for package management.

## Set Up

Here's how to install AgentX:

1. Clone the repository:

```bash
git clone git@github.com:slavakurilyak/agentx.git
cd agentx
```
2. Set up the project and activate the virtual environment via Poetry:

```bash
poetry install
source $(poetry env info --path)/bin/activate
```

3. Copy `.env.example` to `.env`:

```bash
cp .env.example .env
```

4. Update your `OPENAI_API_KEY` and `SERPAPI_API_KEY` values inside newly created `.env`

## Usage

To run the 'experimental version' of AgentX using Python, type:

```bash
python agentx/agents/autogpt/main.py
python agentx/agents/babyagi/main.py
```

-or-

```bash
poetry run python agentx/agents/autogpt/main.py
poetry run python agentx/agents/babyagi/main.py
```

To run the 'stable version' of AgentX using Python, type:

```bash
python agentx/autogpt.py
python agentx/baby_agi_with_tools.py
```

-or-

```bash
poetry run python agentx/autogpt.py
poetry run python agentx/baby_agi_with_tools.py

```

### Contibuting

We use `black`, `isort` and `flake8` to ensure good code quality.

Always run the linters to check your code using:

```bash
isort --check .
black --check .
flake8
```

-or-

```bash
poetry run isort --check .
poetry run black --check .
poetry run flake8
```

To use `isort` and `black` for autoformatting, run the commands without the `--check` option using:

```bash
isort .
black .
flake8
```

-or-

```bash
poetry run isort .
poetry run black .
poetry run flake8
```

Run tests in the root directory either using:

```bash
pytest
```

-or-

```bash
poetry run pytest
```

## How does AgentX work?

1. User requests assistance from AgentX.
2. AgentX retrieves necessary tools.
3. AgentX selects relevant tools.
4. Selected tools complete the task and their results are combined.
5. AgentX processes the combined results and presents the response to the user.

This user-AgentX interaction can be visualized as:

```mermaid
graph TB
A[User] --> B[AgentX]
B --> C[Find Relevant Agent]
C --> D{Delegate Task to Agent}
D --> E1[Auto-GPT]
D --> E2[BabyAGI]
D --> E3[HuggingFace]
D --> E4[Other AI Agent]
E1 --> F1[Complete Task with Auto-GPT]
E2 --> F2[Complete Task with BabyAGI]
E3 --> F3[Complete Task with HuggingFace]
E4 --> F4[Complete Task with Other AI Agent]
F1 --> G[Evaluate Task Completion]
F2 --> G
F3 --> G
F4 --> G
G --> H[AgentX]
H --> I[User]
```

## Benefits of using AgentX

-  Delegates tasks to multiple AI agents for efficient handling of complex tasks.
-  Can handle a wide range of tasks, from answering questions to creating to-do lists.
-  Can be customized to suit your specific needs.

## Limitations of AgentX

At present, AgentX is limited in its ability to interact with Auto-GPT and babyagi directly due to the following reasons:

-  These models do not currently have APIs available for interaction.
-  They also lack JSON manifest files such as `.well-known/ai-plugin.json` and `.well-known/openai.yaml`, which are required by OpenAI.

As a result of these limitations, AgentX can only interact with Auto-GPT and babyagi by directly cloning their source code using `$ git clone`. We will provide further information on these limitations shortly.

## Progress

- [x] BabyAGI using LangChain
- [x] Auto-GPT using LangChain
- [ ] Auto-GPT from source (see [issue](https://github.com/slavakurilyak/agentx/issues/1))
- [ ] babyagi from source (see [issue](https://github.com/slavakurilyak/agentx/issues/2))
- [ ] Teenage-AGI from source (see [issue](https://github.com/slavakurilyak/agentx/issues/3))

Sure, here's the section about contributions are welcome:

## Get involved

We appreciate your interest in AgentX! Here are some ways you can get involved:

-   If you like our project, please consider starring it on GitHub.
-   If you have an idea for a new feature or improvement, please open a new issue on GitHub.
-   If you see a bug or want to implement a feature, please open a new pull request on GitHub.
-   If you want to follow the founder on Twitter, visit [twitter.com/slavakurilyak](https://twitter.com/slavakurilyak).

Thank you for your support!

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=slavakurilyak/AgentX&type=Date)](https://star-history.com/#slavakurilyak/AgentX&Date)