Source: https://seerepo.com/r/simular-ai/Agent-S/built
Markdown source: https://seerepo.com/r/simular-ai/Agent-S/built.md
Description: Agent-S is a Python repo built with FastAPI and uvicorn. It uses AI through openai, PaddlePaddle, together, mcp, scikit-learn, and 2 more.

# What is Agent-S built with?

Agent-S is a Python repo built with FastAPI and uvicorn. It uses AI through openai, PaddlePaddle, together, mcp, scikit-learn, and 2 more, connects to Google, makes its content with beautifulsoup4, imageio-ffmpeg, pillow, pytesseract, and lxml, validates its data with Pydantic, is tested with Selenium, Pytest, and playwright, and deploys with boto3. It has 55,076 written lines, with 80 test files.

Read on November 10, 2026, at commit 0fff0e6.

Repository: https://github.com/simular-ai/Agent-S

## Backend

### The base

- **[FastAPI](https://seerepo.com/uses/fastapi)**: 1 file
- **[uvicorn](https://seerepo.com/uses/uvicorn)**: 1 file

### AI

- **[openai](https://seerepo.com/uses/openai)**
- **PaddlePaddle**
- **together**
- **[mcp](https://seerepo.com/uses/mcp)**: 2 files
- **[scikit-learn](https://seerepo.com/uses/scikit-learn)**: 2 files
- **[tiktoken](https://seerepo.com/uses/tiktoken)**: 2 files
- **paddleocr**: 1 file

### Services

- **[Google](https://seerepo.com/uses/google)**: 1 file · [gui_agents/s2/core/engine.py, line 1](https://github.com/simular-ai/Agent-S/blob/0fff0e634869dab72027435b4586e62300185d41/gui_agents/s2/core/engine.py#L1)

## Support

### Content

- **[beautifulsoup4](https://seerepo.com/uses/beautifulsoup4)**
- **[imageio-ffmpeg](https://seerepo.com/uses/imageio-ffmpeg)**
- **[pillow](https://seerepo.com/uses/pillow)**: 12 files
- **pytesseract**: 3 files
- **[lxml](https://seerepo.com/uses/lxml)**: 1 file

### Validation

- **[Pydantic](https://seerepo.com/uses/pydantic)**: 3 files

### Testing

- **Selenium**
- **Pytest**: 49 files
- **playwright**: 1 file

### Deploy

- **[boto3](https://seerepo.com/uses/boto3)**: 3 files

### Tools

- **Black**
- **ipykernel**: 1 file
- **tyro**: 1 file

### Other

- **dill**
- **nest-asyncio**
- **pandas**
- **pyobjc**
- **python-gitlab**
- **pywin32**
- **pyyaml**
- **SciPy**
- **tomli**
- **websockets**
- **NumPy**: 14 files
- **requests**: 10 files
- **python-dotenv**: 7 files
- **backoff**: 4 files
- **pyautogui**: 4 files
- **httpx**: 1 file
- **toml**: 1 file

## Other repos with a similar stack

- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): Google, OpenAI, PaddlePaddle, MCP, scikit-learn, tiktoken, paddleocr, beautifulsoup4, pillow, pytesseract, lxml, Pydantic, boto3 · [Compare](https://seerepo.com/compare/run-llama/llama_index/vs/simular-ai/Agent-S)
- [onyx-dot-app/onyx](https://seerepo.com/r/onyx-dot-app/onyx/built): FastAPI, uvicorn, Google, OpenAI, MCP, scikit-learn, tiktoken, beautifulsoup4, pillow, lxml, Pydantic, boto3 · [Compare](https://seerepo.com/compare/onyx-dot-app/onyx/vs/simular-ai/Agent-S)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): FastAPI, uvicorn, Google, OpenAI, MCP, scikit-learn, tiktoken, beautifulsoup4, pillow, lxml, Pydantic · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/simular-ai/Agent-S)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): FastAPI, uvicorn, Google, scikit-learn, tiktoken, beautifulsoup4, imageio-ffmpeg, pillow, lxml, Pydantic, boto3 · [Compare](https://seerepo.com/compare/ray-project/ray/vs/simular-ai/Agent-S)
- [open-webui/open-webui](https://seerepo.com/r/open-webui/open-webui/built): FastAPI, uvicorn, OpenAI, MCP, tiktoken, beautifulsoup4, pillow, lxml, Pydantic, boto3 · [Compare](https://seerepo.com/compare/open-webui/open-webui/vs/simular-ai/Agent-S)
- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/built): FastAPI, uvicorn, OpenAI, MCP, scikit-learn, tiktoken, beautifulsoup4, pillow, lxml, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/hello-agents/vs/simular-ai/Agent-S)

## Frequently asked questions

### What language is Agent-S written in?

Agent-S is written in Python, with 55,076 written lines.

### What framework does Agent-S use?

Agent-S is built with FastAPI and uvicorn.

### Does Agent-S use AI?

Yes. Agent-S uses AI through openai, PaddlePaddle, together, mcp, scikit-learn, tiktoken, and paddleocr.

### What services does Agent-S use?

Agent-S connects to Google.

The proof: [gui_agents/s2/core/engine.py, line 1](https://github.com/simular-ai/Agent-S/blob/0fff0e634869dab72027435b4586e62300185d41/gui_agents/s2/core/engine.py#L1)

### Does Agent-S have tests?

Yes. Agent-S has 80 test files and is tested with Selenium, Pytest, and playwright.

### Which repos have a stack like Agent-S's?

The ones that share most of its stack: run-llama/llama_index, onyx-dot-app/onyx, and bojieli/ai-agent-book.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.