# LiteAgent
[](https://codecov.io/gh/Jannchie/lite-agent)
## Introduction
LiteAgent is an easy-to-learn, lightweight, and extensible AI agent framework built on top of [LiteLLM](https://github.com/BerriAI/litellm). It is designed as a minimal yet practical implementation for quickly building intelligent assistants and chatbots with robust tool-calling capabilities. The codebase is intentionally simple, making it ideal for learning, extension, and rapid prototyping.
**Key Advantages:**
- **Minimal and approachable:** The simplest agent implementation for fast learning and hacking.
- **Accurate and complete type hints:** All function signatures are fully type-hinted and never faked, ensuring reliable developer experience and static analysis.
- **Flexible parameter definition:** Supports defining tool function parameters using basic types, Pydantic models, or Python dataclasses—even in combination.
- **Streaming responses:** Seamless support for LiteLLM streaming output.
- **Custom tool functions:** Easily integrate your own Python functions (e.g., weather, temperature queries).
- **Rich type annotations, Pydantic-based.**
- **Easy to extend and test.**
## Installation
You can install LiteAgent directly from PyPI:
```bash
pip install lite-agent
```
Or use [uv](https://github.com/astral-sh/uv):
```bash
uv pip install lite-agent
```
If you want to install from source for development:
```bash
uv pip install -e .
# or
pip install -e .
```
## Quick Start
### Code Example
See `examples/basic.py`:
```python
import asyncio
from lite_agent.agent import Agent
from lite_agent.runner import Runner
async def get_whether(city: str) -> str:
await asyncio.sleep(1)
return f"The weather in {city} is sunny with a few clouds."
async def main():
agent = Agent(
model="gpt-4.1",
name="Weather Assistant",
instructions="You are a helpful weather assistant.",
tools=[get_whether],
)
runner = Runner(agent)
resp = await runner.run_until_complete("What's the weather in New York?")
for chunk in resp:
print(chunk)
if __name__ == "__main__":
asyncio.run(main())
```
See `pyproject.toml` for details.
## Testing
```bash
pytest
```
## License
MIT License
## Author
Jianqi Pan ([jannchie@gmail.com](mailto:jannchie@gmail.com))
Raw data
{
"_id": null,
"home_page": null,
"name": "lite-agent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "AI, agent framework, assistant, chatbot, function call, openai, pydantic, rich, tooling",
"author": null,
"author_email": "Jianqi Pan <jannchie@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/4e/cb/55b17396d6554a7b1d4068925013546382d2f4fe78275082696c1a037615/lite_agent-0.14.1.tar.gz",
"platform": null,
"description": "# LiteAgent\n\n[](https://codecov.io/gh/Jannchie/lite-agent)\n\n## Introduction\n\nLiteAgent is an easy-to-learn, lightweight, and extensible AI agent framework built on top of [LiteLLM](https://github.com/BerriAI/litellm). It is designed as a minimal yet practical implementation for quickly building intelligent assistants and chatbots with robust tool-calling capabilities. The codebase is intentionally simple, making it ideal for learning, extension, and rapid prototyping.\n\n**Key Advantages:**\n\n- **Minimal and approachable:** The simplest agent implementation for fast learning and hacking.\n- **Accurate and complete type hints:** All function signatures are fully type-hinted and never faked, ensuring reliable developer experience and static analysis.\n- **Flexible parameter definition:** Supports defining tool function parameters using basic types, Pydantic models, or Python dataclasses\u2014even in combination.\n- **Streaming responses:** Seamless support for LiteLLM streaming output.\n- **Custom tool functions:** Easily integrate your own Python functions (e.g., weather, temperature queries).\n- **Rich type annotations, Pydantic-based.**\n- **Easy to extend and test.**\n\n## Installation\n\nYou can install LiteAgent directly from PyPI:\n\n```bash\npip install lite-agent\n```\n\nOr use [uv](https://github.com/astral-sh/uv):\n\n```bash\nuv pip install lite-agent\n```\n\nIf you want to install from source for development:\n\n```bash\nuv pip install -e .\n# or\npip install -e .\n```\n\n## Quick Start\n\n### Code Example\n\nSee `examples/basic.py`:\n\n```python\nimport asyncio\nfrom lite_agent.agent import Agent\nfrom lite_agent.runner import Runner\n\nasync def get_whether(city: str) -> str:\n await asyncio.sleep(1)\n return f\"The weather in {city} is sunny with a few clouds.\"\n\nasync def main():\n agent = Agent(\n model=\"gpt-4.1\",\n name=\"Weather Assistant\",\n instructions=\"You are a helpful weather assistant.\",\n tools=[get_whether],\n )\n runner = Runner(agent)\n resp = await runner.run_until_complete(\"What's the weather in New York?\")\n for chunk in resp:\n print(chunk)\n\nif __name__ == \"__main__\":\n asyncio.run(main())\n```\n\nSee `pyproject.toml` for details.\n\n## Testing\n\n```bash\npytest\n```\n\n## License\n\nMIT License\n\n## Author\n\nJianqi Pan ([jannchie@gmail.com](mailto:jannchie@gmail.com))\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A lightweight, extensible framework for building AI agent.",
"version": "0.14.1",
"project_urls": null,
"split_keywords": [
"ai",
" agent framework",
" assistant",
" chatbot",
" function call",
" openai",
" pydantic",
" rich",
" tooling"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e863fe14b28271ee35ae2df3ab5733110a444f76d9c4cd55f057926936975459",
"md5": "34199831bcedfbda3fc86a949d24f9ae",
"sha256": "a8e8a8ffbfaf48aefa219ea4635c360f7226f94d847166d947b8c1359cdda019"
},
"downloads": -1,
"filename": "lite_agent-0.14.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "34199831bcedfbda3fc86a949d24f9ae",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 55262,
"upload_time": "2025-09-04T01:31:45",
"upload_time_iso_8601": "2025-09-04T01:31:45.393095Z",
"url": "https://files.pythonhosted.org/packages/e8/63/fe14b28271ee35ae2df3ab5733110a444f76d9c4cd55f057926936975459/lite_agent-0.14.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "4ecb55b17396d6554a7b1d4068925013546382d2f4fe78275082696c1a037615",
"md5": "8fc6bd5abe03b8f97d75a4b30280c8ab",
"sha256": "a20f9d694175952be44f12336c3aef8f1a9e79b0809e81199fd9625eb6833ee3"
},
"downloads": -1,
"filename": "lite_agent-0.14.1.tar.gz",
"has_sig": false,
"md5_digest": "8fc6bd5abe03b8f97d75a4b30280c8ab",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 376148,
"upload_time": "2025-09-04T01:31:46",
"upload_time_iso_8601": "2025-09-04T01:31:46.784798Z",
"url": "https://files.pythonhosted.org/packages/4e/cb/55b17396d6554a7b1d4068925013546382d2f4fe78275082696c1a037615/lite_agent-0.14.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-04 01:31:46",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "lite-agent"
}
JSON