Skip to main content

RootDriver

根源出发,驱动万物

一个轻量级的 Python AI Agent 开发框架。

解决痛点:

  • 想快速跑一个 Agent?一行代码,不需要编排、不需要懂设计模式
  • 市面框架太重、太复杂、学习成本高?RootDriver 核心代码几千行,不用记几百个 API
  • 需要扩展?按需添加,想加什么加什么,不被框架绑架

特性

  • 简洁易用:装饰器方式定义工具,快速构建 Agent
  • 模块化设计:LLM 适配器、工具系统、会话管理解耦
  • 工具调用:支持 function calling,自动执行工具并返回结果
  • 状态管理:支持内存和数据库持久化检查点
  • 异常体系:完整的异常类层次结构
  • 异步支持:全面异步支持,并发 Agent / 工具调用

安装

pip install rootdriver

快速开始

定义工具

from rootdriver import tool

@tool
def get_weather(city: str) -> str:
    """获取城市天气"""
    return f"{city} 晴天"

创建 Agent

from rootdriver import Agent, AgentLLM, OpenAIAdapter

agent_llm = AgentLLM(
    adapter=OpenAIAdapter(
        api_key="YOUR_API_KEY",
        base_url="BASE_URL"
    ),
    model= "gpt-4",
    temperature=0.7
    )


agent = Agent(
    agent_llm=agent_llm,
    tools=[get_weather],
    system_prompt="你是一个有用的助手",
)

# 单次对话(无 tool)
response = agent.talk("北京天气怎么样?")
print(response)

使用工具

# 完整对话循环(包含工具调用)
response = agent.react("帮我查下上海天气")
print(response)

异步用法

import asyncio
from rootdriver import Agent, AgentLLM, OpenAIAdapter

async def main():

    # 单次异步对话
    response = await agent.atalk("你好")
    print(response)

    # 并发多个 Agent
    results = await asyncio.gather(
        agent.areact("问题1"),
        agent.areact("问题2"),
        agent.areact("问题3"),
    )

asyncio.run(main())

记忆持久化

Agent 支持对话历史自动持久化到 JSON 文件:

agent = Agent(
    agent_llm=agent_llm,
    system_prompt="你是一个有用的助手",
    db_path="conversations.json",     # 记忆数据库路径
    auto_save=True,            # 开启自动保存(默认开启)
)

# 对话自动增量保存到 memory.json
response = agent.react("我们之前聊了什么?")

# 新建 Agent 时可从数据库恢复对话历史
agent2 = Agent(agent_llm=agent_llm, id="same_user", db_path="memory.json")
agent2.state.load_from_db("auto_saved")  # 恢复对话

手动检查点

# 内存快照
agent.state.checkpoint("backup_point")

# 保存到数据库
agent.state.save_from_checkpoints(name="my_backup", checkpoint_name="backup_point")

# 从数据库加载
agent.state.load_from_db("my_backup")

核心组件

组件 说明
Agent 智能体入口,整合 LLM、工具、会话
Engine 核心引擎,处理对话循环和工具调用
Conversation 会话管理,维护消息历史
LLM LLM 调用封装
Tool 工具集合,管理所有可调用工具
State 状态管理,支持检查点和持久化
JsonDB JSON 文件数据库封装

项目结构

rootdriver/
├── agent.py           # Agent 智能体
├── engine.py          # 引擎核心
├── conversation.py    # 对话管理
├── state/             # 状态管理包
│   └── state.py       # State 实现
├── db/                # 数据库封装包
│   └── json_db.py     # JsonDB 实现
├── exception.py       # 异常定义
├── llm/
│   ├── llm.py         # LLM 封装
│   ├── base_adapter.py    # 适配器基类
│   └── adapter/
│       └── openai_adapter.py  # OpenAI 适配器
├── tool/
│   ├── base_tool.py   # 工具基类
│   └── tools.py       # 工具集
├── types/             # 类型定义
└── utils/             # 工具函数

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rootdriver-0.4.0.tar.gz (13.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rootdriver-0.4.0-py3-none-any.whl (8.2 kB view details)

Uploaded Python 3

File details

Details for the file rootdriver-0.4.0.tar.gz.

File metadata

  • Download URL: rootdriver-0.4.0.tar.gz
  • Upload date:
  • Size: 13.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.7

File hashes

Hashes for rootdriver-0.4.0.tar.gz
Algorithm Hash digest
SHA256 4c87f81311ef1d70ed56859bbf8ffe3bd75ece6492bae5e30cfeb3515320e720
MD5 9029c17e181a5d106dc7827a9da58514
BLAKE2b-256 cb7437ba0c2cc4a49801f6fdcacc1d58386c35b026ca3a5420f5518ed6147c45

See more details on using hashes here.

File details

Details for the file rootdriver-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: rootdriver-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 8.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.7

File hashes

Hashes for rootdriver-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 60b57ce20649f0c46b4ff02fcdd030e8dad16928ba797b202d40dcbf6f446ec4
MD5 5ed0d99807be7f4ed29b11d4b9bda452
BLAKE2b-256 9bc84d33883b1e90c9502080ae09bd585b9ee3c9cd559b3ec6ca1c61779f0b9e

See more details on using hashes here.

Release history Release notifications | RSS feed

0.9.3

2 files

0.9.2

2 files

0.9.1

2 files

0.9.0

2 files

0.8.2

2 files

0.8.1

2 files

0.8.0

2 files

0.7.1

2 files

0.7.0

2 files

0.6.1

2 files

0.6.0

2 files

0.5.0

2 files

0.4.3

2 files

0.4.2

2 files

0.4.1

2 files

This release

0.4.0 This release

2 files

0.3.0

2 files

0.2.0

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page