Skip to main content

AI Agent SDK

Project description

🇨🇳中文 | 🌐English | 🇯🇵日本語


Agentica: Build AI Agents

PyPI version Downloads License Apache 2.0 python_version GitHub issues Wechat Group

Agentica 是一个轻量级 Python 框架,用于构建 AI 智能体。Async-First 架构,支持工具调用、RAG、多智能体团队、工作流编排和 MCP 协议。

安装

pip install -U agentica

快速开始

import asyncio
from agentica import Agent, ZhipuAI

async def main():
    agent = Agent(model=ZhipuAI())
    result = await agent.run("一句话介绍北京")
    print(result.content)

asyncio.run(main())
北京是中国的首都,是一座拥有三千多年历史的文化名城,也是全国的政治、文化和国际交流中心。

需要先设置 API Key:

export ZHIPUAI_API_KEY="your-api-key"      # 智谱AI(glm-4.7-flash 免费)
export OPENAI_API_KEY="sk-xxx"              # OpenAI
export DEEPSEEK_API_KEY="your-api-key"      # DeepSeek

功能特性

  • Async-First — 原生 async API,asyncio.gather() 并行工具执行,同步适配器兼容
  • 20+ 模型 — OpenAI / DeepSeek / Claude / 智谱 / Qwen / Moonshot / Ollama / LiteLLM 等
  • 40+ 内置工具 — 搜索、代码执行、文件操作、浏览器、OCR、图像生成
  • RAG — 知识库管理、混合检索、Rerank,集成 LangChain / LlamaIndex
  • 多智能体 — Team(动态委派)和 Workflow(确定性编排)
  • 安全守卫 — 输入/输出/工具级 Guardrails
  • MCP / ACP — Model Context Protocol 和 Agent Communication Protocol 支持
  • Skill 系统 — 基于 Markdown 的技能注入,模型无关
  • 多模态 — 文本、图像、音频、视频理解

CLI

agentica --model_provider zhipuai --model_name glm-4.7-flash

Web UI

通过 agentica-gateway 提供 Web 页面,同时支持飞书 App、企业微信直连调用 Agentica。

示例

查看 examples/ 获取完整示例,涵盖:

类别 内容
基础用法 Hello World、流式输出、结构化输出、多轮对话、多模态
工具 自定义工具、Async 工具、搜索、代码执行、文件操作
Agent 模式 Agent 作为工具、并行执行、团队协作、辩论
RAG PDF 问答、高级 RAG、LangChain / LlamaIndex 集成
工作流 数据管道、投资研究、新闻报道、代码审查
MCP Stdio / SSE / HTTP 传输、JSON 配置
应用 LLM OS、深度研究、客服系统

→ 查看完整示例目录

文档

完整使用文档:https://shibing624.github.io/agentica

社区与支持

  • GitHub Issues提交 issue
  • 微信群 — 添加微信号 xuming624,备注 "llm",加入技术交流群

引用

如果您在研究中使用了 Agentica,请引用:

Xu, M. (2026). Agentica: A Human-Centric Framework for Large Language Model Agent Workflows. GitHub. https://github.com/shibing624/agentica

许可证

Apache License 2.0

贡献

欢迎贡献!请查看 CONTRIBUTING.md

致谢

Project details


Download files

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

Source Distribution

agentica-1.3.2.tar.gz (369.9 kB view details)

Uploaded Source

Built Distribution

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

agentica-1.3.2-py3-none-any.whl (465.2 kB view details)

Uploaded Python 3

File details

Details for the file agentica-1.3.2.tar.gz.

File metadata

  • Download URL: agentica-1.3.2.tar.gz
  • Upload date:
  • Size: 369.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for agentica-1.3.2.tar.gz
Algorithm Hash digest
SHA256 08a12237466ce050e71314e34e3a521754c16a1dd20a17fb224044f3c966d4f1
MD5 b4add1111189958eb9ef01c0c896e1e7
BLAKE2b-256 523a4414f80d54e6dae65a7a727bc82d723ebd29d1e130dcb29233030951f280

See more details on using hashes here.

File details

Details for the file agentica-1.3.2-py3-none-any.whl.

File metadata

  • Download URL: agentica-1.3.2-py3-none-any.whl
  • Upload date:
  • Size: 465.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for agentica-1.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 8c20c2f35ad7d5b2c61665a9c754ce17368ed9815ab2f843d1b9108c5b99351c
MD5 9da33acd7b4fd30397f1d84d4a3cdf24
BLAKE2b-256 a822edb592b0682be656eb00f3109a32d6480f71f460ddf12a51a40c22f8f8ad

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page