diff --git a/README.md b/README.md index 5c721dc..0e9af4c 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,9 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理,属于社区翻译,非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/agentscope-ai/agentscope) · [上游 README](https://github.com/agentscope-ai/agentscope/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +

-[**中文主页**](https://github.com/agentscope-ai/agentscope/blob/main/README_zh.md) | [**Documentation**](https://docs.agentscope.io/) | [**Roadmap**](https://github.com/orgs/agentscope-ai/projects/2/views/1) +[**English Homepage**](https://github.com/agentscope-ai/agentscope/blob/main/README.md) | [**文档**](https://docs.agentscope.io/) | [**路线图**](https://github.com/orgs/agentscope-ai/projects/2/views/1) @@ -32,11 +38,11 @@ /> - discord - + discord + agentscope-ai%2Fagentscope | Trendshift

-## What is AgentScope 2.0? +## 什么是 AgentScope 2.0? -AgentScope 2.0 is a production-ready, easy-to-use agent framework with essential abstractions that work with rising model capability and built-in support for . +AgentScope 2.0 是一款面向生产、易于使用的智能体框架,提供与不断进化的模型能力相匹配的核心抽象。 -- [**Event System** →](https://docs.agentscope.io/latest/en/building-blocks/message-and-event) A unified event bus to the frontend and human-in-the-loop support. -- [**Permission System** →](https://docs.agentscope.io/latest/en/building-blocks/permission-system) Fine-grained, configurable control over tools and resources. -- [**Multi-tenancy & Multi-session Service** →](https://docs.agentscope.io/latest/en/deploy/agent-service) Production-grade serving with isolation across tenants and sessions. -- [**Workspace / Sandbox Support** →](https://docs.agentscope.io/latest/en/building-blocks/workspace) Run tools and code in isolated environments, with built-in backends for local, Docker, E2B, and OpenSandbox. -- [**Extensible Middleware System** →](https://docs.agentscope.io/latest/en/building-blocks/middleware) Composable hooks to customize and extend the agent's reasoning-acting loop. +- [**事件系统** →](https://docs.agentscope.io/latest/zh/building-blocks/message-and-event) 统一的事件总线,服务于前端智能体应用与 human-in-the-loop 协作。 +- [**权限系统** →](https://docs.agentscope.io/latest/zh/building-blocks/permission-system) 对工具和资源进行细粒度、可配置的控制。 +- [**多租户与多会话服务** →](https://docs.agentscope.io/latest/zh/deploy/agent-service) 提供生产级服务,在租户与会话之间实现隔离。 +- [**工作区 / 沙箱支持** →](https://docs.agentscope.io/latest/zh/building-blocks/workspace) 在隔离环境中运行工具和代码,内置支持本地文件系统、Docker、E2B 和 OpenSandbox 后端。 +- [**可扩展中间件系统** →](https://docs.agentscope.io/latest/zh/building-blocks/middleware) 可组合的钩子系统,用于自定义和扩展智能体的推理-行动循环。 -We design for increasingly agentic LLMs. -Our approach leverages the models' reasoning and tool use abilities -rather than constraining them with strict prompts and opinionated orchestrations. +我们为日益自主的大语言模型而设计。 +我们的方法是充分发挥模型的推理与工具调用能力, +而不是用严格的提示词和固化的编排方式来束缚它们。 + +## 为什么选择 AgentScope? + +- **简单**:通过内置的 ReAct 智能体、工具、技能、人机协作干预、记忆、计划、实时语音、评估和模型微调,5 分钟即可开始构建你的智能体 +- **可扩展**:丰富的生态系统集成,覆盖工具、记忆和可观测性;内置 MCP 和 A2A 支持;通过消息中心(MsgHub)实现灵活的多智能体编排和工作流 +- **生产就绪**:支持本地部署、云端 Serverless 部署或 K8s 集群部署,并内置 OTel 支持 agentscope -## News +## 新闻 -- **[2026-07] `INTE`:** K8s, OpenSandbox-based workspace/sandbox supported. [Docs](https://docs.agentscope.io/latest/en/building-blocks/workspace) -- **[2026-07] `INTE`:** ReMe long-term memory supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory/reme) | [Docs](https://docs.agentscope.io/latest/en/building-blocks/long-term-memory) -- **[2026-06] `FEAT`:** Agentic Memory supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory/agentic_memory) | [Docs](https://docs.agentscope.io/latest/en/building-blocks/long-term-memory) -- **[2026-06] `FEAT`:** Distributed & Multi-Tenancy & Multi-Session RAG service supported. [Docs](https://docs.agentscope.io/latest/en/deploy/agent-team) -- **[2026-06] `FEAT`:** RAG supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/rag) | [Docs](https://docs.agentscope.io/latest/en/building-blocks/rag) -- **[2026-06] `INTE`:** Mem0 supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory) | [Docs](https://docs.agentscope.io/latest/en) -- **[2026-06] `FEAT`:** Agent Team supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent_service) | [Docs](https://docs.agentscope.io/latest/en/deploy/agent-team) -- **[2026-05] `RELS`:** AgentScope 2.0 released! [Docs](https://docs.agentscope.io/) +- **[2026-07] `集成`:** 集成 K8s,OpenSandbox 工作区/沙箱实现。 [文档](https://docs.agentscope.io/latest/en/building-blocks/workspace) +- **[2026-07] `集成`:** 集成 ReMe 长期记忆。 [样例](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory/reme) | [文档](https://docs.agentscope.io/latest/zh/building-blocks/long-term-memory) +- **[2026-06] `功能`:** 支持 Agentic Memory。 [样例](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory/agentic_memory) | [文档](https://docs.agentscope.io/latest/zh/building-blocks/long-term-memory) +- **[2026-06] `功能`:** 支持分布式 & 多租户 & 多会话 RAG 服务。 [文档](https://docs.agentscope.io/latest/en/deploy/agent-team) +- **[2026-06] `功能`:** 支持多模态 RAG。 [样例](https://github.com/agentscope-ai/agentscope/tree/main/examples/rag) | [文档](https://docs.agentscope.io/latest/en/building-blocks/rag) +- **[2026-06] `集成`:** 集成 Mem0 长期记忆。 [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory) | [Docs](https://docs.agentscope.io/latest/zh) +- **[2026-06] `功能`:** 支持 Agent Team。[样例](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent_service) | [文档](https://docs.agentscope.io/latest/zh/deploy/agent-team) +- **[2026-05] `发布`:** AgentScope 2.0 已发布![文档](https://docs.agentscope.io/) -[More news →](./docs/NEWS.md) +[更多新闻 →](./docs/NEWS_zh.md) -## Community +## 社区 -Welcome to join our community on +欢迎加入我们的社区 -| [Discord](https://discord.gg/eYMpfnkG8h) | DingTalk | +| [Discord](https://discord.gg/eYMpfnkG8h) | 钉钉 | |----------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------| | | | -## Quickstart + + +## 📑 Table of Contents -### Installation +- [快速开始](#%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B) + - [安装](#%E5%AE%89%E8%A3%85) + - [从 PyPI 安装](#%E4%BB%8E-pypi-%E5%AE%89%E8%A3%85) + - [从源码安装](#%E4%BB%8E%E6%BA%90%E7%A0%81%E5%AE%89%E8%A3%85) +- [Hello AgentScope!](#hello-agentscope) +- [智能体服务](#%E6%99%BA%E8%83%BD%E4%BD%93%E6%9C%8D%E5%8A%A1) +- [贡献](#%E8%B4%A1%E7%8C%AE) +- [许可](#%E8%AE%B8%E5%8F%AF) +- [论文](#%E8%AE%BA%E6%96%87) +- [贡献者](#%E8%B4%A1%E7%8C%AE%E8%80%85) -> AgentScope requires **Python 3.11** or higher. + -#### From PyPI +## 快速开始 + +### 安装 + +> AgentScope 需要 **Python 3.11** 或更高版本。 + +#### 从 PyPI 安装 ```bash uv pip install agentscope -# or +# 或者 # pip install agentscope ``` -#### From source +#### 从源码安装 ```bash -# Pull the source code from GitHub +# 从 GitHub 拉取源码 git clone -b main https://github.com/agentscope-ai/agentscope.git -# Install the package in editable mode +# 以可编辑模式安装 cd agentscope uv pip install -e . -# or +# 或者 # pip install -e . ``` -## Hello AgentScope! +## Hello AgentScope! -Start your first agent with AgentScope 2.0: +使用 AgentScope 2.0,启动你的第一个智能体: ```python from agentscope.agent import Agent @@ -159,7 +188,7 @@ async def main() -> None: ) async for evt in agent.reply_stream(UserMsg("Tony", "Hi, Friday!")): - # Handle the event stream, e.g., print the message, update UI, etc. + # 处理事件流,例如打印消息、更新 UI 等 match evt.type: case EventType.REPLY_START: ... @@ -172,79 +201,79 @@ async def main() -> None: case EventType.TEXT_BLOCK_END: ... - # Handle other event types + # 处理其他事件类型 asyncio.run(main()) ``` -## Hello Agent Service! +## 智能体服务 -An extensible FastAPI based **multi-tenancy**, **multi-session** agent service with pre-built Web UI in `examples/web_ui` +一个基于 FastAPI 的可扩展**多租户**、**多会话**智能体服务,并在 `examples/web_ui` 中提供预构建的 Web UI
- Agent team + 智能体团队
- Agent team — a leader agent spawns workers and coordinates them through the built-in team tools. + 智能体团队 —— leader 智能体派生 worker,并通过内置的团队工具进行协调。
- Task planning + 任务规划
- Task planning — the agent breaks complex work into a tracked plan and updates it as it goes. + 任务规划 —— 智能体将复杂工作拆解为可追踪的计划,并在执行过程中持续更新。
- Permission control in bypass mode + bypass 模式下的权限控制
- Permission control in bypass mode — the agent runs end-to-end without pausing for tool-call confirmations. + bypass 模式下的权限控制 —— 智能体端到端运行,无需为工具调用确认而暂停。
- Background task offloading + 后台任务卸载
- Background task offloading — a long-running tool moves to the background; its result later wakes the agent up and the conversation resumes. + 工具后台执行 —— 长时间运行的工具被转入后台;其结果稍后唤醒智能体并恢复对话。
-Run the following commands to start the agent service backend and the web UI: +运行以下命令启动智能体服务后端和 Web UI: ```bash git clone -b main https://github.com/agentscope-ai/agentscope.git cd agentscope/examples/agent_service -# start the agent service backend +# 启动智能体服务后端 python main.py ``` -Then open another terminal to start the web UI: +然后打开另一个终端启动 Web UI: ```bash cd agentscope/examples/web_ui -# start the webui +# 启动 webui pnpm install pnpm dev ``` -## Contributing -We welcome contributions from the community! Please refer to our [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines -on how to contribute. +## 贡献 -## License +我们欢迎社区的贡献!请参阅我们的 [贡献指南](./CONTRIBUTING_zh.md) 了解如何贡献。 -AgentScope is released under Apache License 2.0. +## 许可 -## Publications +AgentScope 基于 Apache License 2.0 发布。 -If you find our work helpful for your research or application, please cite our papers. +## 论文 + +如果我们的工作对您的研究或应用有帮助,请引用我们的论文。 - [AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications](https://arxiv.org/abs/2508.16279) @@ -268,9 +297,9 @@ If you find our work helpful for your research or application, please cite our p } ``` -## Contributors +## 贡献者 -All thanks to our contributors: +感谢所有贡献者: