LibreChat:集成 Agents、MCP 与多模型支持的开源自托管 AI 对话平台
英文标题:🔥 LibreChat-AI/LibreChat
LibreChat 发布 v0.8.8-rc4,新增面向 Agents 的公开 API 文档、实验性附加工作区、Trace Viewer,以及可创建和导入的 Skills。该版本还强化了 MCP 可靠性,包括按请求传递请求头、跨副本协调 OAuth 刷新,以及在服务商故障期间保留凭据。LibreChat 将 OpenAI、Anthropic、AWS Bedrock、Google、Azure、Vertex AI 及各类兼容 API 整合进可自托管的多用户聊天界面,并提供 Agent、代码解释器、网页搜索和可恢复流等能力。对开发者和企业而言,该项目提供了更可控的 AI 基础设施、Agent 管理接口及面向生产部署的认证、可观测性和扩展能力。
81.3 KB
中文
🚀 v0.8.8-rc4 更新内容
- **公开 Agents API 文档:**提供 OpenAPI 规范和交互式 Swagger UI,覆盖推理、事件、Agent 管理及 Skill 管理。
- **附加工作区(高度实验性):**按对话隔离工作区、加载代码仓库指令,并采用有界队列等待和命令超时机制。
- **Trace Viewer:**以有序步骤查看模型对话,包括角色、Agent 身份、工具轮次、预览和成本。
- **Skills:**可编写或导入 Skill,并在同一 Agent 运行中调用;对于导入失败,提供更安全的回滚机制。
- **Agent 活动:**将系统事件渲染为独立轮次,并将实时活动保持在单个稳定行中。
- **MCP 可靠性:**可发送按请求指定的请求头而不隐藏工具,跨副本协调 OAuth 刷新,并在服务提供商故障期间保留凭据。
- **性能:**增量流式输出 Markdown、对模型搜索进行虚拟化,并减少已完成 Agent 消息的渲染工作量。
-
🖥️ UI 与体验:受 ChatGPT 启发,并提供更出色的设计与功能
-
🤖 AI 模型选择:
- Anthropic(Claude)、AWS Bedrock、OpenAI、Azure OpenAI、Google、Vertex AI、OpenAI Responses API(包括 Azure)
- 自定义端点:通过 LibreChat 使用任意 OpenAI 兼容 API,无需代理
- 兼容本地与远程 AI 提供商:
- Ollama、AMD Lemonade、groq、Cohere、Mistral AI、Apple MLX、koboldcpp、together.ai,
- OpenRouter、Helicone、Perplexity、ShuttleAI、Deepseek、Qwen 等更多服务
-
🔧 代码解释器 API:
- 支持 Python、Node.js(JS/TS)、Go、C/C++、Java、PHP、Rust 和 Fortran 的安全沙盒执行
- 无缝文件处理:可直接上传、处理和下载文件
- 无隐私顾虑:执行环境完全隔离且安全
- 开源且可自托管:由 ClickHouse/code-interpreter 驱动
-
🔦 Agents 与工具集成:
- LibreChat Agents:
- 无代码自定义助手:构建专业化、由 AI 驱动的助手
- Agent 市场:发现并部署社区构建的 Agent
- 协作共享:与指定用户和群组共享 Agent
- 灵活且可扩展:可使用 MCP Servers、工具、文件搜索、代码执行等能力
- Skills:创建可复用的
SKILL.md指令包,适用于手动、自动或始终开启的 Agent 工作流 - Agent Plugins:以实验性方式将部署 Skills 和 MCP servers 打包为启动时加载的软件包
- Subagents:将聚焦任务委派给拥有独立上下文窗口的隔离子 Agent 运行
- Agent 管理 API:通过与部署绑定的 OIDC 客户端,自动化管理 Agent、文件和 Skill
- 附加代码工作区:让 Agent 在托管或个人工作区中检查、搜索、编辑文件并运行命令(高度实验性)
- 兼容自定义端点、OpenAI、Azure、Anthropic、AWS Bedrock、Google、Vertex AI、Responses API 等更多服务
- 支持用于工具的 Model Context Protocol(MCP)
- LibreChat Agents:
-
🔍 网页搜索:
- 搜索互联网并检索相关信息,以增强 AI 上下文
- 结合搜索提供商、内容抓取器和结果重排序器,以获得最佳结果
- 可自定义 Jina 重排序:可为重排序服务配置自定义 Jina API URL
- 了解更多 →
-
🪄 基于代码 Artifacts 的生成式 UI:
- 代码 Artifacts 可直接在聊天中创建 React、HTML 和 Mermaid 内容
- 可全屏打开预览,并将 Mermaid 图导出为 SVG 或 PNG
-
🎨 图像生成与编辑
-
💾 预设与上下文管理:
- 创建、保存和共享自定义预设
- 可在聊天过程中切换 AI 端点和预设
- 通过对话分支编辑、重新提交和续写消息
- 创建提示词并与指定用户和群组共享
- 分叉消息与对话,实现高级上下文控制
- 按需压缩长对话,同时保留近期上下文
-
💬 多模态与文件交互:
- 使用 Claude 3、GPT-4.5、GPT-4o、o1、Llama-Vision 和 Gemini 上传并分析图像 📸
- 通过自定义端点、OpenAI、Azure、Anthropic、AWS Bedrock 和 Google 实现文件聊天 🗃️
- 可将消息复制为带格式的富文本,用于文档、电子邮件和协作应用
-
🌎 多语言 UI:
- English、中文(简体)、中文(繁體)、العربية、Deutsch、Español、Français、Italiano
- Polski、Português(PT)、Português(BR)、Русский、日本語、Svenska、한국어、Tiếng Việt
- Türkçe、Nederlands、עברית、Català、Čeština、Dansk、Eesti、فارسی
- Suomi、Magyar、Հայերեն、Bahasa Indonesia、ქართული、Latviešu、ไทย、ئۇيغۇرچە
-
🧠 推理 UI:
- 为 DeepSeek-R1 等思维链/推理 AI 模型提供动态推理 UI
-
🎨 可自定义界面:
- 可自定义的下拉菜单和界面,可同时适应高级用户与新手
- 支持浅色、深色、系统和高对比度外观模式
-
📈 可观测性:
- 通过 OpenTelemetry 导出追踪数据和日志,并连接 Langfuse 以获得 Agent 与模型洞察
-
🌊 可恢复流:
- 永不丢失回复:如果连接中断,AI 回复会自动重新连接并恢复
- 多标签页与多设备同步:可在多个标签页打开同一聊天,或在另一台设备上继续对话
- 生产就绪:从单服务器部署到使用 Redis 的水平扩展部署均可运行
-
🗣️ 语音与音频:
- 借助 Speech-to-Text 和 Text-to-Speech 实现免手操作聊天
- 自动发送和播放音频
- 支持 OpenAI、Azure OpenAI 和 Elevenlabs
-
📥 导入与导出对话:
- 从 LibreChat、ChatGPT、Chatbot UI 导入对话
- 将对话导出为截图、markdown、text、json
-
🔍 搜索与发现:
- 搜索所有消息和对话
-
👥 多用户与安全访问:
- 支持多用户,以及 OAuth2、LDAP 和电子邮件登录的安全认证
- 内置内容审核和 Token 消耗工具
-
🎛️ 管理面板:
- 基于浏览器的 UI,可管理用户、群组、角色和配置覆盖项
- 无需重新部署,即可实时编辑设置和按角色/群组划分的权限
- 随 Docker Compose 栈提供,支持一条命令完成设置
-
⚙️ 配置与部署:
- 可配置代理、反向代理、Docker 及多种部署选项
- 使用 搭配 CloudFront 的 S3,获得稳定的媒体链接、边缘分发、签名 Cookie 和安全下载
- 可完全在本地使用,也可部署到云端
-
📖 开源与社区:
- 完全开源,并以公开方式构建
- 由社区驱动的开发、支持和反馈
🪶 使用 LibreChat 一站式进行 AI 对话
LibreChat 是一个自托管 AI 聊天平台,可在单一、注重隐私的界面中统一接入所有主流 AI 提供商。
除聊天外,LibreChat 还提供 AI Agents、Model Context Protocol(MCP)支持、Artifacts、代码解释器、自定义操作、对话搜索,以及面向企业的多用户认证。
项目开源、持续积极开发,面向所有重视自身 AI 基础设施控制权的用户。
GitHub Repo:
其他:
请访问发布页面和发布说明,以获取最新更新:
⚠️ 更新前请查阅更新日志,了解破坏性变更。
欢迎贡献、建议、Bug 报告和修复!
如需新增功能、组件或扩展,请在提交 PR 前先创建 issue 进行讨论。
如果你愿意帮助将 LibreChat 翻译成你的语言,我们非常欢迎你的贡献!改进翻译不仅能让全球用户更容易使用 LibreChat,也能提升整体用户体验。请查看我们的翻译指南。
💖 项目能发展至今,感谢所有贡献者
感谢 Locize 提供支持 LibreChat 多语言功能的翻译管理工具
English / 原文
English · 中文
🚀 What's New in v0.8.8-rc4
- Public Agents API docs: Serve an OpenAPI specification and interactive Swagger UI for inference, events, Agent management, and Skill management.
- Attached workspaces (highly experimental): Isolate workspaces by conversation, load repository instructions, and use bounded queue waits and command timeouts.
- Trace Viewer: Inspect model conversations as ordered steps with roles, Agent identity, tool rounds, previews, and cost.
- Skills: Author or import a Skill and invoke it in the same Agent run, with safer rollback for failed imports.
- Agent activity: Render system events as distinct turns and hold live activity to one stable row.
- MCP reliability: Send per-request headers without hiding tools, coordinate OAuth refresh across replicas, and preserve credentials through provider outages.
- Performance: Stream Markdown incrementally, virtualize model search, and reduce completed Agent message rendering work.
Read the full v0.8.8-rc4 changelog.
-
🖥️ UI & Experience inspired by ChatGPT with enhanced design and features
-
🤖 AI Model Selection :
- Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure)
- Custom Endpoints: Use any OpenAI-compatible API with LibreChat, no proxy required
- Compatible with Local & Remote AI Providers:
- Ollama, AMD Lemonade, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
- OpenRouter, Helicone, Perplexity, ShuttleAI, Deepseek, Qwen, and more
-
- Secure, Sandboxed Execution in Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, and Fortran
- Seamless File Handling: Upload, process, and download files directly
- No Privacy Concerns: Fully isolated and secure execution
- Open-Source & Self-Hostable: powered by ClickHouse/code-interpreter
-
🔦 Agents & Tools Integration:
- LibreChat Agents :
- No-Code Custom Assistants: Build specialized, AI-driven helpers
- Agent Marketplace: Discover and deploy community-built agents
- Collaborative Sharing: Share agents with specific users and groups
- Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
- Skills: Create reusable
SKILL.mdinstruction bundles for manual, automatic, or always-on agent workflows - Agent Plugins: Experimentally bundle deployment Skills and MCP servers into startup-loaded packages
- Subagents: Delegate focused work to isolated child agent runs with their own context windows
- Agent Management API: Automate Agent, file, and Skill management with deployment-bound OIDC clients
- Attached Code Workspaces: Let Agents inspect, search, edit, and run commands in managed or personal workspaces (highly experimental)
- Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
- Model Context Protocol (MCP) Support for Tools
- LibreChat Agents :
-
🔍 Web Search :
- Search the internet and retrieve relevant information to enhance your AI context
- Combines search providers, content scrapers, and result rerankers for optimal results
- Customizable Jina Reranking : Configure custom Jina API URLs for reranking services
- Learn More →
-
🪄 Generative UI with Code Artifacts :
- Code Artifacts create React, HTML, and Mermaid content directly in chat
- Open previews fullscreen and export Mermaid diagrams as SVG or PNG
-
🎨 Image Generation & Editing
-
💾 Presets & Context Management:
- Create, Save, & Share Custom Presets
- Switch between AI Endpoints and Presets mid-chat
- Edit, Resubmit, and Continue Messages with Conversation branching
- Create and share prompts with specific users and groups
- Fork Messages & Conversations for Advanced Context control
- Compact long conversations on demand while preserving recent context
-
💬 Multimodal & File Interactions:
- Upload and analyze images with Claude 3, GPT-4.5, GPT-4o, o1, Llama-Vision, and Gemini 📸
- Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, & Google 🗃️
- Copy messages as formatted rich text for documents, email, and collaboration apps
-
🌎 Multilingual UI :
- English, 中文 (简体), 中文 (繁體), العربية, Deutsch, Español, Français, Italiano
- Polski, Português (PT), Português (BR), Русский, 日本語, Svenska, 한국어, Tiếng Việt
- Türkçe, Nederlands, עברית, Català, Čeština, Dansk, Eesti, فارسی
- Suomi, Magyar, Հայերեն, Bahasa Indonesia, ქართული, Latviešu, ไทย, ئۇيغۇرچە
-
🧠 Reasoning UI :
- Dynamic Reasoning UI for Chain-of-Thought/Reasoning AI models like DeepSeek-R1
-
🎨 Customizable Interface :
- Customizable Dropdown & Interface that adapts to both power users and newcomers
- Light, dark, system, and high-contrast appearance modes
-
📈 Observability :
- Export traces and logs with OpenTelemetry and connect Langfuse for Agent and model insights
-
- Never lose a response: AI responses automatically reconnect and resume if your connection drops
- Multi-Tab & Multi-Device Sync: Open the same chat in multiple tabs or pick up on another device
- Production-Ready: Works from single-server setups to horizontally scaled deployments with Redis
-
🗣️ Speech & Audio:
- Chat hands-free with Speech-to-Text and Text-to-Speech
- Automatically send and play Audio
- Supports OpenAI, Azure OpenAI, and Elevenlabs
-
📥 Import & Export Conversations:
- Import Conversations from LibreChat, ChatGPT, Chatbot UI
- Export conversations as screenshots, markdown, text, json
-
🔍 Search & Discovery:
- Search all messages/conversations
-
👥 Multi-User & Secure Access:
- Multi-User, Secure Authentication with OAuth2, LDAP, & Email Login Support
- Built-in Moderation, and Token spend tools
-
🎛️ Admin Panel :
- Browser-based UI to manage users, groups, roles, and configuration overrides
- Edit settings and per-role/group permissions live, without redeploying
- Bundled with the Docker Compose stacks for one-command setup
-
⚙️ Configuration & Deployment:
- Configure Proxy, Reverse Proxy, Docker, & many Deployment options
- Use S3 with CloudFront for stable media links, edge delivery, signed cookies, and secured downloads
- Use completely local or deploy on the cloud
-
📖 Open-Source & Community:
- Completely Open-Source & Built in Public
- Community-driven development, support, and feedback
For a thorough review of our features, see our docs here 📚
🪶 All-In-One AI Conversations with LibreChat
LibreChat is a self-hosted AI chat platform that unifies all major AI providers in a single, privacy-focused interface.
Beyond chat, LibreChat provides AI Agents, Model Context Protocol (MCP) support, Artifacts, Code Interpreter, custom actions, conversation search, and enterprise-ready multi-user authentication.
Open source, actively developed, and built for anyone who values control over their AI infrastructure.
GitHub Repo:
Other:
Keep up with the latest updates by visiting the releases page and notes:
⚠️ Please consult the changelog for breaking changes before updating.
Contributions, suggestions, bug reports and fixes are welcome!
For new features, components, or extensions, please open an issue and discuss before sending a PR.
If you'd like to help translate LibreChat into your language, we'd love your contribution! Improving our translations not only makes LibreChat more accessible to users around the world but also enhances the overall user experience. Please check out our Translation Guide.
💖 This project exists in its current state thanks to all the people who contribute
We thank Locize for their translation management tools that support multiple languages in LibreChat.