LibreChat：集成 Agents、MCP 与多模型支持的自托管 AI 对话平台

🚀 v0.8.8-rc3 新增内容

• **Agent Management API（beta）：**创建、发现、更新和删除 Agents；管理 Agent 文件与 Skills；并通过与部署绑定的 OIDC 身份验证机器客户端，同时保留既有角色和 Agent 访问控制。
• **附加工作区（高度实验性）：**为每个受管理或个人代码工作者选择或保存按 Agent 设置的默认工作区，让 Agents 检查目录树、读取和搜索文件、编写修改，并在受限超时内运行 Bash。个人工作者支持受限的自助注册、就绪状态和按 Agent 设置的 Git 身份。
• **后台工具控制：**可选择取消常规后台工具（包括附加 Bash），同时保持分离式 Subagent 执行的独立性。
• **代码审批控制：**在管理员允许的范围内，为文件写入和命令执行选择 询问、允许 或 拒绝，其中包括面向受信任附加环境的 完全访问 模式。文件搜索和运行代码同样遵循角色授权。
• **手动上下文压缩：**在上下文窗口填满之前启动一个仅总结的轮次，并根据部署的总结策略保留近期对话内容。
• **上下文使用情况：**查看对话、保留的工具流量、Agent 指令、缓存、成本和上下文余量压力，且不会对类别子集进行重复计算。
• **统一附件：**一次上传后，由 LibreChat 将内容路由至模型或提取出的文本；仅在需要时配置文件搜索和代码工具。
• **模型：**为 OpenAI 和 Agents 端点新增 GPT-6 Astra，支持 Responses API 路由和工具调用。
• **Agent 与聊天 UI：**统一工具活动、推理、搜索和 Agent 工作流；新增一个可拖动的置顶区域，用于聊天和收藏；加入形态变化状态图标、高对比度主题、富文本消息复制、更清晰的侧栏标题以及优化的实时阶段布局。
• **可观测性：**通过 OpenTelemetry 导出具有关联关系的应用日志；配置白名单式 Langfuse 追踪身份和元数据；使用客户端构建 ID 标记浏览器诊断信息；并将 Insights 限定为授权 Agents 可用。
• **可靠性与安全性：**强化 Agent 延续和检查点恢复、Redis 存活检测、DocumentDB 协调、OpenID 和 MCP OAuth 会话、共享链接限流、租户隔离、附件边界以及上传错误处理。

阅读完整的 v0.8.8-rc3 更新日志。

• 🖥️ UI 与体验：受 ChatGPT 启发，并提供增强的设计与功能

• 🤖 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 使用任何兼容 OpenAI 的 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

• 🔧 Code Interpreter API：

  • 在 Python、Node.js（JS/TS）、Go、C/C++、Java、PHP、Rust 和 Fortran 中提供安全的沙盒执行
  • 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 驱动的辅助工具
    • Agent 市场：发现和部署社区构建的 Agents
    • 协作式共享：与指定用户和群组共享 Agents
    • 灵活且可扩展：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，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：将聚焦任务委派给具有独立上下文窗口的隔离子 Agent 运行实例
    • Agent Management 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 Agents 在受管理或个人工作区中检查、搜索、编辑文件和运行命令（高度实验性）
    • 兼容自定义端点、OpenAI、Azure、Anthropic、AWS Bedrock、Google、Vertex AI、Responses API 等
    • 提供用于工具的 Model Context Protocol（MCP）支持

• 🔍 网络搜索：

  • 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：为重排序服务配置自定义 Jina API URL
  • 了解更多 →

• 🪄 通过 Code Artifacts 实现生成式 UI：

  • Code 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 图表导出为 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
  • 在聊天过程中切换 AI 端点和预设
  • 通过对话分支编辑、重新提交和继续消息
  • 创建提示词并与特定用户和群组共享
  • 通过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 📸
  • 使用自定义端点、OpenAI、Azure、Anthropic、AWS Bedrock 和 Google 与文件聊天 🗃️
  • 将消息复制为格式化富文本，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 等支持思维链/推理的 AI 模型提供动态推理 UI

• 🎨 可定制界面：

  • 可定制下拉菜单与界面，能够同时适应高级用户和新用户
  • 提供浅色、深色、跟随系统和高对比度外观模式

• 📈 可观测性：

  • 使用 OpenTelemetry 导出追踪和日志，并连接 Langfuse 以获取 Agent 与模型洞察

• 🌊 可恢复流式传输：

  • 永不丢失响应：如果连接中断，AI 响应会自动重新连接并恢复
  • 多标签页与多设备同步：可在多个标签页中打开同一聊天，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：

  • 通过语音转文字和文字转语音实现免手操作聊天
  • 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、文本、json

• 🔍 搜索与发现：

  • 搜索所有消息/对话

• 👥 多用户与安全访问：

  • 支持 OAuth2、LDAP 和电子邮件登录的多用户安全认证
  • 内置内容审核和 Token 消耗工具

• 🎛️ 管理面板：

  • 基于浏览器的 UI，用于管理用户、群组、角色和配置覆盖项
  • 无需重新部署，即可实时编辑设置以及按角色/群组划分的权限
  • 随 Docker Compose 部署栈提供，支持一条命令完成设置

• ⚙️ 配置与部署：

  • 配置代理、反向代理、Docker 和多种部署选项
  • 使用 S3 with CloudFront 实现稳定媒体链接、边缘分发、签名 Cookie 和安全下载
  • 可完全在本地使用，也可部署至云端

• 📖 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、支持与反馈

如需全面了解功能，请查看我们的文档 📚

🪶 使用 LibreChat 进行一体化 AI 对话

LibreChat 是一个自托管 AI 聊天平台，在单一、注重隐私的界面中整合所有主要 AI 提供商。

除聊天外，LibreChat 还提供 AI Agents、Model Context Protocol（MCP）支持、Artifacts、Code Interpreter、自定义操作、对话搜索和企业级多用户认证。

它开源、持续积极开发，面向所有重视 AI 基础设施控制权的用户。

GitHub Repo：

其他：

请访问发布页面和说明，了解最新更新：

⚠️ 更新前请查阅更新日志，以了解破坏性变更。

[ ![danny-avila%2FLibreChat | Trendshift](https://camo.githubusercontent.com/762c3f9dc43091fe5976077ebb3ff6d65bc26e9f02249ca808f5e71ae13ce48a/68747470733a2f2f7472656e6473686966742e696f2f6170692f62616467652f

English · 中文

🚀 What's New in v0.8.8-rc3

• Agent Management API (beta): Create, discover, update, and delete Agents; manage Agent files and Skills; and authenticate machine clients through deployment-bound OIDC identities while preserving existing role and Agent access controls.
• Attached workspaces (highly experimental): Select or save a per-Agent default workspace for each managed or personal code worker, then let Agents inspect trees, read and search files, author changes, and run Bash with bounded timeouts. Personal workers support bounded self-service enrollment, readiness status, and per-Agent Git identity.
• Background tool controls: Optionally cancel ordinary background tools, including attached Bash, while keeping detached Subagent execution independent.
• Code approval controls: Choose Ask , Allow , or Deny for file writes and command execution where administrators permit it, including a Full access mode for trusted attached environments. File Search and Run Code also honor role grants.
• Manual context compaction: Start a summarize-only turn before the context window fills while preserving recent conversation content according to the deployment's summarization policy.
• Context Usage: Inspect dialogue, retained tool traffic, Agent instructions, cache, cost, and runway pressure without double-counting category subsets.
• Unified attachments: Upload once and let LibreChat route content to the model or extracted text, then provision File Search and Code tools only when needed.
• Models: Added GPT-6 Astra for the OpenAI and Agents endpoints, with Responses API routing and tool-call support.
• Agent and chat UI: Unified tool activity, reasoning, search, and Agent workflows; added one draggable Pinned section for chats and favorites, morphing state icons, high-contrast themes, rich-text message copying, clearer sidebar titles, and refined live phase layouts.
• Observability: Export correlated application logs through OpenTelemetry, configure allowlisted Langfuse trace identity and metadata, tag browser diagnostics with client build IDs, and scope Insights to authorized Agents.
• Reliability and security: Strengthened Agent continuation and checkpoint recovery, Redis liveness detection, DocumentDB coordination, OpenID and MCP OAuth sessions, shared-link throttling, tenant isolation, attachment bounds, and upload error handling.

Read the full v0.8.8-rc3 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

• 🔧 Code Interpreter API :

  • 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.md instruction 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

• 🔍 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

• 🌊 Resumable Streams :

  • 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.