uvx 方式需先安装 uv；插件需单独安装，不随 Core 发布打包；Docker 部署需进入 docker 目录并用 --profile all 启动
LangBot
langbot-appApache-2.0活跃维护生产级多平台智能机器人开发平台，把 Agent、知识库和插件系统统一编排，一套代码接入 Discord、Slack、微信、飞书、钉钉等主流 IM，并对接 GPT、DeepSeek、Dify、Coze 等模型与工作流。
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow
v4.11.4发布于 2026-10-29 13:44 UTC18,862star +71 / 7 天1,697fork同步于 2026-11-10 05:23 UTC
uvx langbot
# 访问 http://localhost:5300 硬件要求按 README 说明
README 未说明显存或 GPU 要求，可接 Ollama、LM Studio 等本地模型，也可用云端 API
有 Docker 镜像
开源生产级多平台 IM 智能机器人平台，把 LLM 接入各类聊天软件
生产级多平台智能机器人开发平台，把 Agent、知识库和插件系统统一编排，一套代码接入 Discord、Slack、微信、飞书、钉钉等主流 IM，并对接 GPT、DeepSeek、Dify、Coze 等模型与工作流。
核心能力
- 多平台统一接入 Discord、Telegram、Slack、微信、飞书等
- 内置 RAG 知识库并集成 Dify、Coze、n8n、Langflow
- 插件生态支持 MCP 协议与事件驱动扩展
- Web 管理面板配置监控，无需手写 YAML
- 多流水线架构支持不同场景机器人并带访问控制与限流
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
- v4.11.4LangBot v4.11.4最新正式版2026-10-29 · 2026-10-29 13:44 UTC
LangBot 是一个开源的 AI 聊天机器人与智能体平台，支持多种即时通讯平台、大语言模型、知识库和插件，帮助你构建、部署和管理 AI 助手。 LangBot is an open-source AI chatbot and agent platform that connects messaging platforms, large language models, knowledge bases, and plugins to help you build, deploy, and manage AI assistants.
Patch release that folds in 4.11.3 and the fixes made since.
主要更新 / Highlights
- 插件 / Plugins：官方插件（LocalAgent、LangRAG、DifyAgent 等）迁入主仓并独立发版，可单独升级，不再跟随 Core 发布；调试插件包可直接上传到 LangBot Space，支持可选 GitHub 关联。
- 图片资源 / Media：会话、监控与执行详情共享同一份资源 URL 目录，OneBot 过期的图片链接会在历史记录与模型请求中自动刷新。
- 存储 / Storage：SQLite 改用增量方式回收空间，Docker 镜像随附修补后的 SQLite（Debian trixie）。
- SDK：
langbot-plugin由 0.7.16 固定到 0.7.19。
修复 / Fixed
- 数据库：修复资源 URL 迁移的规范化与作用域 SQL 失败，并让
alembic_runner downgrade回滚可用；移除不再使用的索引。 - 插件运行时：持久化 v4 运行时状态、容忍 Runner 注册缺口；本地挂载插件补齐 setting 能力；托管 Runtime 尊重
display_plugin_debug_url端口。 - Agent：取消执行时保留终态事件，执行不再卡在“进行中”。
- 平台适配：QQ 官方机器人修正群内 @ 与回复序列、接收全量群消息；企业微信回调解耦并用 Push API 主动推送、流式分片按窗口节流；Line 与 HTTP Bot 会话上下文修复。
- 事件：毫秒时间戳在转换前归一化。
- MCP：不支持的 mode 在落库前拒绝。
- 依赖：python-multipart 下限提到锁定版本。
发布验证 / Release verification
以真实的 4.11.2 数据库（PostgreSQL 与 SQLite）升级到本版本：迁移到 head 无报错，升级后 schema 与全新安装逐列一致，历史图片消息仍按原始 URL 读回；LocalAgent、LangRAG、DifyAgent 三个插件完成端到端对话验证。 Upgraded real 4.11.2 databases (PostgreSQL and SQLite) to this release: migrations reach head without errors, the upgraded schema matches a fresh install column by column, historical image payloads still read back as their original URLs, and LocalAgent, LangRAG and DifyAgent completed end-to-end conversations.
- v4.11.3LangBot v4.11.3pre-release2026-10-23 · 2026-10-23 06:15 UTC
查看更新说明
Patch release for the Cloud notice banner.
- A custom Cloud banner copy no longer drops the dedicated-environment link, so the new Cloud environment can point readers at the stable dedicated offering.
- Plan copy uses 计划 consistently.
- Dependency vulnerability patches for Python and web.
- v4.11.2LangBot v4.11.22026-10-22 · 2026-10-22 15:45 UTC
查看更新说明
LangBot 是一个开源的 AI 聊天机器人与智能体平台，支持多种即时通讯平台、大语言模型、知识库和插件，帮助你构建、部署和管理 AI 助手。 LangBot is an open-source AI chatbot and agent platform that connects messaging platforms, large language models, knowledge bases, and plugins to help you build, deploy, and manage AI assistants.
Patch release for dedicated (自建独立环境) deployments.
- #2755 修复独立环境 Space OAuth 登录 404（provider 行缺失导致回调 500/404 中断），以及「添加第一个模型」500
- #2757 插件安装拒绝 SDK 无法安全解压的压缩包条目名
In-place verified on a dedicated-space Core (edition=cloud, OSS runtime) at 4.11.1 + these patches: login on a fresh database returns a token, plugin install from archive works, and an agent pipeline executes in the nsjail sandbox.
- v4.11.1LangBot v4.11.12026-10-20 · 2026-10-20 15:54 UTC
查看更新说明
LangBot 是一个开源的 AI 聊天机器人与智能体平台，支持多种即时通讯平台、大语言模型、知识库和插件，帮助你构建、部署和管理 AI 助手。 LangBot is an open-source AI chatbot and agent platform that connects messaging platforms, large language models, knowledge bases, and plugins to help you build, deploy, and manage AI assistants.
LangBot v4.11.1
本次更新改进监控性能、消息处理和插件兼容性。 This maintenance release improves monitoring performance, message handling, and plugin compatibility.
Highlights / 主要更新
- 监控与存储 / Monitoring and storage：优化会话查询，修复任务终态处理，改进历史图片存储和迁移兼容性。Optimize session queries, fix terminal execution states, and improve historical image storage and migration compatibility.
- 消息与插件 / Messages and plugins：修复消息过滤、插件安装诊断、显式附件发送及部分平台消息处理。Fix message filtering, plugin installation diagnostics, explicit attachment delivery, and platform-specific message handling.
- SDK：精确固定
langbot-plugin==0.7.16，避免对无事件监听器的插件执行不必要的事件 RPC。Pinlangbot-plugin==0.7.16and avoid unnecessary event RPC calls for plugins without event listeners.
Release verification / 发布验证
PyPI 包、双架构 Docker 镜像、源码 ZIP 和 fnOS FPK 已发布并读回验证；全新安装与隔离 Linux 启动检查通过。 PyPI packages, dual-architecture Docker images, the source ZIP, and fnOS FPK were published and verified. Clean installation and isolated Linux startup checks passed.
Contributors / 贡献者
感谢本版本的所有贡献者（含共同作者）！ Thanks to everyone who contributed to this release, including co-authors!
@BiFangKNT, @carfeii, @dadachann, @fluo-rite, @HaiYangBG1, @haoxuanjng-lang, @huanghuoguoguo, @Jonathan-Improving, @Li-john1021, @MuonChaser, @Nikarhub, @qingshungLI, @RockChinQ, @ShaoLOWu
自动化与 AI 协作 / Automation and AI assistance: @claude, @multica-agent.
New Contributors / 首次贡献者
- @MuonChaser 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2714
- @ShaoLOWu 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2654
- @carfeii 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2628
- @Jonathan-Improving 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2620
- @Li-john1021 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2658
- @haoxuanjng-lang 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2626
- @fluo-rite 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2656
- @qingshungLI 首次贡献 / made their first contribution: https://github.com/langbot-app/LangBot/pull/2631
Full Changelog: https://github.com/langbot-app/LangBot/compare/v4.11.0...v4.11.1
- v4.11.0LangBot v4.11.02026-10-14 · 2026-10-14 07:57 UTC
查看更新说明
LangBot 是一个开源的 AI 聊天机器人与智能体平台，支持多种即时通讯平台、大语言模型、知识库和插件，帮助你构建、部署和管理 AI 助手。 LangBot is an open-source AI chatbot and agent platform that connects messaging platforms, large language models, knowledge bases, and plugins to help you build, deploy, and manage AI assistants.
🚀 Key Features / 关键更新
LangBot 4.11 带来了一次较大的架构升级：机器人可以响应平台事件，Agent 运行器改为插件化，WebUI 新增工作区助手。 LangBot 4.11 brings a major architectural update: bots can react to platform events, Agent runners are now plugins, and the WebUI adds a Workspace Assistant.
⚡ 事件驱动智能体 / Event-Based Agents (EBA) - Authored by @RockChinQ @huanghuoguoguo @wangcham @dadachann
除消息外，入群、退群、撤回、表情回应、卡片点击等平台事件现在也可以触发处理。13 个平台适配器已基于 EBA 架构重写，可在「事件路由」中将事件分发给 Pipeline、Agent 或插件处理器。 Beyond messages, platform events such as joins, leaves, recalls, reactions and card clicks can now trigger processing. 13 adapters have been rebuilt on EBA, and Event Routing dispatches each event to a Pipeline, an Agent or a plugin processor.
- 场景化路由 / Scenario routes：按欢迎新成员、处理成员离开等常用场景创建路由 / Create routes from common scenarios such as welcoming new members
- 三类处理器 / Three processor types：Pipeline、Agent、插件事件处理器可组合使用 / Pipelines, Agents and plugin Event Processors can be combined
- 事件调试器 / Event debugger：表单编辑事件数据，查看运行日志与执行详情 / Edit event payloads in a form and inspect run logs and details
- 平台增强 / Platform upgrades：Slack Socket Mode、钉钉卡片交互、微信“正在输入”、OneBot WebSocket 等 / Slack Socket Mode, DingTalk card interactions, WeChat typing indicator, OneBot WebSocket and more
🧩 AgentRunner 插件化 / Pluginized AgentRunner - Authored by @huanghuoguoguo @RockChinQ @fdc310
LocalAgent、Dify、Coze、n8n 等内置运行器已迁出主程序，改为扩展市场中的官方插件，并新增 Codex、Claude Code、ACP 等运行器。运行器可独立更新、按需安装，开发者也可基于 AgentRunner Protocol v1 编写自己的运行器。 Built-in runners such as LocalAgent, Dify, Coze and n8n have moved out of the core into official Marketplace plugins, alongside new runners such as Codex, Claude Code and ACP. Runners are updated independently and installed on demand, and developers can write their own on AgentRunner Protocol v1.
- 一键迁移 / One-click migration：自动安装所需插件，原配置自动备份 / Auto-installs required plugins and backs up your configuration
- 权限可控 / Scoped authorization：运行器只能调用当前上下文授权的工具与平台 API / Runners only reach tools and platform APIs authorized for the current context
- 插件认证 / Plugin certification：扩展市场展示认证徽章，主程序校验插件签名 / Certification badges in the Marketplace and signature verification in the core
🤖 工作区助手 / Workspace Assistant - Authored by @huanghuoguoguo @RockChinQ @dadachann
WebUI 新增工作区助手，可通过对话查询资源、创建并配置流水线与知识库，所有写操作需确认后才执行。 The WebUI adds a Workspace Assistant that inspects resources and sets up Pipelines and knowledge bases through chat; every write runs only after confirmation.
🔐 更多亮点 / More Highlights
- Passkey 与两步验证 / Passkeys & 2FA：WebAuthn 登录（@BiFangKNT）与 TOTP 两步验证（@TyperBody）/ WebAuthn sign-in and TOTP two-factor auth
- 操作日志 / Operation trace：记录每次操作改了什么，支持完整性校验（@TyperBody）/ See what every operation changed, with integrity checks
- 监控升级 / Monitoring：统一执行视图、工具调用追踪、实时处理中面板（@dadachann）/ Unified execution views, tool-call tracing and a live in-flight dock
- 媒体缓存 / Media cache：媒体按内容去重存储，减少
langbot.db膨胀（@BiFangKNT）/ Content-addressed media storage reduceslangbot.dbgrowth - 扩展市场 / Marketplace：已安装/可更新状态与实时安装进度（@TyperBody）/ Installed & update states and live install progress
- CLI 与诊断 / CLI & diagnostics：用
lbctl和 API Key 管理与诊断实例（@huanghuoguoguo）/ Manage and diagnose instances withlbctlan
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
English / 简体中文 / 繁體中文 / 日本語 / Español / Français / 한국어 / Русский / Tiếng Việt
Website ｜ Features ｜ Docs ｜ API ｜ Cloud ｜ Plugin Market ｜ Roadmap
What is LangBot?
LangBot is an open-source, production-grade platform for building AI-powered instant messaging bots. It connects Large Language Models (LLMs) to any chat platform, enabling you to create intelligent agents that can converse, execute tasks, and integrate with your existing workflows.
Key Capabilities
- AI Conversations & Agents — Multi-turn dialogues, tool calling, multi-modal support, streaming output. Built-in RAG (knowledge base) with deep integration to Dify, Coze, n8n, Langflow, Deerflow, Weknora.
- Universal IM Platform Support — One codebase for Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
- Production-Ready — Access control, rate limiting, sensitive word filtering, comprehensive monitoring, and exception handling. Trusted by enterprises.
- Plugin Ecosystem — Hundreds of plugins, event-driven architecture, component extensions, and MCP protocol support.
- Web Management Panel — Configure, manage, and monitor your bots through an intuitive browser interface. No YAML editing required.
- Multi-Pipeline Architecture — Different bots for different scenarios, with comprehensive monitoring and exception handling.
→ Learn more about all features
📍 Practical guides: deploy a multi-platform AI bot in 5 minutes, connect DeepSeek to WeChat, Discord, and Telegram, run a Dify Agent in Discord, Telegram, and Slack, and build an n8n-powered chatbot.
😎 Stay Updated
Click the Star and Watch buttons in the top-right corner of the repository to get the latest updates.
Quick Start
Official plugin source index: plugins/README.md · machine-readable catalog · independent plugin releases. Plugins are installed separately and are not bundled in Core releases.
☁️ LangBot Cloud (Recommended)
Zero deployment, ready to use.
One-Line Launch
uvx langbot
Requires uv. Visit http://localhost:5300 — done.
Docker Compose
git clone https://github.com/langbot-app/LangBot
cd LangBot/docker
docker compose --profile all up -d
One-Click Cloud Deploy
More options: Docker · Manual · BTPanel · Kubernetes
Supported Platforms
| Platform | Status | Notes |
|---|---|---|
| Discord | ✅ | Official |
| Telegram | ✅ | Official |
| Slack | ✅ | Official |
| LINE | ✅ | Official |
| ✅ | Personal & Official API (Channel, DM, Group) | |
| WeCom | ✅ | Enterprise WeChat, External CS, AI Bot |
| ✅ | Personal & Official Account | |
| Lark | ✅ | Official |
| DingTalk | ✅ | Official |
| KOOK | ✅ | Official |
| Satori | ✅ | |
| ✅ | Matrix, Satori | |
| Matrix | ✅ | Supports multiple bridged platforms such as Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip, and more |
Supported LLMs & Integrations
| Provider | Type | Status |
|---|---|---|
| OpenAI | LLM | ✅ |
| Anthropic | LLM | ✅ |
| DeepSeek | LLM | ✅ |
| Google Gemini | LLM | ✅ |
| xAI | LLM | ✅ |
| Moonshot | LLM | ✅ |
| Zhipu AI | LLM | ✅ |
| Ollama | Local LLM | ✅ |
| LM Studio | Local LLM | ✅ |
| Dify | LLMOps | ✅ |
| MCP | Protocol | ✅ |
| SiliconFlow | Gateway | ✅ |
| Aliyun Bailian | Gateway | ✅ |
| Volc Engine Ark | Gateway | ✅ |
| ModelScope | Gateway | ✅ |
| GiteeAI | Gateway | ✅ |
| CompShare | GPU Platform | ✅ |
| PPIO | GPU Platform | ✅ |
| ShengSuanYun | GPU Platform | ✅ |
| 接口 AI | Gateway | ✅ |
| 302.AI | Gateway | ✅ |
| Qiniu | Gateway | ✅ |
Why LangBot?
| Use Case | How LangBot Helps |
|---|---|
| Customer Support | Deploy AI agents to Slack/Discord/Telegram that answer questions using your knowledge base |
| Internal Tools | Connect n8n/Dify workflows to WeCom/DingTalk for automated business processes |
| Community Management | Moderate QQ/Discord groups with AI-powered content filtering and interaction |
| Multi-Platform Presence | One bot, all platforms. Manage from a single dashboard |
Built for AI Agents 🤖
LangBot is agent-friendly by design — your coding agents (Claude Code, Codex, Copilot, Cursor, …) can operate, extend, and deploy LangBot with first-class support:
- MCP Server — LangBot exposes a built-in Model Context Protocol endpoint at
/mcp, mirroring the HTTP API so an agent can manage bots, pipelines, plugins, and models programmatically. Authenticate with the same API key (set a global key inconfig.yamlor use a per-user key) — no login flow required. Configure it in the Web panel's API & MCP tab. - CLI (
lbctl) — The standalone LangBot CLI lets agents manage a running LangBot Workspace from a terminal through the Service API. It uses an API key and supports bots, pipelines, knowledge bases, models, plugins, skills, and MCP servers. See the CLI repository for installation and commands. - In-repo Skills — The
skills/directory is the single source of truth for working with LangBot: plugin development, core development, end-to-end testing, deployment, and operating the LangBot / LangBot Space MCP servers. Point your agent at this directory and it knows how to build. - AGENTS.md — Every repo ships an
AGENTS.md(symlinked toCLAUDE.md) describing architecture, conventions, and the rule that API changes must keep the MCP server and skills in sync. llms.txt— Machine-readable project context for LLMs is published on the website.
Cloud / Marketplace: LangBot Space also exposes an MCP server so agents can search and inspect the plugin / MCP / skill marketplace, authenticated with a Personal Access Token.
Community
Contributors
Thanks to all contributors who have helped make LangBot better:
langchain
langchain-ai·Python
用 Python 搭建 LLM 应用和智能体的开发框架，把模型调用、工具、检索和记忆串成可组合的链路，省去自己拼装底层胶水代码。
智能体开发+4RAG 框架
149288+14625klangchain-typesafe==0.0.22026-11-10 04:12 UTC
awesome-llm-apps
Shubhamsaboo·Python
收录 100 多个可直接上手的 AI Agent、Agent Skills 和 RAG 应用示例，帮开发者快速找到能跑起来的 LLM 项目参考。
AI Agent+4RAG 框架
144320+25321k2026-11-10 01:54 UTC
hello-agents
datawhalechina·Python
从零开始手把手教你构建 LLM 智能体的中文教程，覆盖 Agent 原理、RAG 等核心实践，适合入门与动手复现。
智能体教程+4RAG 框架
86546+23711kV1.0.32026-10-13 22:28 UTC
serviette
pathwaycom·Python
一个免代码的 RAG 服务器，能随文档更新自动同步答案，支持 8 种向量数据库，基于 Pathway 构建。
RAG+4RAG 框架
587211.5kv0.1.82026-11-02 15:57 UTC