mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-06-02 03:55:55 +00:00
a327182cb2
* deps: add `langbot-plugin` * feat: connector for plugin runtime * feat(plugin): basic communication * feat: listing plugins * feat: switch tool entities and format * feat: switch Query to langbot-plugin definition * chore: delete Query class * feat: switch message platform adapters to sdk * chore: remove adapter meta manifest from components.yaml * feat: preliminary migration of events entities * fix: serialization bug in events emitting * feat: minor changes adapt to event emitting * feat: adapt more events * feat: switch all event emitting logic to new method * refactor: use `emit_event` from connector * feat: runtime reconnecting * feat: add Tool component * feat: switch command entities to sdk * feat: command execution via plugin * feat: `reply_message` api * feat: get bot uuid api * feat: query-based apis * refactor: switch llm_entities to plugin sdk * feat: backward call apis * perf: longer timeout for emit_event * feat: binary storage api * feat(ui): list plugins * feat: get plugin info * feat: kill runtime process when exit in stdio mode * perf: dispose process * chore: bump langbot-plugin version to 0.1.1a1 * fix: message chain init * feat: `get_bot_info` api * feat: set cloud_service_url * feat: refactor webui httpclient * fix: bot switching * feat: tag debugging plugins in webui * feat: plugin installation * feat: plugin installation webui * feat: trace plugin installation * feat: marketplace page * perf: frontend * fix: i18n fallback * feat: plugin operations * feat: plugin deletion and upgrade * feat: setting plugin config * feat: bump version of langbot-plugin * chore: remove plugin reorder functionality * chore: bump version 4.3.0b1 * chore: bump langbot_plugin version * fix: conflict in table `plugin_settings` * chore: bump version to '4.3.0b2' * chore: bump version 4.3.0b3 * Update package.json (#1627) * feat: change standalone runtime tag env * fix: use --standalone-runtime * feat: update docker launch method * fix: change tag of image to `latest` * perf: inline code display style in markdown * fix: syntax errors * fix: wrong migration target version * fix: set plugin enabled=true as default * fix: replace message_chain.has usage * fix: dark mode for plugins management page * fix: minor bugs * fix: tool call params in localagent * chore: bump version 4.3.0b4 * feat: available for disabling marketplace(offline env) * perf: display installed plugin icon * refactor: market plugin detail dialog * perf: dark theme * fix: cloudServiceClient api * feat: supports for command return image base64 * chore: bump langbot_plugin to 0.1.1b6 * del self.ap error * fix: dingtalk pydantic.BaseModel norm * fix: wechatpad pydantic.BaseModel norm * chore: move docker-compose.yaml for plugin edition --------- Co-authored-by: How-Sean Xin <mcjiekejiemi@163.com> Co-authored-by: fdc <2213070223@qq.com>
LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.
📦 Getting Started
Docker Compose Deployment
git clone https://github.com/langbot-app/LangBot
cd LangBot
docker compose up -d
Visit http://localhost:5300 to start using it.
Detailed documentation Docker Deployment.
One-click Deployment on BTPanel
LangBot has been listed on the BTPanel, if you have installed the BTPanel, you can use the document to use it.
Zeabur Cloud Deployment
Community contributed Zeabur template.
Railway Cloud Deployment
Other Deployment Methods
Directly use the released version to run, see the Manual Deployment documentation.
😎 Stay Ahead
Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
✨ Features
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with Dify.
- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic MCP protocol; Currently has hundreds of plugins.
- 😻 Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
For more detailed specifications, please refer to the documentation.
Or visit the demo environment: https://demo.langbot.dev/
- Login information: Email:
demo@langbot.appPassword:langbot123456 - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.
Message Platform
| Platform | Status | Remarks |
|---|---|---|
| Personal QQ | ✅ | |
| QQ Official API | ✅ | |
| WeCom | ✅ | |
| WeComCS | ✅ | |
| Personal WeChat | ✅ | |
| Lark | ✅ | |
| DingTalk | ✅ | |
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ |
LLMs
| LLM | Status | Remarks |
|---|---|---|
| OpenAI | ✅ | Available for any OpenAI interface format model |
| DeepSeek | ✅ | |
| Moonshot | ✅ | |
| Anthropic | ✅ | |
| xAI | ✅ | |
| Zhipu AI | ✅ | |
| CompShare | ✅ | LLM and GPU resource platform |
| Dify | ✅ | LLMOps platform |
| PPIO | ✅ | LLM and GPU resource platform |
| ShengSuanYun | ✅ | LLM and GPU resource platform |
| 302.AI | ✅ | LLM gateway(MaaS) |
| Google Gemini | ✅ | |
| Ollama | ✅ | Local LLM running platform |
| LMStudio | ✅ | Local LLM running platform |
| GiteeAI | ✅ | LLM interface gateway(MaaS) |
| SiliconFlow | ✅ | LLM gateway(MaaS) |
| Aliyun Bailian | ✅ | LLM gateway(MaaS), LLMOps platform |
| Volc Engine Ark | ✅ | LLM gateway(MaaS), LLMOps platform |
| ModelScope | ✅ | LLM gateway(MaaS) |
| MCP | ✅ | Support tool access through MCP protocol |
🤝 Community Contribution
Thank you for the following code contributors and other members in the community for their contributions to LangBot: