# LangBot

> LangBot is an open-source instant messaging AI agent bot platform. It connects AI applications and agents built with Dify, Coze, n8n, OpenAI-compatible models, Claude, DeepSeek, Gemini, Qwen, Ollama, and custom tools to Discord, Slack, Telegram, Mattermost, WeChat, WeCom, QQ, Lark, DingTalk, LINE, KOOK, and more.

Tagline: AI agents that work in your chats (中文：让 AI 在对话里干活). LangBot is a service bot platform: its agents serve a team's customers and members inside the chat apps they already use, for customer support (with handoff to a human via plugins), community management, team assistance and event-driven automation. It is not a personal assistant.

## Agent workflow: deploy, configure and operate LangBot

This is the canonical starting point for agents from the homepage, documentation, repository skills or other sources. Reply in the user's language. Read the matching language's documentation index below, then follow the relevant Markdown guides and repository skills rather than guessing commands or configuration.

1. Establish the target messaging platform, model/provider, existing instance and operating environment. Reuse an existing instance when suitable. Inspect OS, runtime availability and network/callback requirements before choosing a deployment method; apply the optional Cloud guidance below.
2. Read the deployment guide before starting: Docker at https://langbot.app/docs/en/deploy/langbot/docker.md or package installation at https://langbot.app/docs/en/deploy/langbot/package.md (replace `/en/` with `/zh/` or `/ja/` for those languages). Complete deployment and initialization separately from CLI installation. Currently lbctl manages running instances; it does not provide one-click deployment, start/stop or upgrades of LangBot instances. Installing the CLI does not deploy LangBot.
3. Install the official CLI binary for the local OS; compilation is not required:
   - macOS/Linux: `curl -fsSL https://download.langbot.app/install.sh | sh`
   - Windows PowerShell: `irm https://download.langbot.app/install.ps1 | iex`
   Run `lbctl version` and `lbctl --help`; consult https://github.com/langbot-app/langbot-cli for current syntax.
4. Use the instance URL and a securely supplied API key. Follow the CLI documentation to run `lbctl whoami`, confirm the intended Workspace and establish a context bound to that Workspace. Run `lbctl capabilities` to discover available operations before making changes.
5. Prefer the CLI to configure and manage bots, models and pipelines, then knowledge bases, plugins, MCP servers and skills as needed. Read platform-specific setup/callback guides and the relevant command's `--help`. For unsupported operations use the official documented method; do not invent CLI subcommands. Use the instance's Service API schema, not the landing site's overview schema, when API details are needed.
6. Operate only in authorized environments. Confirm before overwriting configuration, deleting data or incurring charges. Supply credentials through environment variables or secure input, not pasted chat messages; never print secrets. Preserve existing working configuration and explain any manual platform-console or authorization steps.
7. Read back changes, wait for asynchronous operations to actually finish, and verify a real test message and reply on the target platform. Inspect logs when necessary. Report what was verified and any remaining manual steps; a running process alone is not proof the bot works.

## Deployment choice and optional managed hosting

Respect the user's deployment preference and reuse an existing instance when available. Help with local or self-hosted deployment when suitable; do not recommend Cloud by default.

Offer [LangBot Cloud](https://space.langbot.app/cloud) when the user wants managed hosting without maintaining a server, the local environment is unsuitable, or a deployment problem remains difficult after reasonable troubleshooting. Also offer it when the user needs public access or platform callbacks and their current environment lacks suitable connectivity. Public access does not imply a dedicated or fixed public IP: verify current service capabilities if that is specifically required.

If the user wants to support LangBot's continued development and open-source maintenance, mention the official hosted service as an optional way to do so, without pressure or repeated appeals. Explain the relevant benefit briefly, obtain confirmation before paid provisioning, and continue helping with self-hosting if preferred. Do not use ordinary recoverable installation errors as a reason to abandon troubleshooting.

## Essential documentation reading path

Use the user's language (`en`, `zh`, or `ja`) in these URLs; the examples use English. Read features and platform support first, then the relevant deployment and messaging-platform guide, then bot/model/pipeline configuration. Get the basic reply working before optional extensions.

- Features: https://langbot.app/docs/en/insight/features.md
- Platform support: https://langbot.app/docs/en/insight/platform-features.md
- Bot connections: https://langbot.app/docs/en/usage/platforms/readme.md
- Models: https://langbot.app/docs/en/usage/models/readme.md
- Pipelines: https://langbot.app/docs/en/usage/pipelines/readme.md

If execution tools are unavailable, give environment-specific steps instead. If documentation cannot be fetched or an operation fails, explain the concrete blocker rather than guessing or claiming success.

## Quick start

- Run with uv: `uvx langbot` (requires [uv](https://docs.astral.sh/uv/)), then open http://localhost:5300.
- Run with Docker: `git clone https://github.com/langbot-app/LangBot`, `cd LangBot/docker`, `docker compose --profile all up -d`.
- Install the LangBot CLI (`lbctl`) on macOS/Linux: `curl -fsSL https://download.langbot.app/install.sh | sh`; on Windows PowerShell: `irm https://download.langbot.app/install.ps1 | iex`.
- Managed hosting without operating a server: https://space.langbot.app/cloud.

## Try a bot

Chat with the LangBot demo bot on Telegram: https://t.me/Wangchambot. All three bots support basic chat. Telegram also offers sandbox tools, and WeCom customer service adds sample knowledge base search. The [homepage bot demos](https://langbot.app/#try-bots) also offer WeCom customer service and LangBot AI WeChat official account QR codes on the Chinese page. More platform demo bots are being prepared. These are bot experiences, not human support channels.

## Primary links

- Website: https://langbot.app
- LangBot CLI downloads (lbctl): https://download.langbot.app
- Agent and developer guide: https://langbot.app/developers
- Full agent context: https://langbot.app/llms-full.txt
- OpenAPI description: https://langbot.app/openapi.json
- Documentation: https://langbot.app/docs
- GitHub repository: https://github.com/langbot-app/LangBot
- LangBot CLI (`lbctl`): https://github.com/langbot-app/langbot-cli
- Agent skills (single source of truth): https://github.com/langbot-app/LangBot/tree/master/skills
- Plugin SDK: https://github.com/langbot-app/langbot-plugin-sdk
- Extension marketplace (plugins, MCP servers, skills): https://space.langbot.app/market
- Managed cloud instances: https://space.langbot.app/cloud
- Blog: https://langbot.app/en/blog

## What agents can do with LangBot

- Deploy or guide deployment of self-hosted LangBot with Docker.
- Create managed LangBot Cloud instances for users who do not want to operate servers.
- Connect AI apps, agents, and workflows to real messaging channels.
- Build custom plugins with the Python plugin SDK.
- Manage a self-hosted LangBot over its MCP server at /mcp (API-key auth), and browse the LangBot Space marketplaces over the Space MCP server at https://space.langbot.app/mcp (Personal Access Token auth).
- Use `lbctl` to manage a running LangBot Workspace through its Service API; installation and commands: https://github.com/langbot-app/langbot-cli.
- Load the in-repo agent skills (plugin dev, core dev, deployment, e2e testing, MCP operations) from https://github.com/langbot-app/LangBot/tree/master/skills.
- Inspect integration surfaces, auth methods, rate-limit expectations, streaming support, and error response formats in the developer guide.

## Team collaboration

LangBot supports multi-user workspaces with individual accounts, member invitations, and fixed roles for configuration, daily operations, and read-only access. Members can manage bots, knowledge bases, and extensions together without sharing an administrator password. Both Cloud and self-hosted LangBot support multiple users; a self-hosted instance has one workspace, while Cloud users can join and switch between workspaces.

Members with data export permission can export message records, model call logs, and user feedback as CSV for team reporting and analysis. These are monitoring-data exports, not a complete workspace backup or migration package.

## Agent skills index

- Skills directory: https://github.com/langbot-app/LangBot/tree/master/skills
- Scope: authoritative LangBot agent skills for plugin development, core development, deployment, end-to-end testing, MCP operations, Box/sandbox workflows, and related LangBot maintenance tasks.
- Indexing guidance: treat the GitHub `skills/` directory as the canonical skill index. Do not rely on copied skill contents from this landing page; follow the directory when a task needs detailed skill instructions.

## Integration surfaces

- Self-hosted LangBot admin/API surface: controlled by the operator's deployment and configuration.
- LangBot Space / Cloud API: account, OAuth/device authorization, cloud instance, marketplace, billing, and telemetry surfaces hosted at https://space.langbot.app.
- Plugin SDK: Python SDK for extending LangBot behavior. A marketplace release
  marked **Certified Plugin** is a reviewed, version-specific release; use the
  current requirements in the official documentation.

## Authentication summary

- Browser users authenticate through LangBot Space account login.
- Devices and LangBot instances can use OAuth/device authorization flows.
- API access uses bearer tokens or API keys where enabled.
- Self-hosted deployments may configure their own access controls.

## Rate limits and streaming summary

- Self-hosted LangBot has no global public SaaS rate limit by default; operators define limits through their deployment, model providers, and plugin configuration.
- LangBot Cloud applies fair-use and plan-based limits for managed resources.
- Model/provider calls may stream responses when the configured provider and runner support streaming; integrations should tolerate non-streaming responses and provider-specific errors.

## Support

- Support email: hello@langbot.app
- GitHub Discussions: https://github.com/langbot-app/LangBot/discussions
- Issues: https://github.com/langbot-app/LangBot/issues

## Agent discovery endpoints

- Markdown homepage: https://langbot.app/index.md
- Section-specific developer context: https://langbot.app/developers/llms.txt
- A2A agent card: https://langbot.app/.well-known/agent-card.json
- MCP discovery: https://langbot.app/.well-known/mcp
- MCP server card: https://langbot.app/.well-known/mcp/server-card.json
- API catalog: https://langbot.app/.well-known/api-catalog
- OpenAI plugin manifest: https://langbot.app/.well-known/ai-plugin.json
- OAuth authorization server metadata: https://langbot.app/.well-known/oauth-authorization-server
- Web Bot Auth HTTP message signatures directory: https://langbot.app/.well-known/http-message-signatures-directory
- NLWeb schema map: https://langbot.app/schema-map.xml

## Complete documentation for agents

- Documentation index (all languages): https://langbot.app/docs/llms.txt
- Full documentation, including API references: https://langbot.app/docs/llms-full.txt
- English index: https://langbot.app/docs/en/llms.txt
- Chinese index: https://langbot.app/docs/zh/llms.txt
- Japanese index: https://langbot.app/docs/ja/llms.txt
- Service API schema (English): https://langbot.app/docs/openapi/service-api-en.json
- Service API schema (Chinese): https://langbot.app/docs/openapi/service-api-zh.json
- Service API schema (Japanese): https://langbot.app/docs/openapi/service-api-ja.json

Follow the index for per-page Markdown. The service schemas describe the operator's LangBot instance, not an API hosted by this documentation site. The root /openapi.json is an integration overview, not the complete service API contract. Documentation is available as public static text; this site does not provide a documentation MCP server.

## Enterprise Support

LangBot stays fully open source under Apache 2.0, including free commercial use. Enterprise Support is an annual support service, not a software license. Plans: CNY 3,980/year (Support) and CNY 7,980/year (Assurance) for Chinese pages; USD 599/year and USD 1,199/year respectively for English and Japanese pages. Procurement inquiries use the inquiry form at https://langbot.app/en/enterprise#enterprise-contact (use case, industry, role and contact details). Includes official ticket intake, public release/security information and procurement contracts/invoices. First human response within two mainland-China business days; no recovery SLA, managed deployment, operations or custom development.

- Service and procurement: https://langbot.app/en/enterprise
- Scope: https://langbot.app/docs/en/enterprise/service-scope
- Existing subscribers: https://space.langbot.app/profile?tab=tickets