# LangBot full agent context

LangBot is an open-source instant messaging AI agent bot platform. It helps developers and operators expose AI applications, agents, workflows, and LLM-backed automations to real end users in instant messaging channels.

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.

## Canonical agent entry

Read https://langbot.app/llms.txt first for the maintained deployment, CLI, hosting-choice and verification workflow. This file retains extended product and integration context.

## 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.

## 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.

## Product identity

- Name: LangBot
- Category: Developer tool, AI bot platform, AI agent bot platform
- Website: https://langbot.app
- Documentation: https://langbot.app/docs
- Repository: https://github.com/langbot-app/LangBot
- License: Apache-2.0
- Managed cloud: https://space.langbot.app/cloud
- Marketplace (plugins, MCP servers, skills): https://space.langbot.app/market
- Contact: hello@langbot.app

## Core use cases

1. Connect an AI application to messaging platforms such as Discord, Slack, Telegram, Mattermost, WeChat, WeCom, QQ, Lark, DingTalk, LINE, and KOOK.
2. Connect AI builders such as Dify, Coze, n8n, FastGPT, OpenAI-compatible APIs, Claude, DeepSeek, Gemini, Qwen, Ollama, and custom providers to end users.
3. Operate a production bot with access control, rate limiting, conversation context, observability, knowledge base/RAG, and plugin extensibility.
4. Build plugins with the Python SDK. Marketplace releases marked **Certified
   Plugin** are reviewed, version-specific releases; use the official
   documentation for current requirements.
5. Use LangBot Cloud when the user wants a managed instance instead of self-hosting.

## Agent-friendly navigation

- Start here for agents: https://langbot.app/developers
- Machine-readable summary: https://langbot.app/llms.txt
- OpenAPI description: https://langbot.app/openapi.json
- Main docs: https://langbot.app/docs
- GitHub source: https://github.com/langbot-app/LangBot
- LangBot CLI downloads (lbctl): https://download.langbot.app
- LangBot CLI (`lbctl`), for managing a running Workspace through the Service API: https://github.com/langbot-app/langbot-cli
- Agent skills (single source of truth): https://github.com/langbot-app/LangBot/tree/master/skills
- Self-hosted MCP server: http://<your-langbot-host>:5300/mcp (API-key auth)
- LangBot Space MCP server: https://space.langbot.app/mcp (Personal Access Token auth)
- Plugin SDK source: https://github.com/langbot-app/langbot-plugin-sdk

## 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

LangBot's authoritative agent skills live in the LangBot repository, not in the landing-page repository:

- Skills directory: https://github.com/langbot-app/LangBot/tree/master/skills
- Scope: plugin development, core development, deployment, end-to-end testing, MCP operations, Box/sandbox workflows, and related LangBot maintenance tasks.
- Indexing guidance: use the GitHub `skills/` directory as the canonical index and load detailed instructions from there when needed. This file links to the directory instead of duplicating each skill.

## Integration and auth overview

LangBot has multiple integration surfaces:

- Self-hosted LangBot: configured by the operator. API availability, auth, and rate limits depend on the deployment.
- LangBot Space / Cloud: hosted API surfaces under https://space.langbot.app for accounts, OAuth/device authorization, cloud instances, marketplace, billing, and telemetry.
- Plugin SDK: Python package and runtime protocol for extending LangBot. A
  **Certified Plugin** marker applies to a reviewed, version-specific marketplace
  release rather than an author or plugin name.

Authentication patterns:

- Browser login for account users.
- OAuth/device authorization for linking LangBot instances to LangBot Space accounts.
- Bearer tokens and API keys for API-enabled surfaces.
- Self-hosted deployments may add network, proxy, or application-level access controls.

## Rate limits

- Self-hosted deployments do not impose a universal LangBot public rate limit by default. Limits may come from the operator, configured model providers, IM platform adapters, or plugins.
- LangBot Cloud applies fair-use and plan-based resource limits, especially for managed instance resources, model usage, and billing/credit-controlled features.
- Agents should implement exponential backoff for HTTP 429 and respect `Retry-After` when present.

## Streaming

- LangBot runners can forward streaming model/provider output when the configured provider, runner, and adapter support it.
- Integrations should support both streaming and non-streaming responses because some providers, workflows, or messaging channels return complete messages only.
- If a channel or provider cannot stream, LangBot may deliver the final response after the upstream call completes.

## Error response expectations

HTTP APIs use JSON error responses. Agents should expect fields such as:

```json
{
  "code": 400,
  "message": "human-readable error message",
  "data": null
}
```

Common status classes:

- 400: invalid request or missing required field
- 401: missing or invalid authentication
- 403: authenticated but not allowed
- 404: resource not found
- 409: conflict or duplicate resource
- 429: rate limited; retry after the indicated delay if provided
- 500: server or upstream provider error

## Recommended agent behavior

- Prefer official docs and OpenAPI links before guessing endpoint shapes.
- Follow the deployment-choice guidance at https://langbot.app/llms.txt; do not recommend Cloud by default.
- For self-hosting, inspect the user's deployment config before changing adapters, credentials, or model provider settings.
- Never expose IM platform tokens, model provider API keys, or LangBot Space tokens in chat logs.
- When building plugins, use the official plugin SDK and isolate network/file operations.

## Canonical keywords

LangBot, AI bot platform, AI agent bot platform, Dify integration, Coze integration, n8n integration, OpenAI-compatible model, Discord bot, Slack bot, Telegram bot, WeChat bot, WeCom bot, QQ bot, Lark bot, DingTalk bot, LINE bot, plugin SDK, chatbot framework, open-source bot platform, self-hosted AI bot, managed AI bot cloud.

## Well-known agent discovery endpoints

LangBot publishes standard discovery endpoints for AI agents and crawlers:

- `/.well-known/agent-card.json` for A2A Agent Card discovery.
- `/.well-known/mcp` for MCP server discovery.
- `/.well-known/mcp/server-card.json` for MCP server preview metadata and tool annotations.
- `/.well-known/api-catalog` for RFC 9727 API catalog discovery.
- `/.well-known/ai-plugin.json` for OpenAI plugin-style discovery.
- `/.well-known/oauth-authorization-server` for OAuth metadata and PKCE S256 support discovery.
- `/.well-known/http-message-signatures-directory` for Web Bot Auth key directory discovery.
- `/index.md` for markdown homepage fallback.
- `/developers/llms.txt` for scoped developer context.
- `/schema-map.xml` for NLWeb schema feed discovery.

## 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