# LangBot vs AstrBot

Source: https://langbot.app/en/compare/langbot-vs-astrbot · Last reviewed: 2026-11-11

LangBot and AstrBot are both open-source AI chatbot platforms for IM apps. Compare licensing, managed hosting, team features, platforms and agent-platform integration.

## In short

Both are open-source Python platforms that connect LLMs and agents to chat apps, with plugins, knowledge bases, MCP and sandboxed tools. The main differences are licensing (Apache 2.0 vs AGPL-3.0), LangBot's official managed hosting and multi-user workspaces, and LangBot's focus on serving customers, communities and teams.

| | LangBot | AstrBot |
| --- | --- | --- |
| Natural-language control | Tell the Workspace Assistant or an authorized agent what to change: routing, pipelines, replies, group actions; every write is confirmed or permission-gated | Not listed in its README |
| Try without deploying | cloud.langbot.app, run by the LangBot team, with a free plan | Third-party one-click hosting |
| Official model service | LangBot Models: Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi and more with no API key; free starter quota for self-hosted instances signed in with a LangBot account | Configure your own model providers |
| Configure by chatting | Workspace Assistant inspects the workspace and applies changes after you confirm | Not listed in its README |
| APIs and automation | HTTP Service API, LangBot MCP server, lbctl CLI and outgoing event webhooks | Not listed in its README |
| Plugin interfaces | Cross-process plugin runtime; Runner, Tool, Command, EventListener, KnowledgeEngine, Parser and Page components; permissioned Workspace API; Certified Plugins | Plugin marketplace with 1000+ plugins |
| Licence | Apache 2.0 | AGPL-3.0 |
| Team features | Workspaces with members and roles, operation log, two-factor sign-in | Check AstrBot's documentation |
| Agent platforms | Dify, n8n, Coze, Langflow, DeerFlow, Bailian, Tbox runners | Dify, Bailian, Coze |
| Platforms | Both cover QQ, WeCom, Lark, DingTalk, WeChat Official Accounts, Telegram, Slack, Discord, LINE and KOOK | Same, with some adapters community-maintained |
| Positioning | Service bots for customers, communities and teams | All-in-one agent chatbot for individuals, developers and teams |

## What LangBot gives you out of the box

### No deployment: cloud.langbot.app

Sign up at [cloud.langbot.app](https://cloud.langbot.app) and build a bot in the browser with a setup wizard. There is a free plan, the public HTTPS URL webhook platforms need is included, and a Dedicated environment is available for production. Self-hosting stays free and unlimited.

### Official model service: LangBot Models

Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, Grok and more, plus embedding, rerank and speech models, with no model API key to obtain. Cloud plans include monthly credits; self-hosted instances signed in with a LangBot Space account get the models added automatically with a free starter quota. Your own API keys keep working alongside.

### Control your bots in natural language

Agents, a unified API and standard platform events and APIs work together. Every Workspace operation (bots, routing, pipelines, models, knowledge bases, monitoring) is one catalog shared by the HTTP API, the MCP server, the Workspace Assistant and plugins, and adapters expose standard platform APIs such as send, reply, edit and recall messages, query groups and members, and, where the platform allows, mute or remove members. So you can change how a bot behaves by telling the Workspace Assistant, or let an authorized agent act on the platform from a chat instruction. Writes need your confirmation or an explicit permission grant.

### Workspace Assistant

Describe what you want in plain language. The assistant inspects your existing models, knowledge bases and pipelines, proposes a configuration and applies it only after you confirm each change.

### Rich APIs and flexible tools

An HTTP Service API with API keys, LangBot's own MCP server, the `lbctl` CLI and outgoing event webhooks for your systems. Agents can use MCP tools (stdio and HTTP), Skills, a code sandbox (Docker, nsjail or E2B), knowledge bases with rerank, and platform events such as member joins, reactions and card clicks.

### Rich, stable plugin interfaces

Plugins run in a separate Plugin Runtime process and are hot-pluggable. The Python SDK offers Runner, Tool, Command, EventListener, KnowledgeEngine, Parser and Page components, and a Workspace API whose operations a plugin must declare and a member must grant. The [LangBot Space marketplace](https://space.langbot.app/market) lists plugins, MCP servers and Skills, with reviewed Certified Plugins.

### Open source, with official backing

Apache 2.0 with free commercial use, an official managed service, and optional Enterprise Support with contracts and invoices.

## Licensing matters for products

Apache 2.0 lets you modify LangBot and ship it inside your own product or service without releasing your source code. AGPL-3.0 requires you to offer the source of a modified version to users who interact with it over a network. Check with your legal team if you plan to embed or resell either.

## Choose LangBot when

- You want an official managed option (LangBot Cloud) or enterprise support with contracts and invoices.
- Several people manage the bots and you need roles and an operation log.
- You want to plug in agents from Dify, n8n, Coze or Langflow.

## Choose AstrBot when

You prefer its plugin ecosystem or community, and AGPL-3.0 fits how you will distribute it.

## FAQ

### Can I use LangBot commercially?

Yes. LangBot is Apache 2.0 licensed; commercial use is free, and Enterprise Support is optional.

## Further reading

- [AstrBot on GitHub](https://github.com/AstrBotDevs/AstrBot)