LangBot vs NoneBot and Koishi
NoneBot (Python) and Koishi (TypeScript) are general chatbot frameworks for developers. LangBot is an AI-native bot platform with a web panel, built-in Agent, knowledge bases and Dify/n8n/Coze integration. Compare them.
Last reviewed:
In short
NoneBot and Koishi are mature cross-platform chatbot frameworks: you write plugins in code, and AI features come from plugins. LangBot is built around AI from the start: models, an Agent, knowledge bases, MCP, Skills, a sandbox and agent-platform runners are configured from a web panel, and plugins extend it.
| LangBot | NoneBot / Koishi | |
|---|---|---|
| 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 | Change the code |
| Try it | cloud.langbot.app: no deployment, no code | Install and write the bot in code |
| Models | LangBot Models built in, no API key needed; or any compatible API | Through community plugins and your own provider keys |
| Set-up help | Workspace Assistant configures resources from a description | Not listed in their READMEs |
| APIs for your systems | HTTP Service API, MCP server, lbctl CLI and event webhooks | Framework APIs in code |
| Primary user | Teams that want AI bots running without much code | Developers writing bot logic in code |
| AI features | Built in: Agent, RAG, MCP, Skills, sandbox, Dify/n8n/Coze/Langflow runners | Through community plugins |
| Configuration | Web panel | Code and config files (Koishi also has a web console) |
| Language for extensions | Python plugin SDK | Python (NoneBot) / TypeScript (Koishi) |
| Licence | Apache 2.0 | MIT (both) |
What LangBot gives you out of the box
No deployment: cloud.langbot.app
Sign up and build a bot in your browser. Free plan, public URL included.
cloud.langbot.app- Sign up
- Pick a platform
- Bot online
Details ›
Sign up at 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
Top models ready to use. No API key to apply for.
- Claude
- GPT
- Gemini
- DeepSeek
- Qwen
- GLM
- Kimi
- Grok
No API key neededDetails ›
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
Say what should change. Agents and the assistant carry it out after you approve.
In the support group, only answer when someone @mentions the bot, and welcome new members.Routing: reply on @mentiongroup.member_joined → welcomeApplied after you confirmDetails ›
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 the goal; review the proposed changes; confirm.
Proposed changes
- Create pipeline “Support”
- Attach knowledge base “FAQ”
- Bind to the WeCom bot
ConfirmDetails ›
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
One set of operations behind HTTP, MCP, CLI and webhooks; agents get MCP, Skills, a sandbox and knowledge bases.
One Workspace API
HTTP APIMCP ServerlbctlWebhooksAgent tools
MCPSkillsSandboxRAGEventsDetails ›
An HTTP Service API with API keys, LangBot's own MCP server, the
lbctlCLI 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
Seven component types in an isolated runtime, with permissions you grant.
Plugin Runtime · isolated process
RunnerToolCommandEventListenerKnowledgeEngineParserPageCertified PluginsDetails ›
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 lists plugins, MCP servers and Skills, with reviewed Certified Plugins.
Open source, with official backing
Apache 2.0, official hosting and enterprise support.
Apache 2.0Free commercial useOfficial CloudEnterprise SupportDetails ›
Apache 2.0 with free commercial use, an official managed service, and optional Enterprise Support with contracts and invoices.
Choose NoneBot or Koishi when
You are building rule-based or game bots in code, you want full control of the event loop, and AI is one feature among many.
Choose LangBot when
The bot is mainly an AI assistant or agent, you want non-developers to manage it in a web panel, or you want to plug in an existing Dify, n8n or Coze app.