← Compare LangBot

Self-hosted LangBot vs LangBot Cloud

Compare running open-source LangBot on your own server with LangBot Cloud: start instantly at cloud.langbot.app with no deployment, or choose a Dedicated environment for production.

Last reviewed:

In short

Both run the same open-source LangBot. LangBot Cloud is the fastest way in: sign up at cloud.langbot.app and build a bot in the browser, with no server, no deployment and no model API key required, because LangBot Models is built in. For production you can move up to a Dedicated environment with its own database, storage and public URL. Self-hosting is free and keeps everything on your own machines, but you operate the server, upgrades, backups and the public HTTPS address webhook platforms need.

Self-hosted LangBotLangBot Cloud
Getting startedInstall with uvx langbot or Docker, then configureSign up at cloud.langbot.app and follow the setup wizard; nothing to deploy
PriceFree (Apache 2.0)Free plan on cloud.langbot.app; paid plans and Dedicated environments on the pricing page
AI modelsBring your own API keys, or sign in with a LangBot Space account to add LangBot Models with a free starter quotaLangBot Models ready to use, no API key needed; paid plans include monthly credits; your own keys also work
Configuration helpWorkspace Assistant (needs a LangBot account or a configured model)Workspace Assistant ready from the start
Public HTTPS URL for webhooksYou provide a domain, HTTPS and reverse proxyIncluded
Upgrades and backupsYou run themHandled by the LangBot team
Where data livesYour own serversLangBot-operated cloud; Dedicated gives you an isolated environment
Personal QQ / WeChatPad (protocol-based adapters)AvailableNot available on Cloud plans
Best forTeams with ops capacity, strict data residency, custom infrastructureAnyone who wants a working bot today, and teams that want production bots without running servers

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
    1. Sign up
    2. Pick a platform
    3. 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.

    • ClaudeClaude
    • OpenAIGPT
    • GeminiGemini
    • DeepSeekDeepSeek
    • QwenQwen
    • ZhipuGLM
    • KimiKimi
    • GrokGrok
    No API key needed
    Details ›

    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 @mention
    group.member_joined → welcome
    Applied after you confirm
    Details ›

    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
    Confirm
    Details ›

    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 ServerlbctlWebhooks

    Agent tools

    MCPSkillsSandboxRAGEvents
    Details ›

    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

    Seven component types in an isolated runtime, with permissions you grant.

    Plugin Runtime · isolated process

    RunnerToolCommandEventListenerKnowledgeEngineParserPageCertified Plugins
    Details ›

    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 Support
    Details ›

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

Choose LangBot Cloud when

  • You want to try LangBot right now: open cloud.langbot.app, sign up, and the wizard walks you through your first bot. There is nothing to install.
  • You do not have a model API key yet: LangBot Models (Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi and more) works out of the box.
  • You want a bot answering on LINE, Lark, WeCom, DingTalk or WeChat without buying a server or setting up tunnels: these platforms call a public webhook URL, and Cloud provides it.
  • You do not want to own upgrades, backups and uptime. For production workloads, a Dedicated environment adds an isolated database, storage and public URL with 24/7 message processing.

See current plans on the pricing page.

Choose self-hosted when

  • You need all data on your own machines or inside your network.
  • You already run Docker or Kubernetes and can maintain HTTPS and upgrades.
  • You use adapters that are not offered on Cloud plans, such as protocol-based personal QQ or WeChatPad.

Start with uvx langbot or the Docker guide. Signing the instance in with a LangBot Space account adds LangBot Models automatically.

Moving between them

Both are the same LangBot, so bots, pipelines and plugins are configured the same way. Platform credentials and webhook URLs have to be updated on the platform side when the address changes.

Further reading

FAQ

Can I use LangBot without deploying anything?

Yes. Sign up at cloud.langbot.app and create bots in the browser. A free plan is available, and LangBot Models works without your own model API key.

Is the self-hosted version limited?

No. LangBot is open source under Apache 2.0, self-hosting has no feature limits and commercial use is free.

Do I need a public IP to self-host?

Only for platforms that push messages to a webhook (for example WeCom, LINE, QQ Official and WeChat Official Accounts). Telegram, Discord, Slack Socket Mode, Lark long connection and DingTalk Stream Mode work without one.

Does LangBot Cloud give me a fixed IP?

It includes a public HTTPS URL, not a dedicated fixed outbound IP. If your platform needs IP allowlisting, contact us first.