LangBot
Platform for AI chatbots on WeChat, WeCom, QQ, Feishu, DingTalk, Slack, Discord and Telegram, run from one dashboard.
Quick answer
LangBot is a platform for AI chatbots on WeChat, WeCom, QQ, Feishu, DingTalk, Slack, Discord and Telegram, run from one dashboard, listed under AI app & agent builders. A typical small-business use: answer customer questions in WeCom, WeChat or Slack groups from a company knowledge base. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: Apache-2.0, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Nov 4, 2026.
What is LangBot?
LangBot connects LLMs and agent platforms to instant-messaging apps. One instance can run bots on Discord, Telegram, Slack, LINE, QQ, WeChat (personal and Official Account), WeCom, Lark, DingTalk, KOOK and Matrix bridges, with multi-turn chat, tool calling, a built-in knowledge base, and integrations with Dify, Coze, n8n and Langflow. A web panel configures pipelines, models and plugins, and adds access control, rate limiting, sensitive-word filtering and monitoring. It also exposes an HTTP API and an MCP server.
Where it fits in a 10–200 person business
- Answer customer questions in WeCom, WeChat or Slack groups from a company knowledge base
- Put an existing Dify or n8n workflow behind a DingTalk or Feishu bot for staff
- Moderate and engage community groups across several chat platforms from one dashboard
These use cases are our editorial suggestions, not claims made by the project.
Can a business use LangBot? (license)
| License | Apache-2.0 |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep license and notices. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does LangBot phone home?
| Telemetry (usage data sent to the vendor) | On by default Sends execution telemetry and a daily instance heartbeat (configuration categories and resource counts) to the LangBot Space service, by default https://space.langbot.app. Message bodies, prompts and credentials are not intentionally collected. How to turn it off: Set space.disable_telemetry to true in data/config.yaml (or SPACE__DISABLE_TELEMETRY). |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Yes, by default The plugin marketplace is enabled by default (plugin.enable_marketplace) and telemetry goes to LangBot Space. |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Yes, free The open-source edition supports multiple users in its single Workspace with five fixed roles (Owner, Admin and others) and invitations. Source: langbot.app/en/blog/langbot-cloud-multi-user-workspaces |
| Data residency / GDPR notes from the project | Not documented |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does LangBot need?
The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.
No CPU, RAM or disk figures are published. The Docker Compose profile starts the core, a plugin runtime and a sandbox container; models are called through APIs or a local server such as Ollama.
How much does it cost to host LangBot per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy LangBot
Method: Docker Compose
git clone https://github.com/langbot-app/LangBot
cd LangBot/docker
docker compose --profile all up -d
# dashboard: http://localhost:5300From the official instructions: langbot.app/docs/en/deploy/langbot/docker. Always check the source for the current version before you run it.
Known gotchas when self-hosting LangBot
- Telemetry to LangBot Space is on by default and includes instance and Workspace IDs, versions, resource counts and short error text; set space.disable_telemetry to true to turn it off. source
- On a server, the docs say to firewall the dashboard and runtime ports so only trusted sources can reach them. source
- A non-empty api.global_api_key authenticates the HTTP API and built-in MCP server without a login session; treat it as a secret and expose authenticated endpoints only over HTTPS. source
- On Linux, put the project in a writable directory such as /opt, not /root or /etc, or sandbox features can be blocked by security rules. source
Alternatives in AI app & agent builders
- AutoGPT Platform Visual builder for long-running AI agents and workflows, self-hostable as a single container. Compare AutoGPT Platform vs LangBot
- Dify Visual platform for building LLM apps, RAG chatbots, agents and workflows. Compare Dify vs LangBot
- Langflow Visual builder for AI agents and RAG flows that you can deploy as APIs or MCP servers. Compare LangBot vs Langflow
- Mem0 Long-term memory layer for AI assistants and agents, with a self-hosted REST server and dashboard. Compare LangBot vs Mem0
- Flowise Drag-and-drop builder for LLM agents and chatflows (archived August 2026).
- CowAgent Self-hosted AI agent (formerly chatgpt-on-wechat) that answers in WeChat, WeCom, Feishu, DingTalk, Slack and a web console. Compare CowAgent vs LangBot
- AstrBot Multi-platform AI chatbot and agent framework for QQ, WeCom, Feishu, DingTalk, Official Accounts, Telegram and Slack. Compare AstrBot vs LangBot
- Sim Visual builder for AI agent workflows, with knowledge bases, integrations and an API. Compare LangBot vs Sim
- Coze Studio Open-source edition of ByteDance's Coze agent-building platform. Compare Coze Studio vs LangBot
- DB-GPT AI data assistant that connects to your databases, writes SQL and code, and turns analysis into reports. Compare DB-GPT vs LangBot
- Agent Zero General-purpose personal AI agent that uses its own Linux environment, browser, memory and tools. Compare Agent Zero vs LangBot
LangBot FAQ
How much RAM does LangBot need?
LangBot does not publish an official RAM figure, so we do not state one. No CPU, RAM or disk figures are published. The Docker Compose profile starts the core, a plugin runtime and a sandbox container; models are called through APIs or a local server such as Ollama.
How much does it cost to self-host LangBot?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is LangBot free for commercial use?
LangBot is licensed under Apache-2.0 (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep license and notices. This is a summary, not legal advice.
What are common problems when self-hosting LangBot?
Telemetry to LangBot Space is on by default and includes instance and Workspace IDs, versions, resource counts and short error text; set space.disable_telemetry to true to turn it off. On a server, the docs say to firewall the dashboard and runtime ports so only trusted sources can reach them. A non-empty api.global_api_key authenticates the HTTP API and built-in MCP server without a login session; treat it as a secret and expose authenticated endpoints only over HTTPS. On Linux, put the project in a writable directory such as /opt, not /root or /etc, or sandbox features can be blocked by security rules.
Is LangBot still maintained?
Yes, it is actively developed. Last commit: Nov 4, 2026. Latest release: v4.11.4 (Oct 29, 2026). Checked Nov 4, 2026.
How do I install LangBot?
The official method is Docker Compose. The exact commands are in the "How to deploy" section above and in the official instructions: https://langbot.app/docs/en/deploy/langbot/docker
What are self-hosted alternatives to LangBot?
Other apps in AI app & agent builders: AutoGPT Platform, Dify, Langflow, Mem0, Flowise, CowAgent, AstrBot, Sim, Coze Studio, DB-GPT, Agent Zero.
Sources
- GitHub repository: github.com/langbot-app/LangBot
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 2, Gotcha 4: langbot.app/docs/en/deploy/langbot/docker
- License text: github.com/langbot-app/LangBot/blob/master/LICENSE
- Gotcha 1: langbot.app/docs/en/insight/data-collection-policy
- Gotcha 3: langbot.app/docs/en/deploy/settings
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-11-04. Spotted something out of date? Tell us.