
Deploy LangBot
Open-source LLM chatbots for Telegram, Discord, Slack, WeChat and more
Plugin Runtime
Just deployed
/app/data
Just deployed
/var/lib/postgresql/data
Just deployed
/app/data
Deploy and Host LangBot on Railway
LangBot is an open-source platform for running LLM-powered bots on instant messaging apps. You connect Telegram, Discord, Slack, Lark, DingTalk, WeCom, QQ, WeChat or LINE to models such as OpenAI, Anthropic, Gemini, DeepSeek or Ollama, or to Dify, n8n and Coze, and manage bots, pipelines, knowledge bases and plugins from one web UI.
About Hosting LangBot
This template runs LangBot v4.11.9 as three services on Railway's private network. LangBot serves the web UI, API and webhook callbacks on its public domain. Plugin Runtime installs and runs plugins and is reachable only privately, protected by a generated token. Postgres stores bots, pipelines, models, users and history; LangBot migrates it on boot. Both app services build from a public GitHub repo that pins the official image by version and digest, and each keeps its data on a volume. The owner account is created on first boot from the email you enter, with a generated password, so nobody else can claim the instance.
Common Use Cases
- Team assistant: an LLM bot in Slack, Discord, Lark or Telegram groups
- Customer support bot that answers from a knowledge base on WeCom, WeChat or LINE
- Chat front end for Dify, n8n, Coze or Langflow workflows
- One place to manage many bots, models and pipelines, extended with marketplace plugins and MCP tools
Dependencies for LangBot Hosting
- PostgreSQL (included, Railway Postgres)
- LangBot Plugin Runtime (included, private service)
- An API key for at least one model provider, added in the web UI after sign-in
- Bot credentials for each IM platform you connect
Deployment Dependencies
- LangBot on GitHub and release v4.11.9
- LangBot Docker deployment docs
- LangBot configuration reference
- Template repo, start scripts and changelog
Implementation Details
The only prompt is LANGBOT_ADMIN_EMAIL. After deploy:
- Open the LangBot service's Variables tab and copy
LANGBOT_ADMIN_PASSWORD. - Open the LangBot domain, sign in with your email and that password, and change the password under your account settings. Keep
SYSTEM__RECOVERY_KEYfor the Forgot password flow. - Add a model provider and its API key, create a pipeline, then add a bot for your IM platform. Webhook URLs shown in the UI use your Railway domain; set
API__WEBHOOK_PREFIXon the LangBot service if you add a custom domain.
LangBot reads any SECTION__KEY environment variable as a config.yaml override, for example SPACE__DISABLE_TELEMETRY=true to turn off its optional usage telemetry. Email for workspace invitations (EMAIL__PROVIDER, EMAIL__SMTP__HOST and related settings) is optional.
Not included: the upstream Box sandbox, because it needs the host Docker socket or nsjail namespaces, which Railway containers don't have. Shell and file agent tools and local stdio MCP servers are therefore off; plugins, skills, knowledge bases and HTTP or SSE MCP servers work.
Updates: the services build from the template repo's main branch. When we bump the LangBot version there, Railway shows you an update notice and you choose when to apply it. Read the repo's CHANGELOG.md first; LangBot migrates the database on boot.
Why Deploy LangBot on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.
By deploying LangBot on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.
Template Content
Plugin Runtime
aalfath/langbot-railway-templateLANGBOT_ADMIN_EMAIL
Email of the LangBot owner account, created on first boot so nobody else can claim the instance. Sign in with it.

