Railway

Deploy Astrbot

AI Agent Assistant & Chatbot Platform - multi-platform, LLM-agnostic

Deploy Astrbot

Just deployed

/AstrBot/data

AstrBot — AI Agent Assistant & Chatbot Platform

Deploy to Railway

AstrBot is an open-source AI agent assistant and chatbot platform that supports multiple messaging platforms, LLM providers, and plugin extensions. Deploy a self-hosted instance on Railway in one click.

Deploy and Host AstrBot

Deploying AstrBot on Railway gives you a self-hosted AI agent platform with persistent storage, automatic scaling, and a managed environment. No server maintenance required.

About Hosting

AstrBot runs as a single container on Railway with a persistent volume for SQLite data. The WebUI is served on port 6185 and accessible via your Railway public domain.

Why Deploy

  • One-click deploy: No manual server setup — Railway handles provisioning, networking, and SSL
  • Persistent storage: SQLite data survives restarts via Railway volume mounts
  • Auto-redeploy: Push to your connected GitHub repo to trigger fresh deploys
  • Managed infrastructure: Railway handles health checks, logging, and DNS

Common Use Cases

  • Personal AI assistant: Connect to your preferred LLM and chat from any platform
  • Multi-platform bot: Bridge QQ, Telegram, Discord, WeChat, and more through one backend
  • Plugin development: Build and test community plugins in a live environment
  • Team chatbot: Deploy a shared agent with session isolation and persona management

Dependencies for AstrBot

AstrBot is fully self-contained. It bundles:

  • FastAPI web server
  • SQLite database (no external DB needed)
  • Plugin runtime with sandboxed execution
  • Multi-platform message adapters

Deployment Dependencies

DependencyTypeNotes
VolumeStorageAuto-mounted at /AstrBot/data for persistence
Port 6185NetworkWebUI + API (exposed publicly)

No external databases or third-party services are required.

Features

  • Multi-platform support: QQ, WeChat, Telegram, Discord, DingTalk, Feishu, and more via OneBot v11 adapters
  • LLM provider agnostic: OpenAI, Anthropic, Google Gemini, DeepSeek, Qwen, Ollama, and any OpenAI-compatible API
  • Plugin ecosystem: Extend functionality with community plugins — moderation, tools, knowledge bases, and more
  • Visual dashboard: WebUI at port 6185 for configuration, chat, logs, and plugin management
  • Agent sandbox: Optional native Python/Shell code execution environment (Shipyard)
  • Conversation management: Session isolation, persona switching, and conversation history
  • Multi-agent orchestration: Sub-agent support for complex task delegation

Configuration

Environment Variables

VariableDefaultDescription
TZUTCContainer timezone
ASTRBOT_DASHBOARD_INITIAL_PASSWORDAstrbot1Initial dashboard password (set before first boot)

All other configuration is done through the WebUI after first login.

Ports

PortPurpose
6185WebUI + API (primary, public)
6199OneBot v11 WebSocket (optional)

License

AGPL-3.0


Template Content

More templates in this category

View Template
Chat Chat
Chat Chat, your own unified chat and search to AI platform.

okisdev
116
View Template
stella
Self-host stella with web, API, Postgres, Redis, and object storage.

Jan Kubica
5
View Template
Hermes Agent | OpenClaw Alternative with Dashboard
Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

codestorm
64