QwenPaw on Railway
Personal AI assistant from the AgentScope team with chat-app channels and memory, QwenPaw v2.2.2 on Railway.
QwenPaw is an open-source personal AI assistant from the AgentScope team. It has a web console, a REST API, agents, skills, scheduled tasks and long-term memory, and it can connect to chat apps such as Telegram, Discord, Slack, DingTalk, Feishu, QQ and WeCom.
People run it as an assistant they message from their phone, for scheduled briefings and reminders, and for research and document work with a real Chromium browser. It needs an API key for at least one supported model provider, which you add in the console.
QwenPaw is released under the Apache-2.0 licence. The Railway template is community-made and not affiliated with the QwenPaw or AgentScope teams.
What QwenPaw can do
- Web console and REST API
- Chat-app channels with sender approval
- Long-term memory
- Scheduled tasks and reminders
- Skills and a Chromium browser
- Tool Guard approval for risky tool calls
What people use it for
- A private assistant you message from Telegram, Discord, Slack or Feishu
- Scheduled briefings, reminders and recurring checks delivered to a chat
- Research and document work with a real browser
- A REST API that streams agent replies into your own scripts
Videos
Running QwenPaw on Railway
The Railway template runs QwenPaw v2.2.2 from the official image as one service with a volume at /data for chats, memory and encrypted keys. The login is created from generated credentials before the app starts, and the service will not start without one. Tool Guard is forced on and telemetry is off by default. The template notes put the full container at roughly 0.7 to 0.8 GB idle, more while Chromium runs.
QwenPaw templates on Railway
Tracklayer templates are listed first. Other QwenPaw templates follow, ordered by total deployments on Railway. How this works.
Deployment numbers as of 2026-11-20.
Questions about QwenPaw
How do I log in?
Open the public URL once healthy and sign in with QWENPAW_AUTH_USERNAME and QWENPAW_AUTH_PASSWORD from the Variables tab. Then add a model provider key under Settings, Models. The login cannot be switched off in this template.
Do I need a model key?
Not to deploy. You need an API key for at least one supported provider, entered in the console after login.
What are the security caveats?
The agent's shell tool and the console terminal run as root inside the container with access to the volume and network, and Railway offers no kernel sandbox for them. Set QWENPAW_TOOL_GUARD_DENIED_TOOLS=execute_shell_command to remove shell access.
Can I run more than one replica?
No. QwenPaw is a single-writer process with file-based state, so keep one replica and scale vertically.
How do I upgrade?
Change the pinned tag and digest in the Dockerfile to a newer release and redeploy. Everything on the volume is kept, but download a backup from the console first.
Similar apps
Tracklayer maintains the templates marked as such; QwenPaw is a trademark of its owners and this site is not affiliated with them.