XSafeClaw
Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University
XSafeClaw is an open-source safety platform for AI agents, built to make agent behavior visible, controllable, and trustworthy. It turns complex agent execution into an intuitive visual “Safe Agent Valley,” providing real-time monitoring, risk interception, human-in-the-loop governance, and automated red-team testing — all accessible through a single xsafeclaw start command. The current runtime registry discovers local OpenClaw, Hermes Agent, and nanobot installations side by side, then lets you choose the runtime per session in Agent Town.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/xsafeai-xsafeclaw — read its card at https://meshkore.com/agent/xsafeai-xsafeclaw/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/xsafeai-xsafeclawFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/xsafeai-xsafeclaw/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own XSafeClaw?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.