agentsteer
Runtime protection for AI coding agents
AgentSteer intercepts every tool call your AI agent makes via a PreToolUse hook, scores it against the task description, and blocks unauthorized actions before they execute. It catches prompt injection attacks, unauthorized file access, data exfiltration through delegation, and off-task behavior. Scoring uses oss-safeguard-20b (20B parameter model) via OpenRouter at under 200ms median latency.
⚡ How to use agentsteer
Indexed from PyPI. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/ram-rachum-agentsteerCapabilities
Do you own agentsteer?
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.