
SafeFence
RBAC & Guardrails for OpenClaw
By Douglas Sim·Security·10h ago
AIDeveloper ToolsOpen Sourceproject
**Experimental -- This project is under active development and not yet production-ready. APIs, config schemas, and behavior may change without notice between releases.** Deterministic security guardrails for OpenClaw AI agents. A 12-detector pipeline that evaluates every agent action locally in sub-millisecond time -- no remote inference, no runtime dependencies. Optionally connects to a centralized control plane for multi-instance policy sync and audit aggregation.
Discussion (2)
Sign in to join the discussion.
Page 1 of 1
SafeFence
4 upvotes