{"repo":"SafeAI-Lab-X/ClawKeeper","free":true,"listed":false,"github":"https://github.com/SafeAI-Lab-X/ClawKeeper","clone":"git clone https://github.com/SafeAI-Lab-X/ClawKeeper.git","description":"ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)","language":"TypeScript","stars":1022,"topics":["agents","openclaw","plugins","safety","security","skills"],"license":null,"category":"security-tools","readme_excerpt":"ClawKeeper Host-agnostic safety middleware for tool-using agentic systems (can be wired into Hermes Agent, MCP tools, HTTP bridges, OpenClaw-style runtimes, or a custom host). ClawKeeper sits between an agent and its tools. It can block risky tool calls, redact sensitive tool results, remember recurring attack patterns & self improve guardrail layers, and delegate harder trajectory-level decisions to an external Watcher. What it is for - Guarding shell, Python, browser, filesystem, and network tool calls before execution. - Catching common agent-security failures: prompt injection, credential reads, credential exfiltration chains, unsafe shell execution, protected-path access, SSRF-like URLs, encoded second-stage payloads, and poisoned tool output. - Running a host-independent Judge API for non-Python adapters. - Running an optional Watcher daemon that reasons over intent, recent tool history, deterministic findings, and proposed tool calls. - Self-improving guard coverage: Watcher catches can synthesize learned patterns, persist them under /.clawkeeper/ , and hot-reload them into the live guard layer. Install Sanity check: Use with Hermes Agent This installs the default pre-tool guard chain and post-tool-result scanners. No Hermes patching is required. Run the HTTP core For hosts that cannot import the Python package directly: Useful endpoints include /v1/judge , /v1/event , /v1/audit , /v1/scan/logs , /v1/scan/skill , and maintenance harden/rollback routes. Run the Watcher ","default_branch":null,"files":null,"tree":[],"storefront":"/r/SafeAI-Lab-X","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/SafeAI-Lab-X/ClawKeeper/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}