{"id":"aiming-lab-metaclaw","name":"MetaClaw","af_score":41.2,"security_score":42.5,"reliability_score":31.2,"what_it_does":"MetaClaw is a local proxy/agent runtime that sits in front of a user's personal agent (e.g., OpenClaw/CoPaw/etc.) and an OpenAI-compatible LLM API. It injects “skills” into prompts, can summarize sessions into new skills, and (optionally) runs asynchronous RL-style training (e.g., GRPO) on accumulated interaction data. It also includes a scheduler mode (madmax) to defer weight updates to idle/sleep/meeting windows and provides an Anthropic-compatible /v1/messages endpoint for Anthropic-native clients. A CLI (metaclaw) manages setup, config.yaml, starting/stopping, and daemon logging.","best_when":"You want a locally hosted, agent-proxy workflow to continually evolve skills from live conversations, and you’re comfortable with CLI-driven setup and optional training dependencies/backends (Tinker/MinT/Weaver).","avoid_when":"You need strong enterprise controls (RBAC, audit logs, strict policy enforcement) and a formally documented REST API with stable schemas; or you cannot permit the tool to patch other agents’ configuration files and restart local services.","last_evaluated":"2026-03-29T18:05:45.810351+00:00","has_mcp":false,"has_api":true,"auth_methods":["API key for the underlying LLM provider (configured via metaclaw config / setup wizard)","Proxy api_key configured for local client calls (example shows api_key: metaclaw)"],"has_free_tier":false,"known_gotchas":["Acts as a local proxy; local networking and port availability must be correct.","Service/config patching for many 'claw_type' agents may require permissions and OS-specific service control (systemctl/launchctl).","Anthropic-compatible endpoint (/v1/messages) behavior depends on correct routing/base URLs for Anthropic-native clients.","RL/training backend choice (tinker/mint/weaver) requires extra packages and credentials; misconfiguration may break training even if skills-only mode works."],"error_quality":0.0}