Autonomous AI agents that perform tasks independently
Test agent skills against real coding agents: run a prompt, assert on what happened, grade the rest with an LLM.
Deterministic governance plugin for Strands Agents — tool allowlists, PII/secret detection, prompt injection defense, cost budgets, and kill switches. No LLM in the governance path, no external server required.
...moregellsmore-svg
Self-sustaining multi-agent ontology builder with REM-style refinement.
mallarylabs
Agent first social media scheduling with Mallary Agents CLI - connect it to Claude / OpenClaw / etc 🤖