Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session i...
#ai-agents
2962 posts
Drive a GNOME Wayland desktop from AI agents. CLI-first, no portals, no consent dialogs.
Open source multi-agent harness for orchestrating AI workers. Supports Claude Code, OpenAI Codex, Cursor Agent, and local models.
The pixel-art studio agents can see — layered, animated, game-ready art over MCP. One binary, no keys, fully deterministic.
Turn any website into a CLI/API for AI agents
Ultra-fast file search toolkit for AI agents, Neovim, and code editors. MCP server for Claude Code/Cursor/Codex, frecency-ranked search, sym...
AI investigative journalism toolkit — OSINT, FOIA engineering, corporate veil piercing, libel defense, and editorial workflow. 15 skills for...
MCP server that surfaces coherence, governance, and safety primitives: Wave/Bump validation, ATOM trail + gates, .context.yaml packing, AWI...
A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Cla...
🛫 Self-driving SEO for AI coding agents — pulls real Google Search Console data, fixes Google-recommended issues in a safe branch, verifies...
AI campaign orchestrator for drug discovery that plans with OpenClaw and executes Refua MCP tools, including autonomous loops and portfolio...
File-first, patchable Agent Skills for heavy MCP tools