Claude Code, but better: better performance, OpenAI/OpenRouter support, no telemetry, no lock-in.

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

File-backed workflow harness for reliable Claude Code and Codex sessions.

Quality gate for Agent Skills: lint, security audit, and Claude/Cursor/Codex/OpenCode compatibility.

Describe any machine in one line. Claude builds a photoreal, physics based, interactive simulation of it in one HTML file, plus the film to post it. An open source Claude Code skill.

Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions

DeepAgent Code: AI coding agent with persistent memory and control plane

A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citations.

A fully local Loveable, Replit, Bolt, v0 alternative that you can run with your own LLM. No monthly subscriptions, private by default.

Elegantly manage your MCP services

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!