Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.
- architecture-review
- code-quality
- code-review
- tech-debt
47,133 repositories indexed
1–10 of 10 · Most stars
Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Desktop app for game dev with AI: make games in Unreal Engine, Unity, Godot or the browser. The agent sets up the engine, builds your game and play-tests it by itself.
Oracle3: open-source trading engine and MCP server for prediction markets. Finds fee-adjusted no-arbitrage violations across related event contracts and trades them live on Kalshi, Polymarket and Solana, or on paper, under pre-trade risk limits. 13 MCP tools, JSON CLI, agent skills, 600+ tests.
50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.
An auditable, reversible, evaluable local agent runtime that turns feedback into skills — and ships them only when evidence and tests say so.
An agent skill that makes videos in pure code — narrated explainers and product promos in 32 visual styles (whiteboard, ink-wash, shadow puppets, pixel art, isometric worlds, movie trailers, manga, animated maps, Swiss kinetic type, blueprints, paper collage, Bayeux tapestry, stick-figure parables, pencil tests, pen-drawn worlds…), 16:9 and 9:16.
Scalable, stateless selenium, playwright, devtools, mpc hub for Kubernetes cluster