Less skills. Deeper connections. A lean, interconnected skill ecosystem for Claude Code.

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

lnwjud — local AI-agent runtime & MCP gateway

Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

Claude Code rewritten in Go.. High-performance AI agent harness runtime in Go. MCP server, CLI tool orchestration, session management, Kiro integration. Single binary, zero dependencies.

Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

🥷 Engineering habits you already know, turned into skills Claude can run.

Domscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them

Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.

Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, no runtime.

Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.

Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cursor and more on your own machine, then replies in-thread with verified, evidence-backed results.

An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.

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.

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

Agent skills for fallow, codebase intelligence for TypeScript and JavaScript. Teaches AI agents how to find unused code, duplication, circular deps, complexity hotspots, architecture drift, design-system drift, and (with Fallow Runtime) hot-path and cold-path evidence. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.

Cross-language-safe code-intelligence MCP for AI agents -- 13 languages, family-gated call graph (CodeGraph 745 vs TSA 6 cross-language mis-wires, v1.21.0 same-session -- ~124x by count, ~390x by rate; re-verifying vs current develop). Run miswire-audit on your repo. 8 facade tools, TOON output, 100% local. Python.

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.