Open-source coding-agent harness you can actually change — own the loop (prompts, gates, routing, skills, terminal states), use any model, run long tasks while you're away.

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.

Portable multi-agent harness for .agents-based skills and workflows across Antigravity, Claude Code, Codex, OpenCode, and more

Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local & read-only.

An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.

AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.

🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.

Drive the Pi coding agent from Claude Code or Codex: multi-model review panels, model racing, incremental & sharded reviews, automatic model fallback, /pi:rescue with parallel subagent fan-out. Any provider (DeepSeek/OpenAI/Anthropic/local). Adapted from codex-plugin-cc.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Claude Code plugin & Agent Skills for AI-native development: codebase readiness scoring (/assess), Six Thinking Hats deliberation (/huddle), AI-slop removal (/deslop), skill hardening (/skill-forge), and more.

Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.

Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and knowledge distillation

Coordinate AI coding agents in shared cubes. Works with Claude Code, Codex, and OpenCode.

Planner/Generator/Evaluator orchestration harness for Claude Code (and Codex)

Supercharge your AI agents by versioning, tracking, and merging overlapping skills.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.

CVE hunting harness for Claude Code - 20 skills, 5-agent team, systematic vulnerability research with false positive elimination

TOGA Technology Team Claude Knowledge System — shared AI coding harness with skills, knowledge base CLI, and project installer for Claude Code.

27 FREE Professional and Comprehensive Business Strategy Skills for Claude Code; with intelligent context chaining, skill iteration, terminal charts and HTML visualization options.

The agent harness for offsec. It's a plugin for Claude Code packed with skills, hooks, memory system that works best for using Claude Code to achieve autonomous pentest/ctf