Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Enterprise-grade AI Agent Skills for software development, DevOps, SRE, security, and product teams. Compatible with Claude Code, Cursor, Windsurf, Gemini CLI, GitHub Copilot, and 30+ AI coding agents.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

Comet: agent skill harness for turning ideas into evaluated workflows

A kit for building with AI agents and also the engineering patterns around it.

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.

A Git-native knowledge layer for your team — and a set of tool suite that keeps it alive.

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-first methods, powered by TypeScript and Bun.

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side customization adaptable for any Flutter app. Nowadays it is often called as agentic harness.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.