https://github.com/ai-boost/awesome-harness-engineering
https://openai.com/index/harness-engineering/ - The post argues that with AI coding agents, the key skill shifts from writing code to designing the “harness”—the tools, structure, and feedback systems that let agents work reliably. Success comes from making tasks decomposable, environments well-specified, and failures fixable via better scaffolding rather than retries. The core insight is that engineers create value by shaping the system around the agent, enabling it to autonomously produce high-quality results at scale.
https://www.anthropic.com/engineering/harness-design-long-running-apps
https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
Pi is a minimal terminal coding harness.
https://pi.dev/
https://github.com/earendil-works/pi
https://github.com/disler/pi-vs-claude-code/blob/main/COMPARISON.md
https://github.com/disler/pi-vs-claude-code/blob/main/PI_VS_OPEN_CODE.md
https://www.youtube.com/@indydevdan
A coding agent with the IDE wired in. Originally built on Mario Zechner’s wonderful Pi, omp adds everything you’re missing.
https://omp.sh/
https://github.com/can1357/oh-my-pi
The open source AI coding agent
https://opencode.ai/
https://github.com/anomalyco/opencode
The agent that grows with you. The self-improving AI agent built by Nous Research. It’s the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions.
https://github.com/NousResearch/hermes-agent
https://github.com/openai/symphony
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents
Clears your inbox, sends emails, manages your calendar, checks you in for flights. All from WhatsApp, Telegram, or any chat app you already use.
https://openclaw.ai/
https://github.com/openclaw/openclaw
Deep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.
https://docs.langchain.com/oss/python/deepagents/overview
https://github.com/langchain-ai/deepagents
There’s a hard truth most people learn the hard way: the strongest model in the world will still fail on real engineering tasks if you don’t build a proper environment around it.
https://github.com/walkinglabs/learn-harness-engineering
https://github.com/walkinglabs/awesome-harness-engineering
https://walkinglabs.github.io/learn-harness-engineering/en/