Awesome Agent Harness

Awesome Agent Harness collects tools, frameworks and resources for what it calls agent harness engineering, the discipline of building the infrastructure that wraps around an LLM coding agent: session management, context delivery, tool design, architectural enforcement, failure recovery and human oversight. It draws its core principles from two sources it cites directly, OpenAI's harness-engineering writing and Anthropic's Claude Code tool-design writing, and states eight core principles drawn from them, including that humans steer while agents execute, that repository knowledge is the system of record, that an AGENTS.md file should point to deeper sources rather than contain everything, and that fewer, more expressive tools beat a long menu of narrow ones.

Its contents are organized into full-lifecycle platforms, agent orchestrators, task runners, agent-harness frameworks, agent runtimes, agent knowledge and memory tools, and coding agents.