NeuraLiying/Awesome-Agent-Harnesses
Curated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.
GitHub repository with 51 stars and 9 forks.
Topics: agent, agent-loop, agent-loop-harness, agentic, ai-agents, awsome-list, context-engineering, harness, llm, multi-agent