awesome-harness-engineering
View on GitHub🛠️ Awesome tools & guides for harness engineering.
A curated collection of guides, benchmarks, specifications, and open-source projects for making AI agents more reliable. Covers context and memory, evaluation, observability, safe autonomy, coding-agent harnesses, and runtimes.
Use Cases
Design reliable coding-agent workflowsManage context and memory for long-running agentsEvaluate agent performance and behaviorAdd guardrails and safe execution boundariesCompare agent runtimes, harnesses, and benchmarks
Built With
- Frameworks
- LangChain · OpenHands
Tags
agent harnesses · harness engineering · coding agents · context engineering · agent evaluation · observability · safe autonomy · multi-agent systems · benchmarks · curated resources