A Python framework for recursive harness optimization that refines the prompts, tools and orchestration around a fixed LLM agent on unseen tasks.
9.2K802PythonApache-2.0Updated 6 days ago
#benchmarks
Open-source projects tagged “benchmarks”
Curated GitHub repositories related to benchmarks, with AI summaries and key stats.
Sort:Recently added
2 repositories
Companion code repository for the book AI Agents: The Definitive Guide, with Jupyter notebooks covering agent patterns, tooling, evaluation, memory, and security.
2.8K538Jupyter NotebookNo licenseUpdated 3 months ago