Pinned Loading

1. llm-eval-harness llm-eval-harness Public

   Provider-agnostic LLM eval harness: task suites, deterministic + LLM-as-judge graders, regression gating in CI, and per-model cost & latency tracking. Local-first via Ollama; OpenAI and Anthropic s…

   Python

2. Omnia Omnia Public

   Omnia simulates a small living, breathing town of a few hundred unique agents who live and die, sleep, eat, work, earn and lose money, fall in love, marry, cheat, have children and grandchildren, g…

   TypeScript

3. Crucible Crucible Public

   A verifier-guided reasoning engine: generate many reasoning traces from a small open model, score them with a verifier (programmatic checker or a process-reward > model), and **search** — best-of-N…

   Python