meerax

Every project on this page needed the same handful of things: an LLM provider it could swap between Ollama, Claude, and OpenAI without rewriting call sites, honest evaluation metrics, a report someone non-technical could actually open, and a way to know a repo hadn't drifted from the standards the last one shipped with. Building that once, well, and reusing it turned out to be far more valuable than the models themselves — meerax is that shared foundation, not a demo library.

Every repo here follows the same discipline: a design gets written down before any code does, an implementation plan breaks it into reviewed pieces, and — critically — nothing ships on a per-piece review alone. The broad, whole-project review that runs last is the one that has caught every genuinely serious bug in this ecosystem so far: a schema mismatch in NewsCompass's data pipeline, a training loop in EchoSight that silently stopped learning after one epoch, a beam search that could loop forever, a data-leakage bug in an evaluation split that made an early result look better than it was. None of those were caught by testing one piece in isolation — they only showed up when something ran for real, end to end, against real data.

That's the actual philosophy: run it for real before calling it done, report the real number even when it's an unglamorous one, and fix what a broad review finds instead of letting a narrow pass wave it through. meerax doctor checks the mechanical parts of that — a GOVERNANCE.md, a changelog entry, pinned dependencies — every project below passes it before release.