One toolkit, one governance checklist, eight real production projects. This page is the continuous story of what it's for and who's using it.
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.
Every project below imports meerax directly, or was governed by the same checklist.
SR 11-7 & EU AI Act compliant validation suite for financial LLMs
A local-first auditing suite that automates Model Risk Management artifacts regulators require — converting raw LLM outputs into compliant evidence. Features adversarial red-teaming (50+ templates), SHAP/LIME token attribution, Financial-F1 accuracy scoring, and a YAML-based regulatory mapping registry.
Sales forecast pipeline + GenAI narrative generation
End-to-end time-series forecasting that predicts sales trends, then uses an LLM (via meerax OllamaProvider) to write plain-English summaries — bridging analyst output and executive communication. v0.1.5, meerax doctor clean, zero open PRs.
Four recommenders + a hybrid blend, explained in plain English
User-CF, item-CF, content-based TF-IDF, and ALS behind one interface with a configurable weighted hybrid, plus a GenAI layer that explains why each article was recommended. Real Precision@K/MAP@K evaluation, self-contained HTML report. v0.1.2, built entirely via subagent-driven development.
Credit-card fraud detection with explanations attached
Credit-card fraud classification paired with GenAI-written explanations for each flagged transaction, plus an AI-governance layer documenting intended use, fairness limitations, and audit trail. v0.1.1, built on meerax, shipped clean.
TensorFlow CycleGAN — unpaired image-to-image style transfer
CycleGAN retrofit on meerax adapting tensorflow_examples' hardcoded 3-channel architecture to arbitrary domains via a channel-tiling wrapper. Apple→Orange as the reference pair; extensible to any two-domain task. Full meerax project structure, CI, meerax doctor clean.
Image captioning that speaks — attention, GenAI, and real TTS
InceptionV3 → Bahdanau attention → GRU captioning trained on Flickr8k, with an LLM expanding each caption and real text-to-speech reading it aloud. The real training run surfaced and fixed two bugs no code review had caught, and a genuine evaluation-split data leak — all honestly re-reported. v0.2.0.
Multi-engine OCR benchmark with CER, F1, and audit trail reports
Production-grade OCR framework around PaddleOCR with F1 Score evaluation, Character Error Rate via Levenshtein distance, and timestamped audit trail reports. Replaces black-box OCR with auditable evidence — critical in regulated document intelligence.
In-house ML toolkit powering every project on this page
Installable Python package on PyPI. Claude/OpenAI/Ollama provider abstractions behind one interface, classification + timeseries + text eval metrics, dark-themed matplotlib plots, stratified/time splits with SMOTE, self-contained HTML report builder, and a CLI (meerax new, doctor, bump) that scaffolds and audits projects against a shared governance checklist. See the full ecosystem and live version on its own page.