extract the mentions in a ssb message, just using the markdown. this is _mostly compatible_ with the way patchwork does it. but simpler, because it relies only on the markdown.
A simple TypeScript runner --------------------------
Mailwoman neural-classifier weights for locale 'fr-fr'. Data-only package — loaded by @mailwoman/neural at runtime.
Canonical diagnosis prompts + Zod Diagnosis schema + pure eval-metrics for the reactlens / nativelens AI failure-diagnosis loop. Pure helpers only — no LLM SDK dep.
Super handy eval of anything
Read node.js file and eval it
Extend some standard functionality of JavaScript: Arrays, Strings..
> Compiler for ngx-translate that uses messageformat.js to compile translations using ICU syntax for handling pluralization and gender
This is the parser and evaluator used in the basho project. For documentation see https://www.github.com/jeswin/basho.
Agent evaluation framework — prove whether agent changes improved outcomes with reproducible evidence.
Convert math expressions between postfix (RPN) and infix notations and evaluate them
Mailwoman neural-classifier weights for locale 'en-us'. Data-only package — loaded by @mailwoman/neural at runtime.
Query json with jsonpath expressions
AI/LLM integration for the Kaiord health & fitness data framework
Autonomous SWE agent — triage and fix issues from Sentry, Asana, Linear, and Jira with Claude
Core types, schemas, and domain models for RAG evaluation
Read-Evaluate-Print-Loop environment for JavaScript
An ESLint® plugin that detects and mitigates security-related issues for DevExpress projects.
Multi-provider skill evals with integration mocks
Parse makefiles
Mathematical expression evaluator
unirtm binary for Linux x64
Static obfuscation detector for npm lifecycle scripts — supply chain attack prevention
Evaluate numerical expressions