MiMo Code: Where Models and Agents Co-Evolve

LLM-as-judge completion plugin for tagma-sdk pipelines

Runtime asset loader and manifest for the WerewolfJudge web app — fonts, audio sprites, and image bundles

Tiny runtime assertions that preserve error messages in production.

A generic boolean/predicate condition engine: schema, evaluate, walk.

Shared internals for Constructive PostGraphile v5 plugins - PgCondition query-builder walker and pg-resource introspection helpers

Uses export conditions to return environment information in a way that works with major bundlers and runtimes.

Autonomous agent team harness — coordinate a lead and participant agents in one async session, with eval, benchmark, and trace tooling to prove the changes worked.

No description provided.

utilities for observable asynchronous control flow

looprun eval harness: run a generated subject's cases against a model target (governed or ungoverned variant), dump per-case traces for the LLM judge, fold verdicts, and certify against the bar.

Statsig Node.js SDK for usage in multi-user server environments.

Retry and fallback mechanisms for AI SDK

Warning utility for WordPress.

better fetch for Node.js. Works on any JavaScript runtime!

LLM-powered judge for opencode - blocks file modifications without explicit user permission

Super-simple invariant function

A document-template marker and condition engine: {{...}} marker grammar, parse, compute, serialize, field values.

🐊Putout plugin adds ability apply if condition

Checks CircleCI environment before publishing successful build using semantic-release