Reactive LLM eval, tracing, and regression layer as a Convex component.

A simple online judge for Jupyter Lab.

Evidence-driven /until-done goal loops for Pi with TDD planning, mise verification, and mandatory LLM judge gating.

Batch matrix runtime for Gaunt Sloth (BATCH-1): run a prompt-executable over a matrix of models and/or content-bound inputs

Property descriptor factory

NxNxN cube puzzle simulator

Authoring kit for HomePages marketing-section templates: schema system, contract primitives, theme tokens, and the design-system CSS layer.

Automatically append `content` property for viewport-units-buggyfill

Executable evidence for regressions introduced during Codex-assisted development.

The reference `ust` CLI for UST (Universal State Transcript) 1.0 — verify a transcript, print canonical bytes for cross-language diffing, and run the HIGH genesis ceremony. One entrypoint; the Go binary reproduces this surface.

Playwright reporter that classifies test failures with an LLM (real bug / flaky / selector drift / environment issue) and posts a readable summary to stdout, a GitHub PR comment, or Slack.

Maestro Frontier is an opt-in, zero-dependency local multi-CLI fusion engine for AI coding agents. Compose an Opus 5 and Codex model panel, set provider-supported effort, judge its one-shot read-only responses, and synthesize one grounded answer. Optional

CLI for operating agents on the Introspection platform

Multi-model deliberation for pi, inspired by OpenRouter Fusion

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

fusionkit — real model fusion behind your coding agent (Codex, Claude Code, Cursor, OpenCode).

A small library to print colourful messages.

The webappwiz CLI: judge code against rules, sign off a diff, and manage agent skills

   ![LLM Audit](https://img.shields.io/

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance