GitHub Actions reporting internals for vitest-evals runs.

Hash-chained evidence ledger recording what each ADLC gate verified — agentic provenance with optional HMAC signing (C11).

TypeScript definitions for static-eval

<picture><source media="(prefers-color-scheme: dark)" srcset="./.github/banner-dark.png"><source media="(prefers-color-scheme: light)" srcset="./.github/banner-light.png"><img alt="AG Charts canvas-based charting trusted by the community, built for enterp

Web-based playground for browsing agent-eval experiment results

XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode

45 specialized judges that evaluate AI-generated code for security, cost, and quality.

Mathematical expression evaluator

The customizable admin UI for **gate** — login and permissions as a finished product. Shipped as a **Vite/React source package**, not a prebuilt bundle: your theme and your languages are applied at build time, which a finished `dist` could not do.

Statsig helps you move faster with feature gates (feature flags), and/or dynamic configs. It also allows you to run A/B/n tests to validate your new features and understand their impact on your KPIs. If you're new to Statsig, check out our product and cre

The shared wire formats of **gate**, as [Zod](https://zod.dev) schemas — consumed by [`@anchrd/gate-api`](https://www.npmjs.com/package/@anchrd/gate-api) (which builds the responses) and [`@anchrd/gate-sdk`](https://www.npmjs.com/package/@anchrd/gate-sdk)

Utility for parsing and converting ROS Xacro files in Javascript.

CrewHaus — the meta-harness compiler for AI agents. Compile one crewhaus.yaml spec into a CLI agent, channel bot, RAG pipeline, multi-agent crew, eval harness, voice or browser agent, and more.

**gate** — login and permissions as a finished product. A Cloudflare Worker holds the logic, [D1](https://developers.cloudflare.com/d1/) holds everything as data. Deployable per customer, steerable from the outside over **REST** and **MCP**.

Official CLI for the hosted Taplid audit API.

Universal subprocess executor for plurnk-service's exec scheme — one package exposing the shell + node + python floor plus whichever host interpreters (perl, ruby, php, lua, awk, bc, …) are present.

Core: buyer-side x402 trust gate. Free TWZRD preflight (ReadinessCard) before signing USDC to any merchant, with optional $0.001 paid trust escalate on warn — blocking spend on bad intel, no human in the loop. Optional: createTwzrdSettleGuard for resource

Element descriptors and matchers for @boundaries tools

JSON Eval RS for bundlers (Webpack, Vite, Next.js, etc.) with ergonomic API

Portable pieces of Auden's evaluation path — command redaction, the LLM adapter seam, and guide normalization.