Audit your codebase for wasted LLM API spend, priced against the live IFX inference-cost index.

Deterministic local eval utilities for AgentInspect traces

Web Codegen Scorer is a tool for evaluating the quality of web code generated by Large Language Models (LLMs).

Convenience wrapper for Redis EVAL/EVALSHA

Gate AI-proposed infrastructure changes from the terminal or CI: deterministic policies, honest exit codes, hashed receipts. The gate itself never calls a model.

TypeScript SDK and CLI for evaluating agentskills.io-style AI agent skills with LLM judges, baseline comparison, YAML config, JSONL logs, and HTML reports.

GitHub Actions release gate that batches packtory publishes by waiting for repository activity to settle.

Camera Kit Web

JSON Eval RS core JavaScript wrapper (internal package - not published)

Terrain test intelligence CLI.

Process transparency for agentic work.

CLI for installing qq-radio skills into Codex, Claude, and Cursor on Windows.

Evaluate operations in a scope while retaining resources across evaluations

Fitness scoring and LLM evaluation for functional TypeScript codebases using the functype ecosystem

Multi-agent swarm coordination for OpenCode with learning capabilities, beads integration, and Agent Mail

No description provided.

Diagnostics and project bootstrap helpers for the codex-agent plugin.

Load a string as if it was an esm or commonjs module with a given filename.

GitHub Actions reporting internals for vitest-evals runs.

A tiny, safe, fast JavaScript library for decimal arithmetic expressions.