Search

No description available

Anti-AI-slop quality checker — 58 slop-test gates as an interactive HTML checklist

Stable UI foundation for React Native and React Native Web.

Sigigo L2 thin wrapper — automatic ai_act.* evidence capture for OpenAI / Azure OpenAI chat completions

Fire-and-forget LLM spend capture for Metergraph

AI Cost Intelligence for LLM inference — track and enforce your LLM spend in-process, across providers.

LLM-powered document generation from data sources and templates

A simple Ray + vLLM + FSDP2 (AutoTP/EP/CP) stack for SFT and RL.

No description available

Cut LLM costs in your AI app and coding agents. On-device detection of wasted tokens (redundant calls, stuck loops, oversized + uncached context) with copy-paste fixes. Local-first, values-free.

konsistent is a CLI tool that enforces structural conventions in TypeScript codebases.

Test generation skill framework for AI IDEs, following the test pyramid methodology. Provides /khufu-ut, /khufu-it, /khufu-api, and /khufu-e2e skills.

Agent-composed Strudel radio: a bun server + prebuilt browser player you run with `bunx beats-radio start`.

A motion-review Claude Code skill with ten non-negotiable standards derived from Emil Kowalski's design engineering philosophy — default to flagging, approval is earned. npx installs it into .claude/skills.

Cross-harness skill usage auditing with Chinese Markdown reports

Refinery - Codex-first source review CLI.

OpenHands automation CLI that distills coding-session transcripts into a repo's AGENTS.md via Letta reflection

A terminal coding agent that runs on sable (sable.rotur.dev).

C2PA manifest embedding for AI/ML model container formats: GGUF, SafeTensors, and ONNX

Multimodal source investigation CLI for web, repositories, and visual media.