Stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
Generate production-ready Lottie animations with Claude Code or Codex
ArchUnitTS is an architecture testing library. Specify and ensure architecture rules in your TypeScript app. Easy setup and pipeline integration.
JavaScript in-page GUI agent. Control web interfaces with natural language.
1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app.
Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
Universal way for ignoring unnecessary common files to fit your bundle
🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous, parallel, multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint…
💫 Toolkit to help you get started with Spec-Driven Development
Comprehensive tooling for working with OpenAPI definitions.
Breakthrough Method for Agile Ai Driven Development
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
Your First LLM-Wiki Conversation Knowledge Base
A lightning-fast boilerplate for building Adobe UXP Plugins in Svelte, React, or Vue built on Vite + TypeScript + Sass
EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation
Spec-driven development with auto-generated architecture documentation.
AirLLM 70B inference with single 4GB GPU
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
The elegant bundler for libraries powered by Rolldown
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Lightweight uptime monitor built in Rust — blazing fast, under 5 MB, self-hosted
Automated developer-oriented status page with alerting and incident support
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
AI-powered macOS development workspace. Git worktrees, Claude Code sessions, and dev servers in a single native app.