Stars
Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.
💫 Toolkit to help you get started with Spec-Driven Development
A vector index built on TurboQuant, written in Rust with Python bindings
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.
Framework for evolving code and prompts inspired by Darwinian evolution
Fast, lossless CPU inference for PP-OCRv6 OCR (detection + recognition) via OpenVINO — 2-4x over native PyTorch, no GPU.
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
A fast, helpful, and open-source document parser
Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows.
An open source multi-tool for exploring and publishing data
The most atomic way to train and inference a GPT in pure, dependency-free C
Review-first terminal diff viewer for agentic coders
Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
Liquid Audio - Speech-to-Speech audio models by Liquid AI
Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK
GitHub Quick Review: Evaluate your enterprise and organizations against GitHub best practices
The best-benchmarked open-source AI memory system. And it's free.
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
Token compression proxy for Claude Code. 50% fewer tokens, zero behavior change.
The component library that feels like something. 73 elements, 20 themes, 230+ blocks. Drop in, ship.
AI agents running research on single-GPU nanochat training automatically
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Self-hosted web UI for Claude and Codex. Push notifications, file uploads, no accounts, no database. Uses your existing CLI session history.