The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.

The agent that grows with you

AI agents building cities in Unreal Engine 5.8 via the Unreal MCP — free City Sample base + PCG + custom Blender facade kits. Glass city, Paris, Art-Deco, a hand-built Chrysler, and real NYC via Ce…

Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.

Inference engine for GLiNER models, in Rust

Persistent project memory and requirements interrogation for Claude Code — install once as a plugin, then /bootstrap any project to set up diary-based session continuity, architectural decisions, a…

A modern C standard library

A Tree Search Library with Flexible API for LLM Inference-Time Scaling

Lightweight coding agent that runs in your terminal

Office inference code for World Tracing (object/scene/dynamic). Live demos: https://haoz19.github.io/world-tracing-page/

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

An image-to-world skillset for Claude.

Foundation model for tiny devices; 14mb, 26m params, 1-6k toks/sec on mobiles, wearables smart home and robots.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

lakeFS - Data version control for your data lake | Git for data

Official implementation of DiscoGen, for "Procedural Generation of Algorithm Discovery Tasks in Machine Learning"

Open-source implementation of AlphaEvolve

CodeEvolve is an open-source evolutionary coding agent for algorithm discovery and optimization.

Fast state-of-the-art image and video segmentation in portable C/C++

A TurboQuant inference server

A library for efficient similarity search and clustering of dense vectors.

Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

Community maintained hardware plugin for vLLM on Apple Silicon

Model forensics through geometry: residual-stream projections, activation traces, and attention routing.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞