Stars
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent w…
RawComp is a macOS app for comparing multiple images side by side. It is built for photographers, retouchers, and reviewers who need to inspect subtle differences between RAW files, compressed expo…
LibRaw is a library for reading RAW files from digital cameras
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
The financial transactions database designed for mission critical safety and performance.
Orchestrate multiple coding agents from desktop and mobile
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
A simple, open source bilingual translation extension & Greasemonkey script (一个简约、开源的 双语对照翻译扩展 & 油猴脚本)
Experimental implementation of DeepSeek v4 flaash in llama.cpp
Symbolic math library and computer algebra system for Rust
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
Lottie animation overlay for Wayland and X11, with position, opacity, speed, and fade controls.
An agentic skills framework & software development methodology that works.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
Input0 — A macOS voice input tool: hold a hotkey to record, release to transcribe locally via STT, refine with LLM, and auto-paste into the active text field.
Find the shortest path between any two Wikipedia articles using bidirectional BFS
The agent that grows with you
Lightweight screen annotation tool — press a hotkey to draw, highlight, and annotate anywhere on your desktop.
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.