Stars
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Zero-copy, content-addressed Rust build cache for Rust, C/C++ and more. No copies, no wasted disk — just hardlinks locally and S3 for sharing.
IP addresses break, dial keys instead. A library that adds QUIC + NAT Traversal to your apps.
Fast, lossless LLM inference via dual-view diffusion decoding.
1M-context DeepSeek-V4-Flash inference on NVIDIA Blackwell using sglang and SSD KV cache offload.
A modern port of Turbo Vision 2.0, the classical framework for text-based user interfaces. Now cross-platform and with Unicode support.
The best-benchmarked open-source AI memory system. And it's free.
Self-hosted, semantically-connected personal knowledge base
Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server for Claude, Cursor and Devin, SQL no…
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
A high-performance, pure Rust toolkit for standardizing and preparing biomolecular systems (proteins & nucleic acids). It heals missing atoms, resolves protonation states, adds solvation, and unifi…
io_uring based bittorrent client built for modern Linux kernels
x86 PC emulator and x86-to-wasm JIT, running in the browser
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
OpenAI Whisper ASR Webservice API
World's first AMD NPU driver for TUXEDO laptops - Enable AI acceleration on Linux
A simple, fast, and secure operating system for the cloud.
Democratizing large model inference and training on any device.