Stars
JIT and AOT compiler for the Ethereum Virtual Machine, built on Revm.
An Android recovery written in Rust from scratch: decryption, installs and OTA updates, backup, WLAN, MTP, adb and fastbootd. Runs the phone's own drivers and services from its stock firmware.
A minimal base OS for Anbernic RG XX devices. 4 sec boot time.
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
Tool for automatic PS5 executables porting to Linux and Windows
A background-first macOS voice input tool. Press a hotkey, speak, and the corrected text is pasted into whatever app you're using.
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
PocketJS: create UI on every screen you love. JavaScript components drawn as native pixels on handhelds, desktops and embedded screens.
Everything I know about running LLMs locally
AI 模型随机数分布指纹数据集 — 17 模型 / OpenRouter / 含原始响应与相似度分析
Modular CSS Library that brings the beauty of Terminal UIs to the browser
A vector index built on TurboQuant, written in Rust with Python bindings
Monorepo for @juicesharp/rpiv-* Pi plugins (lockstep versions, single install, single publish pipeline)
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)
Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.
Lucebox inference engine for heterogeneous hardware & consumer GPUs
Open source, cloud native, Postgres platform with copy-on-write branching and scale-to-zero
arnavgr / termux-nf
Forked from getnf/getnfA better way to install NerdFonts on Termux
WeBot — Push notifications to Weixin. Like Bark, but inside Weixin — no extra app needed.
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
EFI boot entry management as an KDE Configuration Module
Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.
A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC
Nix packages for AI coding agents and development tools. Automatically updated daily.
A fast, spec-compliant WebAssembly runtime written in Zig