- Toronto / Hong Kong
Stars
- All languages
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Coq
- Crystal
- Cuda
- Emacs Lisp
- F#
- Fennel
- Fortran
- Go
- Go Template
- HCL
- HTML
- Haskell
- Idris
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Koka
- Kotlin
- Lua
- Makefile
- Markdown
- Motoko
- Nix
- OCaml
- Objective-C
- Perl
- Pony
- PowerShell
- Python
- QML
- ReScript
- Reason
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Standard ML
- Svelte
- Swift
- Tcl
- TeX
- Tree-sitter Query
- TypeScript
- Vala
- Vim Script
- Vue
Background Music, a macOS audio utility: automatically pause your music, set individual apps' volumes and record system audio.
Awesome Logseq resources created by the community <3
A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://logseq.io/p/NX4mc_ggEV
SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression
💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.
collama.nvim is a Neovim plugin that leverages Ollama to provide source code completion capabilities similar to GitHub Copilot.
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon
ekryski / mlx-swift-lm
Forked from ml-explore/mlx-swift-lmLLMs and VLMs with MLX Swift
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…
AirLLM 70B inference with single 4GB GPU
TheTom / llama-cpp-turboquant
Forked from ggml-org/llama.cppLLM inference in C/C++
Free, public API for an independent stock market Fear & Greed Index. No API key required. CORS enabled.
The agent that grows with you
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
A high-performance backtesting framework combining the speed of Rust with the ease of Python. Built for quantitative traders, researchers, and financial institutions who need reliable, fast, and co…
Official inference framework for 1-bit LLMs
RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.
A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
li-nkSN / zio-quill
Forked from zio/zio-quillCompile-time Language Integrated Queries for Scala
li-nkSN / zio-protoquill
Forked from zio/zio-protoquillQuill for Scala 3
Modeling language for Mathematical Optimization (linear, mixed-integer, conic, semidefinite, nonlinear)