- All languages
- ActionScript
- Assembly
- C
- C#
- C++
- CSS
- Clojure
- Common Lisp
- Crystal
- Cuda
- Dart
- Dockerfile
- Fennel
- Go
- HCL
- HTML
- Haskell
- Janet
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MDX
- Makefile
- Markdown
- Nim
- Nix
- Objective-C
- Open Policy Agent
- OpenSCAD
- PHP
- Perl
- PostScript
- Python
- Reason
- Roff
- Ruby
- Rust
- Scheme
- Shell
- Svelte
- Swift
- Tcl
- Tree-sitter Query
- TypeScript
- Vala
- Vim Script
- Vue
Starred repositories
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
flake for harbor-framework/harbor benchmark tool
Open-source IDS/IPS, WAF and bot detection for Linux, Windows, Docker and Kubernetes, with a crowdsourced blocklist of malicious IPs.
Parallel nix evaluator with a streamable json output [maintainers @Mic92, @adisbladis]
A minimalist, terminal-native coding agent written in C.
pytest plugin for distributed testing and loop-on-failures testing modes.
Run MoE models beyond VRAM on AMD, NVIDIA & Intel GPUs. Vulkan-powered, portable Windows app with automatic setup. | 让游戏显卡跑起超显存大模型,支持 AMD、NVIDIA、Intel,免安装、自动配置。只需13MB,即下即用!
Automatically build (netboot) images for NixOS [maintainer=@Mic92]
A Neovim plugin that displays difftastic's structural diffs in a side-by-side view with syntax highlighting.
Distributed, code-native issue tracker - audit workflows via time-travel
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Service runtime configuration through Terraform Providers
Jeeves – Reasoning improves Jev-like decision models
RelBench: Relational Deep Learning Benchmark
SécurixOS is a NixOS-based secure operating system tailored for small to medium-sized teams. It provides a minimal, hardened environment with strong isolation, reproducibility, and policy-driven co…
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
Generalist and Lightweight Model for Text Classification
Access large language models from the command-line
Integrate ChatGPT-style LLMs into Neovim: ask questions, keep multi-file context, pull diagnostics / command output, and chat without leaving your editor. Highly configurable, async, lua-only plugin.
runetes / maiao
Forked from adevinta/maiaoSeamless GitHub PR management from the command-line