- All languages
- Agda
- Aiken
- Assembly
- Astro
- C
- C#
- C++
- CMake
- COBOL
- CSS
- Circom
- Clojure
- CoffeeScript
- Common Lisp
- Coq
- Cuda
- Dart
- Dhall
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Futhark
- Gleam
- Go
- Groovy
- HTML
- Haskell
- Idris
- Isabelle
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Just
- Lua
- MDX
- Makefile
- Markdown
- Mathematica
- NCL
- Nix
- OCaml
- PHP
- PLpgSQL
- Perl
- Puppet
- PureScript
- Python
- ReScript
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Scheme
- Shell
- Solidity
- Standard ML
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- V
- Vim Script
- Vue
- Wikitext
- Zig
Starred repositories
Expressions to change the world (just a tiny bit)
π OpenHands: AI-Driven Development
A clean, modular SDK for building AI agents with OpenHands V1.
π A super-optimized PureScript-to-PHP compiler, leveraging its ubiquity (70% of the web), portability, and huge ecosystem (almost official)
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsingβ¦
A statically typed programming language for scientific computations with first class support for physical dimensions and units
Conventional commits, changelog, versioning, validation
Your GitHub stats, turned into a World-Cup-style player card
β₯ AI Coding agent for the terminal β hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
30 tok/s for 20B MoE on 8 GB VRAM. Flat throughput to 32K context. Native MXFP4 + GGUF Q4_K/Q5_K/Q6_K via ggml CUDA kernels β zero dequant. Expert offloading for models that don't fit in GPU memory.
SGLang is a high-performance serving framework for large language models and multimodal models.
Official inference framework for 1-bit LLMs
Qwen-AgentWorld: Language World Models for General Agents
An MVP implementation of an accumulator in plutus over the BLS12-381 pairing curve
Herdr plugin: per-project dev layouts from .herdr/dev.toml with tunnel-URL env sync
Create and remove Jujutsu (jj) workspaces as Herdr workspaces
A Git-compatible VCS that is both simple and powerful
π€ AI-Powered MCP Server for Polymarket - Enable Claude to trade prediction markets with 45 tools, real-time monitoring, and enterprise-grade safety features
Medieval village economy simulation β up to 1000 LLM agents across multiple villages, driven by supply chains, hunger, tool degradation and market pressure.
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
A GPU-rendered terminal emulator with inline 3D graphics ππ§
the formatter multiplexer [maintainers=@zimbatm,@brianmcgee]
A script to achieve automatically following all flake inputs for Nix