Stars
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
DFlash: Block Diffusion for Flash Speculative Decoding
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClient, Hermes, or DIY Python — and keeps its knowledge…
A terminal multiplexer and user interface (TUI) with a super-powerful agent. Tamux is the only agent runtime that treats the daemon like an operating system kernel – sessions, targets, memory, mana…
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Production-grade engineering skills for AI coding agents.
A fast, helpful, and open-source document parser
OpenTUI is a library for building terminal user interfaces (TUIs)
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Agent Lattice: a knowledge graph for your codebase, written in markdown.
Terminal emulator library for the BEAM — libghostty-vt NIFs with OTP integration
Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
Complete Raft consensus algorithm implementation in Elixir
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Library that fixes problem of losing state on LiveView reconnects
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Spec-driven development (SDD) for AI coding assistants.
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
Open source implementation of Apple's SwiftUI.
Semantic code search and targeted edits for local repositories, all done locally (no cloud).
Open-source AI hackers to find and fix your app’s vulnerabilities.
WSGI/ASGI HTTP server powered by the BEAM. Mix the best of Python (AI, web apps) with Erlang (distribution, concurrency, resilience).
NanoSpeech: a custom modification-aware basecaller
Beginner, advanced, expert level Rust training material
Compile Rust to WebAssembly, run it in users' browsers, and communicate with it from Phoenix LiveView.
