DMI: A decoupled, asynchronous observation substrate for high-speed LLM inference.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

Native macOS menu-bar tracker for GitHub Copilot CLI + VS Code Copilot usage — runs 100% locally, no telemetry

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

https://hf.co/hexgrad/Kokoro-82M

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Visualize Your Ideas With Code

Drop-in Acceleration of SQL/PromQL queries

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.

Agentic review of Linux Kernel code changes

An LLM-friendly Educational RISC-V Operating System

Universal memory layer for AI Agents

An Open Source implementation of Notebook LM with more flexibility and features

Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

Create beautiful slides on the web using a coding agent's frontend skills

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Run frontier AI locally.

Rust virtual machine and JIT compiler for eBPF programs

eBPF verifier based on abstract interpretation

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

Specula: An agentic tool for finding deep bugs in system code using TLA+

Slids of CLK2025, vivo, ShenZhen

NVIDIA Linux open GPU kernel module source

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Fancy stream processing made operationally mundane. This repository is a fork of the original project before the license was changed.

The evaluation benchmark on MCP servers

WaferLLM: Large Language Model Inference at Wafer Scale