Type in Morse code by repeatedly slamming your laptop shut

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

We Have No Moat, And Neither Does Devin

Agentless🐱: an agentless approach to automatically solve software development problems

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

From the Transistor to the Web Browser, a rough outline for a 12 week course

From the Transistor to the Web Browser, a rough outline for a 12 week course

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Stream VR games from your PC to your headset via Wi-Fi

Offline version of the moonrider xr app

🌕🏄🏿 Surf the musical road among the stars. Side project built by two people in a few months to demonstrate WebXR.

A basic implementation of the Beat Saber VR game mechanic in the Godot Game Engine for Oculus Quest (and other VR headsets)

App launcher for Oculus Quest and Android TV devices with a focus on speed and flexibility. Thanks for 50K sidequest downloads!

Open source real-time translation app for Android that runs locally

A tool to detect when your YubiKey is waiting for a touch (to send notification or display a visual indicator on the screen)

A natural language interface for computers

A simple one-file way to run various GGML and GGUF models with a KoboldAI UI

Official Code for Stable Cascade

(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

Fast Multimodal LLM on Mobile Devices

Universal LLM Deployment Engine with ML Compilation

StableLM: Stability AI Language Models

LLM Analytics

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

Official repository of the xLSTM.

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

🐢 Open-Source Evaluation & Testing for LLMs and ML models

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Train LLMs on private data. Simply make an API request to our training endpoint specifying you data and model. LangDrive will handle the rest. ⚡

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.