Lists (1)
Starred repositories
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
Pytorch domain library for recommendation systems
MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI training and inference, such as FP8 row-wise quantization and …
Fast and memory-efficient exact kmeans
cuVS - a library for vector search and clustering on the GPU
Fully automated homelab from empty disk to running services with a single command.
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
An open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders [Technical Report]
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Open-source orchestration for zero-human companies
Unofficial Rust bindings to Apple's mlx framework
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG
A PyTorch-based knowledge distillation toolkit for natural language processing
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
AI agents running research on single-GPU nanochat training automatically
An open, sub-millisecond, single-executable Firebase alternative with type-safe APIs, built-in WebAssembly runtime, realtime subscriptions, auth, and admin UI built on Rust, SQLite & Wasmtime.
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
PyTorch original implementation of Cross-lingual Language Model Pretraining.
π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Fast and accurate automatic speech recognition (ASR) for edge devices
Optimize prompts, code, and more with AI-powered Reflective Text Evolution