🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Kand: Blazing-Fast, Modern Technical Analysis in Rust, Python, and WASM.

Fast and memory-efficient exact kmeans

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

🚀 The Fastest Chunker in the West 🇺🇸 Upto 1TB/s "semantic" chunking, quick and easy!

Open-source Agent Operating System

Build your agent team in OpenClaw with one command.

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

Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archite…

Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite

Unified Emacs interface supporting OpenAI Codex, GitHub Copilot CLI, Claude Code, Gemini CLI, Opencode, and more

Logly is a Rust-powered, Loguru-like logging library for Python that combines the familiarity of Python’s standard logging API with high-performance logging capabilities.

Muon is an optimizer for hidden layers in neural networks

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

An open-source coding agent for the Grok API

A curated list of 100+ libraries and frameworks for AI engineers building with LLMs

A GitHub Action invoking the Gemini CLI.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

AlphaGo Moment for Model Architecture Discovery.

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

The simplest, fastest repository for training/finetuning small-sized VLMs.

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)