DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Raft source-available release mirror. One snapshot commit per release; pull requests are not accepted.

Reproducible Microduck RL experiments, policies, simulation assets, and hardware add-ons

DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe

Turn any open model into a classifier/jev endpoint

Microduck 复刻 · 从官方 MJCF 与 Rust 源码反推出的装配图、CAD 装配体与完整电控方案 | Mechanical + electronics reconstruction of Pollen Robotics' Microduck

Train RL policies for the Pollen Microduck 🦆 on an ordinary Mac, no CUDA GPU, and watch them learn live in the browser.

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

Spot Micro Quadripeg Project

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.

A Nixpkgs module system usage pattern

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

Simplifying reinforcement learning for complex game environments

Democratizing Reinforcement Learning for LLMs

Open-source implementation of AlphaEvolve

NanoGPT (124M) in 3 minutes

Awesome Deep Research list

🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"

A bibliography and survey of the papers surrounding o1

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dat…

High accuracy RAG for answering questions from scientific documents with citations

Reachy 2023 workspace

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

UNet diffusion model in pure CUDA

LLM training in simple, raw C/CUDA