Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Scalable toolkit for efficient model reinforcement

Auto-archived text logs of Nous Research Discord channels (polled every 6h)

vet is a command-line tool that acts as a safety net for the risky curl | bash pattern. It lets you inspect, diff against previous versions, and lint remote scripts before asking for your explicit …

Evaluate and improve models and agents using environments

Training API and CLI

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chem…

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

A minimum time simulation for constructing dyson spheres

Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.

An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.

The agent that grows with you

Tools for the simulation and analysis of circadian rhythms

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

Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

A Next-Generation Training Engine Built for Ultra-Large MoE Models

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Expert Parallelism Load Balancer

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

Real-time terminal monitor for InfiniBand networks - htop for high-speed interconnects

LLM Council works together to answer your hardest questions

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

ring-attention experiments

A high-performance kernel library for LLM training

- Made for the 2025 AMD inference sprint - A collection of high-performance Triton kernels designed to accelerate state-of-the-art deepseek models on AMD GPUs.

Primus-SaFE(Stability and Fault Endurance)

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…