Nous Research 的公共 GitHub 足迹

The agent that grows with you

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company

此仓库未提供描述。

Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

An autonomous novel writing pipeline, by Hermes Agent

Distributed Training Over-The-Internet

Autoresearch for subjective domains.

A comprehensive repository of reasoning tasks for LLMs (and beyond)

此仓库未提供描述。

Maybe the new state of the art vision model? we'll see 🤷‍♂️

AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.

此仓库未提供描述。

Modular Agentic AI Architecture - NousResearch x Teleport (Flashbots)

Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)

Make abliterated models with transformers, easy and fast

此仓库未提供描述。

此仓库未提供描述。

此仓库未提供描述。

A PyTorch native library for large model training

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Generative Agents: Interactive Simulacra of Human Behavior - with Local LLMs

Implementation of Contrastive Neuron Attribution for behavioral detection and steering.

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

此仓库未提供描述。

Example plugins for hermes-agent — reference implementations and documentation companions, not bundled with the core repo.

Simple demo showing how to use the Forge API by Nous Research

Build RL environments for LLM training

此仓库未提供描述。

此仓库未提供描述。

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

OpenShell is the safe, private runtime for autonomous AI agents.

Scalable toolkit for efficient model reinforcement

此仓库未提供描述。

Minimalistic large language model 3D-parallelism training

Offline probe-based evaluation harness for hermes-agent's ContextCompressor. Methodology adapted from Factory's Dec 2025 'Evaluating Compression'.

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Go ahead and axolotl questions

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

⛓️ build cognitive systems, pythonic

A prototype Kotlin LLM library.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Nous Research's experimental LLM story generator

DeepEP: an efficient expert-parallel communication library

LLM inference in C/C++ - nous research

peer-2-peer that just works

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

此仓库未提供描述。

OpenShell is the safe, private runtime for autonomous AI agents.

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

Rust bindings for the C++ api of PyTorch.

此仓库未提供描述。

The frontend for Nous Research's experimental LLM story generator.

solana geyser grpc service

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

此仓库未提供描述。

Ongoing research training transformer models at scale

此仓库未提供描述。

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

Blobs layer for iroh

此仓库未提供描述。

此仓库未提供描述。

🌈 React for interactive command-line apps

Awesome autocompletion, static analysis and refactoring library for python

Efficient Triton Kernels for LLM Training

A high-throughput and memory-efficient inference and serving engine for LLMs

此仓库未提供描述。

YHack 2026 - Nous Portal API Credit Distribution

A terminal emulator for the web

A framework for few-shot evaluation of language models.

An example project for the Nous Research Kaida library.

Get up and running with Llama 2, Mistral, and other large language models locally.

此仓库未提供描述。

此仓库未提供描述。

此仓库未提供描述。

PICO: Performance Insights for Collective Operations

A pure-Rust implementation of group operations on Ristretto and Curve25519

此仓库未提供描述。

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Feedback and issues for the Forge Beta Reasoning API. Submit issues here!

此仓库未提供描述。

此仓库未提供描述。

此仓库未提供描述。

NCCL Tests