Nous Research ORG

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

No description.

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)

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

No description.

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

No description.

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

No description.

No description.

No description.

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.

Implementation of Contrastive Neuron Attribution for behavioral detection and steering.

A PyTorch native library for large model training

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

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

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

No description.

Build RL environments for LLM training

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

No description.

No description.

Scalable toolkit for efficient model reinforcement

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

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

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.

No description.

Minimalistic large language model 3D-parallelism training

Nous Research's experimental LLM story generator

A prototype Kotlin LLM library.

Go ahead and axolotl questions

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.

No description.

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

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

LLM inference in C/C++ - nous research

⛓️ build cognitive systems, pythonic

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

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

DeepEP: an efficient expert-parallel communication library

peer-2-peer that just works

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

🌈 React for interactive command-line apps

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

No description.

Observe-with-approval Telegram Business Mode (secretary bot) plugin for Hermes Agent — every drafted reply requires owner approval before it reaches the customer

Ongoing research training transformer models at scale

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

solana geyser grpc service

No description.

Blobs layer for iroh

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

Rust bindings for the C++ api of PyTorch.

No description.

Awesome autocompletion, static analysis and refactoring library for python

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

YHack 2026 - Nous Portal API Credit Distribution

No description.

Efficient Triton Kernels for LLM Training

No description.

No description.

No description.

An example project for the Nous Research Kaida library.

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

A terminal emulator for the web

PICO: Performance Insights for Collective Operations

A framework for few-shot evaluation of language models.

No description.

No description.

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

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

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

No description.

No description.

No description.

NCCL Tests

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

No description.

Framework for evaluating and improving agents