NousResearch maintains a significant public presence on GitHub, featuring a wide range of repositories primarily in Python, Rust, TypeScript, Kotlin, HTML, and Jupyter Notebook. Notable projects include the hermes-agent, an agent designed for growth, and atropos, a framework for evaluating LLM trajectories.
Top languages
Public repositories
hermes-agent
The agent that grows with you
hermes-agent-self-evolution
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
hermes-paperclip-adapter
Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company
Hermes-Function-Calling
No description provided for this repository.
atropos
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
autonovel
An autonomous novel writing pipeline, by Hermes Agent
DisTrO
Distributed Training Over-The-Internet
autoreason
Autoresearch for subjective domains.
Open-Reasoning-Tasks
A comprehensive repository of reasoning tasks for LLMs (and beyond)
nomos
No description provided for this repository.
Obsidian
Maybe the new state of the art vision model? we'll see 🤷♂️
pokemon-agent
AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.
finetuning-subnet
No description provided for this repository.
nousflash-agents
Modular Agentic AI Architecture - NousResearch x Teleport (Flashbots)
tinker-atropos
Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)
llm-abliteration
Make abliterated models with transformers, easy and fast
StripedHyenaTrainer
No description provided for this repository.
smc-inference-server
No description provided for this repository.
kanban-video-pipeline
No description provided for this repository.
torchtitan
A PyTorch native library for large model training
agent-governance-toolkit
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.
local_generative_agents
Generative Agents: Interactive Simulacra of Human Behavior - with Local LLMs
neural-steering
Implementation of Contrastive Neuron Attribution for behavioral detection and steering.
NemoClaw
Run OpenClaw more securely inside NVIDIA OpenShell with managed inference
huskyholdem-bench
No description provided for this repository.
hermes-example-plugins
Example plugins for hermes-agent — reference implementations and documentation companions, not bundled with the core repo.
forge-api-demo
Simple demo showing how to use the Forge API by Nous Research
Gym
Build RL environments for LLM training
llm-chain
No description provided for this repository.
wandb-rs
No description provided for this repository.
Nemotron
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
OpenShell is the safe, private runtime for autonomous AI agents.
RL
Scalable toolkit for efficient model reinforcement
lm-eval-harness
No description provided for this repository.
nanotron
Minimalistic large language model 3D-parallelism training
hermes-compression-eval
Offline probe-based evaluation harness for hermes-agent's ContextCompressor. Methodology adapted from Factory's Dec 2025 'Evaluating Compression'.
Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
axolotl-func-calling
Go ahead and axolotl questions
litellm
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
funcchain
⛓️ build cognitive systems, pythonic
kaida
A prototype Kotlin LLM library.
lighteval
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
storywriter
Nous Research's experimental LLM story generator
DeepEP
DeepEP: an efficient expert-parallel communication library
nous-llama.cpp
LLM inference in C/C++ - nous research
iroh
peer-2-peer that just works
cline
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.
datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
tinker-nemogym
No description provided for this repository.
OpenShell-Community
OpenShell is the safe, private runtime for autonomous AI agents.
TextArena
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
tch-rs
Rust bindings for the C++ api of PyTorch.
solana-flake
No description provided for this repository.
storywriter-frontend
The frontend for Nous Research's experimental LLM story generator.
yellowstone-grpc
solana geyser grpc service
Megatron-Bridge
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
longform-writing-bench
No description provided for this repository.
Megatron-LM
Ongoing research training transformer models at scale
infini-attention
No description provided for this repository.
hf-hub
Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
iroh-blobs
Blobs layer for iroh
iroh-gossip
No description provided for this repository.
logfire-rust
No description provided for this repository.
ink
🌈 React for interactive command-line apps
jedi
Awesome autocompletion, static analysis and refactoring library for python
Liger-Kernel
Efficient Triton Kernels for LLM Training
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
creative-writing-bench
No description provided for this repository.
yhack
YHack 2026 - Nous Portal API Credit Distribution
wterm
A terminal emulator for the web
lm-evaluation-harness-pretraining
A framework for few-shot evaluation of language models.
kaida-gencritique
An example project for the Nous Research Kaida library.
ollama
Get up and running with Llama 2, Mistral, and other large language models locally.
llama.cpp
No description provided for this repository.
scaling-transformer
No description provided for this repository.
harbor
No description provided for this repository.
pico
PICO: Performance Insights for Collective Operations
curve25519-dalek
A pure-Rust implementation of group operations on Ristretto and Curve25519
eqbench3
No description provided for this repository.
openai-evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
forge-feedback
Feedback and issues for the Forge Beta Reasoning API. Submit issues here!
LeastLoadedEP
No description provided for this repository.
iroh-fake-store
No description provided for this repository.
torchtitan_tests
No description provided for this repository.
nccl-tests
NCCL Tests
Frequently asked questions
What does NousResearch build on GitHub?
NousResearch develops various tools and frameworks on GitHub, focusing on language models and autonomous systems. Key repositories include hermes-agent and autonovel, contributing to advancements in AI and machine learning.
Which programming languages does NousResearch use?
NousResearch primarily utilizes Python, Rust, TypeScript, Kotlin, HTML, and Jupyter Notebook in their projects. This diverse set of languages supports their extensive work in machine learning and software development.
Are NousResearch's repositories public?
Yes, all repositories maintained by NousResearch are public on GitHub. This open access allows for community collaboration and transparency in their research and development efforts.
Is this exposure intended?
Monitor Nous Research with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account