Nous Research
@nousresearch • Open source projects from nousresearch. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
88%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
18 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (12), Unknown (12), TypeScript (3)
Average size
302
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-07-23(6d ago)GitHub API fallback30 repositories
88%
of the visible star count comes from this organization's top three repositories.
302
stars per repository in this same snapshot.
Python
is the most common language here, with 18 repositories updated in the last 90 days.
Why this rank
This organization stands out because one flagship repo drives 54% of its visible star count.
Flagship share 54%Breakout repo: hermes-agent-self-evolution
Organization pages work best when you separate portfolio breadth from flagship concentration. In Nous Research's case, the visible top three repositories account for about 88% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (12), Unknown (12), TypeScript (3). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars | 🍴 Forks | Updated |
|---|---|---|---|---|---|
| 1 | nousresearch/hermes-agent-self-evolution ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA | Python | 4.8K | 558 | 1 months ago |
| 2 | nousresearch/hermes-paperclip-adapter Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company | TypeScript | 1.8K | 356 | 3 months ago |
| 3 | nousresearch/autonovel An autonomous novel writing pipeline, by Hermes Agent | Python | 1.4K | 266 | 4 months ago |
| 4 | nousresearch/autoreason Autoresearch for subjective domains. | TeX | 590 | 49 | 3 months ago |
| 5 | nousresearch/pokemon-agent AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM. | Python | 162 | 27 | 1 months ago |
| 6 | nousresearch/kanban-video-pipeline | Python | 48 | 12 | 2 months ago |
| 7 | nousresearch/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. | Python | 38 | 14 | 2 months ago |
| 8 | nousresearch/neural-steering Implementation of Contrastive Neuron Attribution for behavioral detection and steering. | Python | 33 | 15 | 1 months ago |
| 9 | nousresearch/hermes-example-plugins Example plugins for hermes-agent — reference implementations and documentation companions, not bundled with the core repo. | Python | 30 | 18 | 2 months ago |
| 10 | nousresearch/NemoClaw Run OpenClaw more securely inside NVIDIA OpenShell with managed inference | TypeScript | 27 | 12 | 1 months ago |
| 11 | nousresearch/Gym Build RL environments for LLM training | Python | 22 | 5 | 1 weeks ago |
| 12 | nousresearch/Automodel 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support | 19 | 2 | 1 months ago | |
| 13 | nousresearch/hermes-compression-eval Offline probe-based evaluation harness for hermes-agent's ContextCompressor. Methodology adapted from Factory's Dec 2025 'Evaluating Compression'. | Python | 16 | 9 | 2 months ago |
| 14 | nousresearch/hermes-telegram-business Observe-with-approval Telegram Business Mode (secretary bot) plugin for Hermes Agent — every drafted reply requires owner approval before it reaches the customer | Python | 14 | 5 | 3 weeks ago |
| 15 | nousresearch/RL Scalable toolkit for efficient model reinforcement | 14 | 3 | Yesterday | |
| 16 | nousresearch/OpenShell OpenShell is the safe, private runtime for autonomous AI agents. | 13 | 10 | 3 months ago | |
| 17 | nousresearch/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 | 12 | 3 | 2 months ago | |
| 18 | nousresearch/harbor-fork Framework for evaluating and improving agents | 8 | 3 | 2 weeks ago | |
| 19 | nousresearch/tinker-nemogym | Python | 8 | 6 | 3 months ago |
| 20 | nousresearch/Megatron-LM Ongoing research training transformer models at scale | 6 | 1 | 2 months ago | |
| 21 | nousresearch/OpenShell-Community OpenShell is the safe, private runtime for autonomous AI agents. | 6 | 4 | 3 months ago | |
| 22 | nousresearch/Megatron-Bridge Training library for Megatron-based models with bidirectional Hugging Face conversion capability | 5 | 1 | 2 months ago | |
| 23 | nousresearch/ink 🌈 React for interactive command-line apps | TypeScript | 5 | 2 | 3 months ago |
| 24 | nousresearch/speculators A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM | Python | 3 | 0 | 3 weeks ago |
| 25 | nousresearch/wterm A terminal emulator for the web | 3 | 2 | 3 months ago | |
| 26 | nousresearch/yhack YHack 2026 - Nous Portal API Credit Distribution | HTML | 3 | 3 | 4 months ago |
| 27 | nousresearch/pico PICO: Performance Insights for Collective Operations | 2 | 2 | 5 months ago | |
| 28 | nousresearch/hermes-e2e-evidence Ephemeral visual evidence published by hermes-agent CI. | 1 | 1 | 6 days ago | |
| 29 | nousresearch/torchtitan_tests | Shell | 1 | 1 | 4 months ago |
| 30 | nousresearch/LeastLoadedEP | 1 | 3 | 5 months ago |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.