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
87%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
15 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (13), Unknown (9), TypeScript (4)
Average size
108
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-09-12(2h ago)GitHub API fallback30 repositories
87%
of the visible star count comes from this organization's top three repositories.
108
stars per repository in this same snapshot.
Python
is the most common language here, with 15 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Balanced portfolio across 30 reposTop 3 share 87%
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 87% 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 (13), Unknown (9), TypeScript (4). 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 |
|---|---|---|---|
| 1 | nousresearch/autonovel An autonomous novel writing pipeline, by Hermes Agent | Python | 1.6K |
| 2 | nousresearch/Hermes-Bot-Mode Bot Mode for the Hermes desktop: a roster of named agents with their own chats, avatars, routines, and bot-to-bot messaging. Desktop plugin, no core patches. | JavaScript | 661 |
| 3 | nousresearch/autoreason Autoresearch for subjective domains. | TeX | 603 |
| 4 | nousresearch/kanban-video-pipeline | Python | 52 |
| 5 | 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 | 44 |
| 6 | nousresearch/hermes-plugin-backsearch BackSearch plugin for Hermes Agent — point-in-time web search & fetch over a frozen news archive (General Reasoning) | Python | 43 |
| 7 | nousresearch/hermes-example-plugins Example plugins for hermes-agent — reference implementations and documentation companions, not bundled with the core repo. | Python | 39 |
| 8 | 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 | 35 |
| 9 | nousresearch/NemoClaw Run OpenClaw more securely inside NVIDIA OpenShell with managed inference | TypeScript | 31 |
| 10 | nousresearch/Gym Build RL environments for LLM training | Python | 26 |
| 11 | nousresearch/Automodel 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support | Python | 23 |
| 12 | nousresearch/hermes-compression-eval Offline probe-based evaluation harness for hermes-agent's ContextCompressor. Methodology adapted from Factory's Dec 2025 'Evaluating Compression'. | Python | 20 |
| 13 | nousresearch/RL Scalable toolkit for efficient model reinforcement | 17 | |
| 14 | 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 | 15 | |
| 15 | nousresearch/OpenShell OpenShell is the safe, private runtime for autonomous AI agents. | 14 | |
| 16 | nousresearch/harbor-fork Framework for evaluating and improving agents | 11 | |
| 17 | nousresearch/tinker-nemogym | Python | 8 |
| 18 | nousresearch/hermes-plugin-sprites Sprites terminal backend plugin for Hermes Agent — stateful Fly.io cloud sandboxes with checkpoint & restore | Python | 6 |
| 19 | nousresearch/Megatron-LM Ongoing research training transformer models at scale | 6 | |
| 20 | nousresearch/OpenShell-Community OpenShell is the safe, private runtime for autonomous AI agents. | 6 | |
| 21 | nousresearch/hermes-toolperf-evals Core-toolset A/B eval harness + benchmark cases behind the 15-PR tool-efficiency tracker (hermes-agent #77056). Built from session-DB mining, NeMo Relay traces, and prod error taxonomy. | Python | 5 |
| 22 | nousresearch/Megatron-Bridge Training library for Megatron-based models with bidirectional Hugging Face conversion capability | 5 | |
| 23 | nousresearch/ink 🌈 React for interactive command-line apps | TypeScript | 5 |
| 24 | nousresearch/speculators A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM | Python | 3 |
| 25 | nousresearch/wterm A terminal emulator for the web | 3 | |
| 26 | nousresearch/yhack YHack 2026 - Nous Portal API Credit Distribution | HTML | 3 |
| 27 | nousresearch/hermes-plugin-touchdesigner Hermes Agent plugin: drive TouchDesigner via the twozero MCP server, with the touchdesigner-mcp skill bundled (Agent Plugins v1) | Shell | 2 |
| 28 | nousresearch/hermes-desktop-accent-picker OKLCH accent colour picker for the Hermes Desktop status bar — theme-authoring tool, retints the whole app live | TypeScript | 2 |
| 29 | nousresearch/hermes-e2e-evidence Ephemeral visual evidence published by hermes-agent CI. | 2 | |
| 30 | nousresearch/image-size Security-patched image-size fork; fixes zero-length ICNS, JXL and HEIF parser loops. | TypeScript | 0 |
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.