Data / Repositories / Hugging Face
Hugging Face repositories on GitHub: 9 ranked by stars
9 public repositories tagged Hugging Face are on GitHub, with 74,019 stars between them; 6 had a push in the last 30 days. Most are written in Python (3), TypeScript (2), TeX (1). The most starred: NandhaKishorM/laya (33,012), Orchestra-Research/AI-Research-SKILLs (13,424), huggingface/chat-ui (10,982).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| NandhaKishorM/laya | Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right… | Python | 33,012 | 2,964 | Apache-2.0 | Oct 15 | Oct 15 |
| Orchestra-Research/AI-Research-SKILLs | Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent… | TeX | 13,424 | 949 | MIT | Jun 16 | Oct 11 |
| huggingface/chat-ui | The open source codebase powering HuggingChat | TypeScript | 10,982 | 1,708 | Apache-2.0 | Oct 14 | Oct 14 |
| kyegomez/swarms | The Enterprise-Grade Multi-Agent Orchestration Framework. | Python | 7,255 | 1,042 | Apache-2.0 | Oct 14 | Oct 14 |
| Michael-A-Kuykendall/shimmy | Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary. | Rust | 5,976 | 585 | Apache-2.0 | Aug 30 | Oct 14 |
| mattzcarey/shippie | extendable code review and QA agent | TypeScript | 2,509 | 243 | MIT | Sep 28 | Oct 14 |
| varunvasudeva1/llm-server-docs | End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and… | 845 | 62 | MIT | Jun 30 | Oct 14 | |
| kushalBanda/AI-Engineer | Runnable AI engineering modules: agents, MCP, memory, RAG, voice, fine-tuning, MLOps, and security. One folder per module. | Python | 9 | 2 | MIT | Oct 9 | Oct 14 |
| nvdigitalsolutions/mcp-ai-wpoos | NV Digital Open Operator System (NV oOS) is an Object-Oriented AI Framework/Harness for WordPress connecting your data with OpenAI, Gemini, Anthropic, DeepSeek, Hugging Face… | PHP | 7 | 2 | Oct 14 | Oct 14 |
By language
- Python 3
Related topics
- AI 3
- LLM 3
- Agents 3
- MCP 3
- Claude Code 2
- ChatGPT 2
- Machine learning 2
- Model Context Protocol 2
- AI agents 2
- Calibration 1
- Decision model 1
- Jev 1
Read from GitHub by SpecStream between October 11, 2026 and October 15, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.