#52 168,815
huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A World of Code.
Worth Exploring.
Find your next tool, framework, or rabbit hole.
Explore GitHub’s most-starred repositories, with the sources to go deeper.
Repositories200 / Search Snapshot
Combined Stars30,504,742 Stars
Languages Represented22 Primary Languages
Source Coverage197 README Examples
Leading the ListThe Three Most-Starred Search Results
Discover the Top 200
| Rank | Repository and Purpose | Category | Language | Stars | Details |
|---|---|---|---|---|---|
| 52 | huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. | AI and Machine Learning | Python | 168,815 | |
| 68 | Comfy-Org/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. | AI and Machine Learning | Python | 146,339 | |
| 84 | ggml-org/llama.cpp LLM inference in C/C++ | AI and Machine Learning | C++ | 134,080 | |
| 154 | vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs | AI and Machine Learning | Python | 96,753 | |
| 192 | cheaper-inference/OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ … | AI and Machine Learning | TypeScript | 86,509 |
#68 146,339
Comfy-Org/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
#84 134,080
ggml-org/llama.cpp LLM inference in C/C++
#154 96,753
vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs
#192 86,509
cheaper-inference/OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ …
1–5 of 5
1 / 1
About the Data and Ranking
Public repositories returned by GitHub Search, including forks and archived repositories. Search indexing, candidate scope and pagination limit global completeness. Counts are exact API integers at retrieval, not live counters.
Query: stars:>1000 is:public fork:true. Two pages of 100 results, sorted by stars. All 200 records are validated before replacement; the previous snapshot survives a failed check. Categories are editorial, generated from documented topic and description rules.
Stars reflect interest and popularity, not software quality, safety, or maintenance guarantees. Purpose text comes from upstream repository metadata. README examples are source-extracted and are not execution tests.
Storage: D1. Last Check: 11 Nov 2026, 17:19 UTC. Next Target: 12 Nov 2026, 19:00 UTC. Schedule configuration is verified separately in the operator runbook.
GitHub Search API Documentation