#foundation-models Repositories
Discover 155 active open source GitHub repositories tagged with #foundation-models, accumulating 525,346 total stars (averaging 3,389 stars per project). Leading this topic is facebookresearch/segment-anything with 53,052 stars.
155 repositories total
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
Data processing for and with foundation models! ๐ ๐ ๐ฝ โก๏ธ โก๏ธ๐ธ ๐น ๐ท
OpenSquilla โ Token-Efficient AI Agent with same budget, higher intelligence density
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488
Open-source framework for the research and development of foundation models.
TimeGPT-2.1: production-ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. A generative pre-trained transformer for time series, trained on over 100B data points. It can accurately predict across various domains, such as retail, electricity, finance, and IoT, with just a few lines of code ๐.
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.
Images to inference with no labeling (use foundation models to train supervised models).
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
This is a workshop designed for Amazon Bedrock a foundational model service.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Frequently Asked Questions
What is the most popular #foundation-models repository on GitHub?
The top ranked open source #foundation-models project on GitHub is facebookresearch/segment-anything with 53,052 stars. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Which programming languages are most used in #foundation-models repositories?
Among the top ranked #foundation-models projects on GitHub, the most common programming languages are Python, Jupyter Notebook.
How is the #foundation-models repository ranking calculated?
We track 155 active open source repositories tagged with #foundation-models (500+ stars), totaling 525,346 stars with an average of 3,389 stars per repository. Rankings update daily from the GitHub API.