Repositories
Categories
Contributors

Repositories
Categories
Contributors

Loading category

Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

Loading the homepage

Top AI Repos

An index of open-source AI repositories on GitHub, scored on momentum and on adoption risk — two questions that ranking by stars answers neither of.

Browse

Infrastructure
Model Development
Application Development
All categories

Submit a repository
Top contributors
JSON API

Data from the GitHub REST and GraphQL APIs. Star counts and rankings reflect the last completed sync, not live GitHub state.

Categories
/
Model Development
/
Multimodal

Multimodal

Vision-language models, document understanding and any-to-any architectures.

Signals: multimodal, vision-language-model, vlm, clip, multimodal-llm, visual-question-answering, document-understanding, image-captioning

Repositories: 339
Stars: 548k
Stars this week: +2.0k; across the category
Median quality: 49; 0–100, unscored repos excluded

Loading category

Categories
/
Model Development
/
Multimodal

Multimodal

Vision-language models, document understanding and any-to-any architectures.

Signals: multimodal, vision-language-model, vlm, clip, multimodal-llm, visual-question-answering, document-understanding, image-captioning

Repositories: 339
Stars: 548k
Stars this week: +2.0k; across the category
Median quality: 49; 0–100, unscored repos excluded

Language*

Any language

Licence*

Owner country*

Anywhere

Min stars*

Min quality*

Include archived repositories

Reset

Sort

339 results

cambrian-mllm/cambrian

Cquality grade C, 54 out of 100

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Multimodal Foundation Models Computer Vision Python repositoriesApache-2.0

stars: 2.0k
stars gained this week

+3this week

forks, open issues and contributors

141484

last push

12 months ago

sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning

Dquality grade D, 42 out of 100

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

Multimodal Learning & Awesome Lists Training Frameworks Python repositoriesMIT

stars: 2.9k
stars gained this week: +1this week
forks, open issues and contributors: 7251114
last push: 4 years ago

jingyi0000/VLM_survey

Cquality grade C, 56 out of 100

Collection of AWESOME vision-language models for vision tasks

Multimodal Computer VisionNo licence

stars: 3.1k
stars gained this week: +1this week
forks, open issues and contributors: 23729
last push: last month

337–339 of 339

Previous 1…14 15

24,545 repositories in the index in total.