Open source multimodal projects
Every project in the registry tagged multimodal, ranked by real GitHub adoption.
Chat with your documents using any LLM, fully private
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.
A framework for efficient model inference with omni-modality models
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Sv
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
Visual intelligence for your home.
Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and commun
Related tags
Frequently asked questions
How many open source multimodal projects are there?
This registry tracks 12 projects tagged multimodal, with 120,733 GitHub stars between them. The most-adopted is AnythingLLM at 67,836 stars.
Are these multimodal projects free to use?
Yes — 12 of the 12 carry an explicit open-source licence across 3 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.
Which multimodal project should I choose?
The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.
Are these multimodal projects still maintained?
11 of the 12 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.