GitHub topic

multimodal GitHub repositories

Explore 33 tracked GitHub repositories tagged multimodal. Compare their recorded star activity and implementation languages, then follow related topics to find other projects.

Snapshot: 2026-10-28. The collection gained 655 stars since the previous daily snapshot.

Tracked repositories: 33
Total stars: 284,140
Stars gained · 7 days: +2,395
Stars gained · 30 days: +9,519

Compare star activity

Up to five projects on this page, ordered by daily star growth. Open a project for its description and recorded star history.

Swipe to compare all star periods →

Star activity for multimodal repositories on this page
Repository	Total stars	Today	7 days	30 days
StarTrail-org/PixelRAG	10.6K	+256	+302	+512
bojieli/ai-agent-book	56.2K	+226	+1,079	+4,884
Mintplex-Labs/anything-llm	67.7K	+53	+288	+1,118
datawhalechina/all-in-rag	12.6K	+33	+248	+1,160
modelscope/ms-swift	16.0K	+24	+68	+230

Explore repositories

Showing 1–33 of 33 tracked repositories.

StarTrail-org/PixelRAG

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

★ 10.6K+256 todayPython

ai agent

View ↗

bojieli/ai-agent-book

《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

★ 56.2K+226 todayPython

llm mcp

View ↗

Mintplex-Labs/anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

★ 67.7K+53 todayJavaScript

llm ai-agents

View ↗

datawhalechina/all-in-rag

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

★ 12.6K+33 todayPython

llm ai

View ↗

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

★ 16.0K+24 todayPython

llm deepseek

View ↗

screenpipe/screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

TanStack/ai

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

★ 3.3K+7 todayTypeScript

llm ai

View ↗

HRuiCcc/RuiC-card-skill

全息闪卡通用 Agent Skill，不挑宿主、多模态模型都能用：一句话生成可拖转、会流光、带层次景深的 3D 闪卡网页，附可编辑 Blender 工程 · A host-agnostic Agent Skill: turn one sentence into an interactive 3D holographic card page with layered parallax, plus an editable Blender project.

★ 585+6 todayJavaScript

skills agent-skills

View ↗

yzhao062/pyod

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.

NVIDIA-NeMo/DataDesigner

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

★ 2.4K+3 todayPython

llm mcp

View ↗

zhongkaifu/TensorSharp

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability

★ 632+2 todayC#

llm ai

View ↗

apache/seatunnel

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

★ 9.8K+2 todayJava

llm embeddings

View ↗

oxbshw/watch-skill

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

HUANGCHIHHUNGLeo/claude-real-video

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

★ 2.3K+2 todayPython

llm claude-code

View ↗

xlang-ai/OSWorld

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

★ 3.2K+2 todayPython

llm agent

View ↗

bentoml/BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

★ 8.9K+2 todayPython

llm machine-learning

View ↗

Eventual-Inc/Daft

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

★ 5.8K+2 todayRust

machine-learning python

View ↗

InternLM/xtuner

A Next-Generation Training Engine Built for Ultra-Large MoE Models

★ 5.2K+2 todayPython

llm agent

View ↗

autodistill/autodistill

Images to inference with no labeling (use foundation models to train supervised models).

★ 2.8K+2 todayPython

machine-learning deep-learning

View ↗

RunanywhereAI/runanywhere-sdks

Production ready toolkit to run AI locally

★ 10.3K+2 todayC++

llm ollama

View ↗

UbiquitousLearning/mllm

Fast Multimodal LLM on Mobile Devices

★ 1.6K+2 todayC++

llm ai

View ↗

crmne/ruby_llm

The Ruby AI framework.

pixeltable/pixeltable

The backend agents build with - Multimodal database, orchestration, and serving in one file

★ 1.6K+1 todayPython

llm ai

View ↗

Zen4-bit/Proxima

Multi-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API

★ 1.2K+1 todayJavaScript

ai-agents mcp

View ↗

om-ai-lab/OmAgent

[EMNLP-2024] Build multimodal language agents for fast prototype and production

★ 2.7K+1 todayPython

llm agent

View ↗

genkit-ai/genkit

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

★ 6.5K+0 todayTypeScript

llm ai

View ↗

RobotecAI/rai

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

★ 610+0 todayPython