#multimodal

tong-io/tongflow

TypeScript

89

health

TongFlow — Multimodal GenAI Studio

apache/seatunnel

Java

89

health

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

zhongkaifu/TensorSharp

C#

89

health

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

ysr666/dsh-vision-router

JavaScript

88

health

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

TanStack/ai

TypeScript

88

health

🤖 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.

valentinfrlch/ha-llmvision

Python

88

health

Visual intelligence for your home.

vllm-project/vllm-omni

Python

84

health

A framework for efficient model inference with omni-modality models

however-yir/knowledgeops-agent

Java

84

health

Enterprise-ready Spring AI platform for RAG, tool calling, async ingestion, JWT/RBAC security, and observability.