Havuz

Open-source, customizable frontend for Venice AI. Chat, image gen, audio, video, embeddings + visual workflows — all in one UI. Your API key

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embedding

[MM' 2026] Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Free unlimited Gemini API for any OpenAI-compatible app.

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG,

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries

OpenAI-compatible reverse proxy for free multimodal AI APIs (chat / images / videos / audio / 3d)

Android 16 fork. AI as a platform primitive. Twelve capabilities, one shared runtime, every app. OEM-pluggable. Apache 2.0.

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。

Generate editable scientific SVG figures from method text with local SAM3 and dual-provider routing.

macOS computer-use agent in the notch. Long-press, talk, Claude drives the mouse.

Evolving what multimodal agents see and how they read it. Framework, ten reusable task skills, and paper resources.

Unified native AI runtime for Java 17+, Java 22+ (Panama FFM), Android & C++. Run GGUF LLMs, Vision, Video, Whisper ASR, TTS & Embeddings in

Human-feedback and data-governance infrastructure for RSI research: annotation, review, provenance and frozen dataset candidates.

Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never cr

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

Source-linked collection of published AI model benchmark scores.

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hoste

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

OpenCode vision support: automatically saves pasted images and guides non-vision models to recognize them via tool calling. Supports single

A unified Model Context Protocol server for MiniMax CLI (mmx)

A beautiful Gemini-powered chat interface with multimodal support

Search knowledge by what documents mean and how they look — not one or the other.

Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understanding

让非多模态模型（DeepSeek 等）把图片识别委托给任意 OpenAI 兼容的多模态模型。零厂商硬编码，主模型支持视觉时自动隐藏自己。

Use your X Premium or SuperGrok subscription in pi.

Beyond Time Shifts (ECCV 2026): a reference-free audio-visual synchronization evaluator built on Qwen2.5-Omni-3B, with SynthSync data, R-GRP

NAS OS

甲作 Atelier：手机端 AI 美甲推荐与虚拟试戴；仓库公开其中的轻量评测工作台。

Evidence-aware Bilibili video research MCP for language, vision, and multimodal analysis.

NexcoreVision OCR + CNN + VLM evidence architecture, consent-gated local ComfyUI/Qwen deployment, and Agnes media generation in one Agent Sk

Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3

Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editi

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes

Long-term memory infrastructure for .NET AI agents with semantic, temporal, spatial and robotics memory, hybrid retrieval, and pluggable pro

Give non-multimodal Claude Code main models the ability to see pasted screenshots — a ~200-line UserPromptSubmit hook.

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Local-first novel-to-comic generator — free, no GPU, pluggable providers.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible)

DeepSeek Harness plugin: a pasted animated GIF or WebP keeps playing in the UI, and the model receives a labelled sheet of frames sampled ac

Single-agent multi-modal system for insurance damage claim verification. #1 globally, HackerRank Orchestrate June 2026 (15,295 registrants).

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover

Project page for AV-Phys Bench: Do Joint Audio-Video Generation Models Understand Physics?

Self-hosted multimodal AI workspace — chat, vision QA, text-to-image, image-to-image in one conversation

Model-agnostic AI poster grid inspector: detect a poster's layout grid system with a vision model, view it overlaid, and export SVG guides /

为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。