Havuz

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。

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。

An agent skill that reads a photo the way Sherlock Holmes reads a stranger (福尔摩斯): observe first, deduce second, every conclusion cites its

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

Open-source video compiler that turns videos into structured knowledge for AI agents.

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

Personal finance agent that decides whether an expense is safe — pay in full, split, use installments, or wait — from a 90-day balance forec

Find anything on your PC by what's in it: local, private semantic search for Windows. Photos, screenshots, PDFs, documents, recordings and v

doc7, belgeleri multimodal model kullanarak görsel içeriği de koruyan AI-ready Markdown çıktısına dönüştüren bir Go aracıdır.

Neden yükseliyor · 56 günde 1137 yıldız, projeye erken dönemde belirgin ilgi olduğunu gösteriyor; ancak son 28 günde commit ve farklı yazar sayısı sıfır, dolayısıyla ilginin sürdürülebilirliği ve bakım temposu henüz kanıtlanmış değil.

Production-oriented Spring AI platform prototype for RAG, tool calling, async ingestion, JWT/RBAC, and observability.

NEWTON: Agentic Planning for Physically Grounded Video Generation

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

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

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understa

一条命令，把微信变成任何 AI Agent 的入口 | Connect WeChat to any AI Agent with one command

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

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent

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

Official code for InfoVis: one 9B model for slide image generation and editing, with the VisSlideBench benchmark and 15M+ training records.

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

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

Give your agent eyes: any video link in, one typed JSON out. A Claude skill + API.

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

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

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

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.

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

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

An open-source, self-hosted social AI agent across QQ, Telegram, Feishu/Lark and personal clients, with persistent identity, long-term memor

Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO

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.

Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.

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

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

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