为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字
☆17Jun 26, 2026Updated 4 months ago
Alternatives and similar repositories for minicpm-vision-mcp
Users that are interested in minicpm-vision-mcp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 专业滑块验证码求解库 | Professional Slider CAPTCHA Solver — Multi-provider auto-detection, CDP human-like trajectories, plugin-extensible, automati…☆17Oct 19, 2026Updated last week
- Turn PDF and EPUB books into cached AI analysis, Obsidian notes, and installable Codex/Claude Agent Skills through an open MCP server.☆49Aug 29, 2026Updated last month
- Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as …☆57Aug 21, 2026Updated 2 months ago
- nanobot.NET 是 HKUDS/nanobot (https://github.com/HKUDS/nanobot) 项目的全面 .NET 10 复刻版。它旨在将原始项目“极致轻量”的设计哲学带入 C# 生态系统，提供一个不到 2000 行核心代码但功 能完备的 …☆13Feb 24, 2026Updated 8 months ago
- AI投资大师-基于AI的智能投资分析系统，专为中国A股市场设计，我们的AI系统集成了12位世界级投资大师的投资理念和分析方法☆18Nov 17, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- An easy-to-use tool to convert Zotero PDF files and annotations to markdown files.☆14Oct 6, 2025Updated last year
- ☆39Jul 31, 2026Updated 2 months ago
- AI skill pack distilled from Zhouyi for situational diagnosis and timing.☆16Jun 3, 2026Updated 4 months ago
- 一个高度可定制化的 AI 角色扮演与互动叙事平台。☆32Updated this week
- Claude Science: The Green Book · 科研实战 — run the full academic pipeline with Claude Code☆21Aug 5, 2026Updated 2 months ago
- WebAPI 学习☆15Dec 7, 2015Updated 10 years ago
- AI skill pack distilled from Sunzi Bingfa for strategy and decision making.☆21Jun 3, 2026Updated 4 months ago
- 传统相术图片分析技能 - 面相、手相、骨相、体相 | Chinese Physiognomy Image Analysis Skill☆24Sep 9, 2026Updated last month
- Buff 加持的 SSH 工具 | 面向 AI 的 SSH 工具与 MCP 服务器，内置自研 AI Agent 编排层，接入任意 OpenAI 兼容协议的大模型。 An AI-oriented SSH tool and MCP server with a built-in …☆19Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- 雷·达里奥完整思想资料库 | Ray Dalio Complete Works Collection - 自动化整合的投资哲学与管理原则资料库☆20Jun 27, 2025Updated last year
- 源仓库官网，阅读APP异次元APP最新书源和图源网站|网页版入口|下载☆15May 24, 2025Updated last year
- Self-hosted VRChat friend activity monitor - real-time WebSocket tracking of friends' online status, world changes, avatar updates. Full …☆28Updated this week
- 精选国内可用的医疗和健康 AI Agent Skills、MCP 服务器和工具合集☆31Aug 19, 2026Updated 2 months ago
- Notion 客户端汉化脚本。☆17Jan 21, 2024Updated 2 years ago
- 本地优先的文献阅读与 AI 研究工作台：PDF 与双语阅读、来源笔记、跨篇检索。功能介绍、实机截图与使用教程见官网。☆37Updated this week
- 全平台六爻 Agent Skills：支持 ChatGPT、Claude、Codex、Cursor、Gemini、Copilot、OpenCode、Windsurf 与 Cline☆63Sep 22, 2026Updated last month
- Awvs 14 Scanner、fahai☆10Jul 1, 2021Updated 5 years ago
- A quiet AI companion. Create characters, build memories, feel something real.☆28Oct 18, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 李大魔的 AI Skills 合集：把AI写的中文改成人话 · 让Agent换会话不丢上下文☆43Sep 21, 2026Updated last month
- An AI agent skill for turning characters, products, and everyday objects into themed sticker packs.☆25May 31, 2026Updated 4 months ago
- 旨在通过爬虫机制获取美国亚马逊商品用户评论，并进行用户体验分析☆27Aug 5, 2019Updated 7 years ago
- Turn travel photos into archival photo-and-rubber-stamp field note posters.☆38Aug 24, 2026Updated 2 months ago
- 免费、本地优先的长篇网文写作桌面软件：九大结构化资料板块、可审阅智能体系统、逐章生文工作流、去 AI 味工具链。Electron + Vue 3，数据全在本地。☆23Oct 18, 2026Updated last week
- CSA - Claude Science Assistant☆47Aug 25, 2026Updated 2 months ago
- A visual journal for AI chat timeline☆39May 6, 2026Updated 5 months ago
- ☆39Updated this week
- Codex skill for composition-preserving night-film images with warm light and handwritten diary text☆30Aug 25, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Quickly search and download academic papers for you.☆38Jul 13, 2026Updated 3 months ago
- ☆12Jul 2, 2026Updated 3 months ago
- 共读室 — AI与人类的共读批注系统 / Co-reading room with shared annotations between AI and humans☆106Oct 13, 2026Updated last week
- Fork of VoiceInk with Auto Enter after transcription — automatically presses Enter after pasting transcribed text☆25Sep 25, 2026Updated last month
- AstrBot插件：将Claude Code作为LLM函数工具☆17Aug 12, 2026Updated 2 months ago
- 和彩云自动打卡签到☆11Aug 22, 2021Updated 5 years ago
- CVE-2025-24813利用工具☆16Mar 16, 2025Updated last year