MCP servers and skills: search, filter by where they run, and compare.
opencode skill: let text-only models see images — auto-delegates image parsing to MiMo-V2.5 (free). Paste any screenshot/photo/diagram, get OCR + description.
SkillMIT★ 1Few starsNo key
MCP server wrapping IBM docling —4 tools to give text-only LLMs (DeepSeek) document & image parsing
MCPLink only★ 1Few stars
Local-first desktop studio for ComfyUI, built for AI short-drama production - zero-dependency 10MB exe: creation, gallery, 600+ templates, model hub, character assets (LoRA binding), episodic pipeline
SkillMIT★ 30No key
Give text-only LLMs eyes. A Pi Agent skill + zero-dependency Python CLI that adds image understanding and document parsing (OCR, tables, formulas, PDF → Markdown) to any text-only model such as DeepSe
SkillMIT★ 6No key
Agent skills for Muapi: one-command install for Claude Code, Cursor, Codex and Gemini CLI to discover, price and run 500+ image, video, audio and LLM models.
SkillMIT★ 7No key
A Mojo raster/drawing engine: pixel buffer, colors, primitives, text, image I/O.
SkillMIT★ 4Few starsNo key
Unofficial MCP server for Yandex Search API v2: web, image and generative search with typed tool parameters
PythonMIT★ 3Few starsNo key
Zero-dependency TypeScript utilities for video and social creators: aspect-ratio maths, tap tempo, subtitle conversion (SRT/VTT/ASS), platform frame sizes with sourced safe areas, encoding calculators
Node.jsMIT★ 1Few starsNo key
A Claude Code skill that generates images through OpenAI, Gemini, Higgsfield, FLUX, or any OpenAI-compatible endpoint. One CLI, no dependencies.
SkillMIT★ 5No key
Eyes for text-only LLMs — standalone CLI + Claude Code skill. Qwen3-VL-Plus image understanding (10-dimension description) + MinerU precision REST document parsing. visuals see / visuals parse.
SkillMIT★ 2Few starsNo key
An Agentic AI framework for intelligent FDM additive manufacturing, integrating LLMs, MCP tools, 3D model analysis, and automated slicing workflows.
PythonMIT★ 2Few starsNo key
Highly flexible RAG system with advanced document parsing and audio processing.
SkillGPL-3.0★ 4Few starsNo key
Use ComfyUI easily through Hermes agents across Telegram, Discord, and other chat platforms
SkillMIT★ 2Few starsNo key
Universal document parsing and generation in AILANG. Deterministic Office (DOCX/PPTX/XLSX) extraction, AI-powered PDF/image parsing, 9-format document generation.
Node.jsApache-2.0Few starsNo key
SkillMIT★ 5No key
MCP server for end-to-end 3D printing automation with FDM printers
PythonMIT★ 2Few starsNo key
A privacy first (local) document parsing tool and MCP server — convert PDFs and images to structured Markdown using multiple selectable OCR engines. Includes Streamlit GUI and hierarchical chunking fo
PythonMITFew starsNo key
Open-source Codex design agent/skills system with PromptPacket v1.5, aesthetic quality gates, anti-fragmentation controls, and GitHub workflows.
SkillMIT★ 1Few starsNo key
SkillISC★ 1Few starsNo key
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Hosted by authorNo licenseFew starsNo key
GPU-Bridge MCP Server — 30 AI services as Model Context Protocol tools. LLMs, image gen, video, audio, embeddings, reranking, PDF parsing & more. x402 native for autonomous agents.
Node.jsMIT★ 2Few starsNo key
Agent skill for reconstructing image-based slide PDFs into editable PowerPoint decks
SkillMIT★ 2Few starsNo key
AI skill that turns any design style into polished HTML slides and exports to PDF
SkillMIT★ 2Few starsNo key
Who stands behind it
