SylphxAI

Iris

Community SylphxAI
Updated

Merged into SylphxAI/anymd — any file → Markdown for AI agents

Iris

Image facts with pixel-level proof

Iris gives agents deterministic facts from screenshots, UI captures, forms,diagrams, charts, and other images. It returns dimensions, metadata, OCRregions, layout blocks, crops, and trust warnings without requiring agenerative vision model.

npx -y @sylphx/iris

For Claude Code:

claude mcp add iris -- npx -y @sylphx/iris

The fastest useful workflow

{
  "path": "/absolute/path/to/screenshot.png",
  "include_ocr": true
}

The result includes image dimensions, hash, OCR lines with bounding boxes,layout blocks, a text map for agents, and explicit warnings or gaps.

Jobs Iris is built for

Ask your agent Iris returns
“Read this screenshot.” text regions and layout facts
“What changed between these UI captures?” image diff evidence
“Extract this form.” OCR lines and boxes
“Crop the important region.” citeable pixel evidence
“Check the image metadata.” format, dimensions, EXIF trust warnings

Tool surface

Tool Purpose
read_image Primary image facts and optional OCR
image_probe Cheap metadata and geometry probe
crop_region Extract a citeable pixel region
compare_images Report pixel and layout differences between two images

Predictable defaults

  • fast returns deterministic metadata, geometry, and layout.
  • quality explicitly enables OCR and local semantic helpers.
  • Generative captions and object detection are opt-in and never authoritative.
  • GPS metadata is redacted unless explicitly requested.
  • Oversized or unsupported files fail with a structured error.

Why agents trust it

Every result keeps source path and hash, pixel locators, extraction route,confidence or warnings, and known gaps. OCR and optional model output neverreplace deterministic geometry.

Companion MCP tools

Product Job
Citra PDF answers with page-level proof
Cue Video timelines and timestamp evidence
Spine Repository architecture and impact
Locus Exact code-chunk retrieval
Lookout Web research with source excerpts

Each product is independent. Install only the tools your agent needs.

Development

bun install
bun run build
bun test
cargo test
bun run benchmark:public-proof
bun run benchmark:release-gate

License

MIT

MCP Server · Populars

MCP Server · New

    kitfunso

    Hippo

    One memory for every agent you'll ever use. Hippo writes what you teach a coding agent into a store in your repo, and your other agents read that same store.

    Community kitfunso
    Avazbek22

    DevProjex: MCP / GUI / CLI / TUI all in one

    Repomix alternative with up to 40% fewer tokens. Turn any codebase or Git repository into safe, token-efficient context for LLM and coding agents like Claude Code, Codex, and Cursor. GUI, TUI, CLI, and a read-only RAG MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, and code compression. Windows, macOS, Linux.

    Community Avazbek22
    membaseai

    Membase

    Memory layer for AI agents — SDKs, CLI and MCP server for Membase

    Community membaseai
    dosco

    DeepORG — One AI Agent for Your Whole Organization

    DeepORG (formerly GraphJin) — one AI agent for your whole organization: databases, APIs, files, and code over MCP

    Community dosco
    scumble-app

    Scumble

    Free, open-source desktop editor for AI inpainting: select, prompt, get a colour-matched layer. FLUX 3 Image, FLUX.2, GPT Image, Nano Banana, Seedream and Qwen through your API key or your own ComfyUI. Layers, PSD export, MCP.

    Community scumble-app