penecho/penecho

Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning.

What it solves

PenEcho provides an interactive, visual workspace that bridges the gap between AI chat and visual thinking. It allows users to turn handwritten notes, sketches, and questions into structured diagrams, working widgets, and organized knowledge cards, giving AI agents a persistent canvas to "show" their work rather than just describing it.

How it works

PenEcho acts as a visual interface for AI agents. It supports the Model Context Protocol (MCP), allowing it to connect to existing AI tools like Claude Code, Codex, or Kimi. When you ask an agent to perform a task, it can render the output directly onto your PenEcho canvas. The platform also features "PenEchoLLM," which analyzes your handwriting or sketches in real-time to suggest relevant next steps, such as solving equations, plotting graphs, or creating diagrams.

Who it’s for

It is designed for developers, students, and researchers who need a collaborative, spatial environment to brainstorm, document architecture, or solve complex problems that are better represented visually than through text alone.

Highlights

  • MCP Integration: Connects seamlessly with popular AI agents to render diagrams and interactive widgets directly in your workspace.
  • Smart Assist: Automatically ranks and suggests actions (e.g., "Solve," "Typeset," "Plot") based on your handwritten input.
  • Knowledge Management: Allows you to circle content to create searchable "Knowledge Cards" that can be reused across different projects.
  • Flexible Deployment: Available as a desktop application (macOS/Windows), a CLI tool, or a web-based service.
  • Interactive Widgets: Supports the creation of functional prototypes and calculators that run directly on the canvas.

Related

  • Project
    open-pencil/open-pencil

    OpenPencil is an open‑source, cross‑platform design editor that reads native Figma (`.fig`) and Pencil (`.pen`) files, offers AI‑driven design creation (plug‑in any LLM), and provides a powerful CLI plus an MCP server for headless automation. It ships as a tiny Tauri desktop app and a PWA, supports real‑time WebRTC collaboration, and includes a Vue SDK for embedding custom editors.

  • Project
    Jaxton07/percho

    Percho is an Electron‑based desktop GUI that wraps the official Pi coding‑agent SDK, offering multi‑session chat, tool‑call approvals, UI plugins, custom themes, and support for many LLM providers.

  • Project
    1broseidon/ketch

    A stateless CLI tool that unifies web search, code search, and documentation scraping into a single interface designed for both human researchers and AI agents.

  • Project
    ankimcp/anki-mcp-server

    Anki MCP Server is a Node‑JS bridge that implements the Model Context Protocol, exposing 53 JSON‑based tools (deck, card, note, media, model, and GUI operations) so AI assistants like Claude Desktop, Cursor, or cloud‑based ChatGPT can read, edit, and review Anki flashcards. It works via STDIO (for desktop AI clients) or HTTP, and offers a managed tunnel for remote access. Install via npm, an MCPB bundle, or from source, and configure the client to launch the server as a subprocess.

  • Project
    s0ld13rr/pentestcode

    PentestCode is an open‑source, terminal‑based AI agent that automates full penetration‑testing workflows. A lead LLM coordinates 13 specialist sub‑agents (recon, scanner, enumerator, exploiter, etc.) that share a persistent structured engagement state, enabling the system to scan, enumerate, spray credentials, exploit, and report with minimal human prompting.