JSPM

shelldojo

0.0.1-alpha.0
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 3
  • Score
    100M100P100Q32011F
  • License MIT

🐚 θžΊθ›³ε£³ι‡Œεšι“εœΊ β€” Pure local LLM workflows that run on consumer Macs. No cloud, no API keys, just your machine.

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (shelldojo) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    🐚 shelldojo

    θžΊθ›³ε£³ι‡Œεšι“εœΊ β€” Building a temple inside a snail shell.

    Pure local LLM workflows that run on consumer Macs. No cloud APIs, no API keys, no data leaving your machine. Just your hardware and open-source models.

    What is this?

    A collection of practical, battle-tested local AI workflows for macOS. Each workflow ships as a self-contained CLI tool or agent-readable doc, with real benchmark data from my own M-series Mac.

    Not demos. Not toys. Things I actually use.

    Philosophy

    • Local-first β€” Everything runs offline on Apple Silicon
    • Consumer hardware β€” 16-32GB Macs, not $50K workstations
    • Honest benchmarks β€” Showing what works, what fails, and why
    • Agent-friendly β€” Docs designed for both humans and AI agents to consume

    Contents (coming soon)

    Workflow Stack Status
    CLI scaffold Node.js + TypeScript 🚧
    Receipt OCR β†’ Ledger Tesseract + local LLM πŸ”¬
    Email triage local LLM πŸ’­
    RSS filter local LLM πŸ’­
    File organizer local LLM πŸ’­
    Model benchmarks ollama / mlx-vlm πŸ”¬

    Getting Started

    # Coming soon
    npx shelldojo

    Author

    zhixian β€” @zhixianio

    License

    MIT