pinme

Uploads static files and directories to IPFS via the Glitter Protocol gateway, generating immutable content identifiers (CIDs) without requiring server management or account setup. Uses a dual-path architecture: simple single-file uploads via uploadToIpfs() for files under 200MB, and chunked directory uploads via uploadToIpfsSplit() for directories up to 1GB with session-based state management to handle interruptions and resume capability.

Maintains a local JSON-based history file (~/.pinme/history.json) that records all upload metadata including CIDs, timestamps, file paths, and domain bindings. Implements addHistory() and getHistory() functions to provide users with queryable records of past deployments without requiring external databases or cloud state storage, enabling reproducibility and audit trails.

Generates temporary preview URLs at https://pinme.eth.limo/#/preview/* that embed encrypted or obfuscated CIDs, allowing users to share deployments before binding to permanent domains. Preview URLs provide time-limited or access-controlled viewing without requiring domain setup, using URL fragment-based routing to avoid exposing raw CIDs in server logs.

Abstracts IPFS network interaction through Glitter Protocol gateway, eliminating need for users to run local IPFS nodes or manage provider credentials. Implements uploadToIpfs() and uploadToIpfsSplit() functions that communicate with gateway's HTTP API, handling content upload, chunking, and CID generation without exposing IPFS complexity to CLI users.

Binds IPFS content (identified by CID) to human-readable domains via two mechanisms: automatic Pinme subdomains (*.pinit.eth.limo) for free users, and custom DNS domains (CNAME/TXT records) for VIP users. Implements domain binding logic in PinmeApi class with HTTP methods that communicate with Pinme backend to register domain-to-CID mappings, enabling users to access immutable content via familiar URLs.

Enables users to export IPFS content as Content Addressable aRchive (CAR) files for backup, migration, or sharing, and import CAR files to restore content. Implements bidirectional CAR file handling through PinmeApi integration, allowing users to migrate deployments between IPFS providers or create portable archives of their sites without relying on live IPFS network availability.

Implements JWT-based authentication using AppKey format (<ethereum_address>-<jwt_token>) to gate premium features including custom domain binding, CAR file operations, and VIP status checks. Validates AppKey credentials against Pinme backend via PinmeApi class, enabling role-based access control without requiring OAuth or external identity providers.

Exposes pinme CLI commands as a Claude Code Skill, enabling Claude AI to invoke deployment operations directly within code generation workflows. Implements LLM execution protocol that allows Claude to call upload, domain binding, and history commands with natural language instructions, automating multi-step deployment tasks without manual CLI invocation.

Implements uploadToIpfsSplit() function to handle large directory uploads (up to 1GB) by breaking content into chunks and managing upload sessions with state persistence. Tracks upload progress and session metadata locally, enabling users to resume interrupted uploads without losing progress or re-uploading completed chunks. Uses session-based architecture to coordinate multi-part uploads across network interruptions.

Provides remove command to unpin content from IPFS via Pinme backend, removing user's copy of content from the distributed network. Integrates with PinmeApi to coordinate unpinning across Pinme's IPFS infrastructure, enabling users to delete deployments and free storage resources without manual IPFS node management.

Implements bin/index.ts entry point using Commander.js framework to parse command-line arguments, route user input to appropriate command handlers, and manage help/version output. Provides structured command registration with options, arguments, and descriptions, enabling users to discover and invoke pinme commands via standard CLI patterns (pinme upload, pinme bind, etc.).

Defines build pipeline and distribution configuration in package.json, specifying bin entry point (bin/index.ts), main export, and TypeScript compilation targets. Enables npm/yarn to install pinme as global CLI tool with automatic shebang handling and executable permissions, making deployment as simple as npm install -g pinme.