steipete/birdclaw

Stores all your tweets nicely claw-able for agents.

What it solves

Birdclaw provides a way for users to own their Twitter/X history locally. It solves the problem of relying on a cloud backend to access searchable archives of tweets, direct messages, saved posts, and follow graphs, allowing for a private, local-first approach to social media data management.

How it works

The tool imports Twitter/X archives into a local SQLite database, using FTS5 for fast local searching. It can optionally supplement this static archive with live data via syncs (delegated to xurl or a private bird installation). Users can interact with their data through a web application, a command-line interface (CLI), or a read-only MCP server for external tool integration.

Who it’s for

It is designed for users who want a self-hosted, searchable backup of their X account history and those who prefer local data ownership over cloud-based access.

Highlights

  • Local-first storage: Uses SQLite for all data, ensuring the history is stored on the user's machine.
  • Multiple interfaces: Offers a web app, a CLI for research and scheduled jobs, and a read-only MCP server.
  • Idempotent imports: Archive imports merge data without creating duplicates.
  • Privacy-focused: Local reads do not trigger network traffic by default, and the web server listens on loopback.
  • Deterministic backups: Supports JSONL shards that can be tracked via Git.

Related

  • Project
    ythx-101/x-tweet-fetcher

    A tool for fetching X/Twitter tweets, timelines, and articles without API keys or logins, featuring automatic backend fallback and a unified JSON schema for AI agents.

  • Project
    6551Team/opentwitter-mcp

    An MCP server that gives AI assistants real-time access to Twitter/X data, including user tracking, advanced search, and meme token analysis.

  • Project
    kenn-io/msgvault

    msgvault is a local-first, self-hosted archive that consolidates email, chat, and calendar data, enabling semantic search and AI agent integration via the Model Context Protocol.

  • Project
    ChatLab/ChatLab

    An open-source desktop app that uses AI agents and a local SQL engine to analyze and actually operate on social chat histories from multiple platforms privately.

  • Project
    christopherkarani/Wax

    A local-first shared memory file for AI agents and on-device models, providing a searchable binary store that can be shared across different AI tools via MCP.