Birdclaw offers a local-first Twitter workspace, enabling users to archive, cache, triage, and automate interactions with their Twitter data. It targets power users and agents seeking a private, scriptable, and robust local data store, providing benefits like offline access, agent-friendly JSON output, and a clean interface for managing mentions, DMs, and blocks.

How It Works

The project employs a local-first architecture, storing all Twitter data in a shared SQLite database. It caches media and avatars locally and supports importing user archives. A web UI and CLI offer focused views for timelines, DMs, and moderation tasks. Data can be exported as scriptable JSON for agent automation, with optional live sync capabilities via xurl or bird fallbacks. Its design prioritizes local control and provides Git-friendly text backups for data resilience.

Quick Start & Requirements

Installation is available via Homebrew (brew install steipete/tap/birdclaw) on macOS, or from source using pnpm install. Core requirements include Node.js (v25.8.1) and pnpm. macOS is recommended for archive discovery. Optional dependencies like xurl, bird, and an OpenAI API key enhance live sync and AI-powered features.

Highlighted Details

• Local-first SQLite storage for tweets, DMs, likes, and bookmarks.
• Comprehensive archive import and cached live data synchronization.
• Web UI and CLI for focused triage, filtering, and moderation actions.
• Agent-ready JSON export and AI-driven inbox for signal prioritization.
• Robust, Git-friendly text backup and restore mechanism.

Maintenance & Community

The project is marked as "WIP" (Work In Progress) by its creator, @steipete, with ongoing development expected to include schema churn and transport gaps. No explicit community channels (e.g., Discord, Slack) or sponsorship details are provided in the README.

Licensing & Compatibility

The README does not specify a software license. This omission makes it impossible to determine compatibility for commercial use or closed-source linking without further clarification. The application is designed as a local-only tool with no authentication layer.

Limitations & Caveats

As a Work In Progress, users should anticipate schema changes, incomplete transport coverage, and rough edges. It is not yet a polished, product-grade solution for full sync parity. The absence of a stated license is a significant adoption blocker.