What problem does it solve?
Centralizes discovery, caching, and registration of third-party library source trees so agents and CLIs can inspect dependency code without repeatedly cloning or re-downloading archives, reducing redundant network work and improving reproducible analysis.
Core Features & Use Cases
- Cataloging: Register GitHub repositories or existing local source trees with aliases and canonical names for reuse across agents.
- Fetch & Cache: Download tag archives or perform shallow clones with automatic fallback and maintain a managed local cache.
- Local scanning: Recursively discover many local source roots by manifest markers or git repositories and register them for quick resolution.
- Manifest support: Produce and respect stub and enriched manifest files to supply retrieval metadata for downstream agents.
- Use Case: An AI code-review agent resolves a fuzzy dependency name, fetches the preferred local path from the catalog, and inspects the source without repeatedly querying GitHub.
Quick Start
Run the included source_catalog.py script to add or fetch a repository and then return the preferred local source path for inspection.