Watch Mode With Auto Update Hooks For Continuous Graph Synchronization

via “real-time code graph synchronization with file watching”

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

Unique: Integrates file system watching with the JobManager to provide real-time graph synchronization with debouncing and status tracking. Enables AI assistants to work with current code context through MCP without requiring manual re-indexing, bridging the gap between development and AI context freshness.

vs others: More responsive than periodic re-indexing (Sourcegraph, Tabnine) because it updates immediately on file changes; more efficient than naive per-file updates because debouncing batches rapid changes.

via “watch mode with auto-update hooks for continuous graph synchronization”

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

Unique: Implements filesystem-level watch mode with git hook integration (diagram 4) that automatically triggers incremental graph updates without manual intervention. The system uses SHA-256 change detection to identify modified files and re-parses only those files, keeping the graph synchronized in real-time.

vs others: More convenient than manual graph rebuild commands because it runs continuously in the background and integrates with git workflows, ensuring the graph is always current without developer action.