Skip to content

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, this project adheres to Semantic Versioning, commits follow Conventional Commits, and this changelog is generated by Structured Changelog.

Unreleased

v0.2.0 - 2026-04-12

Highlights

  • Watch mode for auto-rebuild on file changes
  • Git hooks for automatic analysis on commit/checkout
  • Neo4j Cypher and Obsidian vault export formats
  • Path finding and token benchmark commands

Added

New Commands

  • graphize path <from> <to> - Find shortest path between nodes using BFS
  • graphize benchmark - Show token reduction statistics (raw vs TOON)
  • graphize watch - Auto-rebuild on file changes with debouncing
  • graphize hook install/uninstall/status - Git hook management

New Export Formats

  • graphize export cypher - Neo4j CREATE statements
  • graphize export obsidian - Wiki-style vault with wikilinks

New Flags

  • --directed flag for graphize analyze to control edge directionality
  • --html and --report flags for watch mode to auto-regenerate outputs
  • --debounce flag for watch mode (default 500ms)

Git Hooks

  • post-commit: auto-run graphize analyze after commits
  • post-checkout: check if graph is stale after checkout

Documentation

  • CLI reference updated with all new commands
  • Getting started guide with watch mode and git hooks
  • Export formats table updated with Cypher and Obsidian

v0.1.0 - 2026-04-09

Highlights

  • LLM-powered tool to turn Go codebases into queryable knowledge graphs
  • Two-step extraction: deterministic AST + optional LLM semantic analysis
  • TOON export format with 98% token reduction vs JSON for AI agents
  • MCP server for AI agent integration with 5 graph query tools

Added

CLI Commands

  • graphize init - Create graph database directory structure
  • graphize add <repo> - Track repositories with git commit hashes
  • graphize status - Show sources with staleness detection
  • graphize analyze - Extract AST graph from Go sources
  • graphize query - BFS/DFS traversal with depth control and edge filters
  • graphize export html - Cytoscape.js interactive visualization
  • graphize export json - Cytoscape JSON format
  • graphize export toon - Token-efficient agent output
  • graphize summary - Markdown summary for agents
  • graphize report - God nodes, communities, surprises analysis
  • graphize enhance - Prepare files for LLM semantic extraction
  • graphize merge - Merge LLM-extracted semantic edges
  • graphize serve - MCP server for AI agent integration

AST Extraction

  • Go AST extraction: packages, files, functions, methods, types, imports, calls
  • SHA256-based per-file caching
  • --no-cache flag to bypass cache
  • Cache hit/miss statistics

Analysis

  • God nodes: most connected entities (excluding file-level hubs)
  • Community detection: Louvain algorithm with cohesion scores
  • Surprising connections: cross-file, cross-community edges
  • Isolated nodes: potential documentation gaps
  • Package statistics: files, functions, types, imports per package
  • Edge confidence breakdown: EXTRACTED, INFERRED, AMBIGUOUS

Semantic Extraction

  • Edge types: inferred_depends, rationale_for, similar_to, implements_pattern, shared_concern
  • LLM output parsing and validation
  • Claude Code skill for extraction workflow

MCP Server

  • query_graph - BFS/DFS traversal from search terms
  • get_node - Node details by ID or label
  • get_neighbors - Adjacent nodes with edge info
  • get_community - List community members
  • graph_summary - Stats, god nodes, suggested questions

Analysis Insights

  • Suggested questions generation:
  • Ambiguous edges needing verification
  • Bridge nodes connecting communities
  • Inferred relationships to verify
  • Isolated nodes (documentation gaps)
  • Low cohesion communities

Documentation

  • PRD.md: Product requirements
  • TRD.md: Technical requirements
  • TASKS.md: Implementation tracking
  • PLAN.md: Architecture decisions