Skip to content

v0.1.0

Release Date: 2026-04-09

Initial release of Graphize - LLM-powered CLI for transforming Go codebases into queryable knowledge graphs.

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

CLI Commands

Command Description
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 for fast incremental rebuilds
  • --no-cache flag to bypass cache when needed
  • Cache hit/miss statistics reporting

Analysis Features

  • 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: EXTRACTED, INFERRED, AMBIGUOUS breakdown

Semantic Extraction

LLM-discovered edge types:

  • inferred_depends - Implicit dependencies
  • rationale_for - Design rationale from comments
  • similar_to - Semantic similarity
  • implements_pattern - Design pattern implementations
  • shared_concern - Cross-cutting concerns

MCP Server Tools

Tool Description
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

Storage

Uses GraphFS for git-friendly storage:

.graphize/
├── manifest.json      # Tracked sources
├── nodes/             # One file per node
├── edges/             # One file per edge
└── cache/             # Per-file extraction cache