- Replace placeholder metrics with actual benchmark results (29% fewer tokens, 25% fewer tool calls)
- Add full benchmark data table in collapsible section
- Add ASCII architecture diagram showing how CodeGraph integrates with Explore agents
- Explain the hybrid approach: agents query the graph instead of scanning files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add centered npx command in hero section (Next.js style)
- Simplify Quick Start to 3 steps using interactive installer
- Move manual setup and global instructions to collapsible details
- Add install command to CLI usage and commands sections
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New `codegraph install` command and auto-run when invoked with no args
- Beautiful ASCII banner using figlet
- Interactive prompts for global (~/.claude) or local (./.claude) installation
- Writes MCP server config to claude.json
- Writes auto-allow permissions to settings.json
- For local installs: auto-initializes project, indexes, and installs git hooks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated documentation to recommend instructing Explore agents to use
CodeGraph tools (search, callers, callees, context) for faster code
exploration instead of file scanning.
Benchmark results show ~30% fewer tokens and ~25% fewer tool calls
when Explore agents leverage CodeGraph for graph-based lookups.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of returning file paths for Claude to read separately,
codegraph_explore now:
- Reads relevant files internally using fs
- Extracts code snippets for key symbols (functions, types, APIs)
- Includes the code directly in the response
- Returns a synthesis with data flow and key code included
This matches native explore agent behavior where file reading
happens in the sub-agent context, keeping main context clean.
Bump version to 0.1.8
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move warnings to TOP of output so Claude sees them first
- If existing implementations found: "STOP: Similar implementations exist!"
- If feature request: "BEFORE PLANNING: Use AskUserQuestion to clarify..."
- Update tool description to emphasize checking existing code first
- Fixes issue where Claude listed questions but never asked them
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Pattern generation now uses multiple naming conventions:
PascalCase, snake_case, and camelCase
- Common suffixes/prefixes work across languages (Service,
Handler, Controller, handle_, create_, etc.)
- Removed JS/React-specific patterns like useBundle, SwapDialog
- Bump version to 0.1.6
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add codegraph_explore MCP tool for deep exploration with condensed output
- Expand default exclude patterns for framework build outputs (.next, .nuxt, .expo, etc.)
- Increase node ID hash length from 16 to 32 chars to prevent collisions
- Add feature request detection with UX clarification reminders
- Update README with MCP tools reference and best practices
- Update CLAUDE.md with context usage guidelines
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add centered hero with key metrics (2x faster, 40% fewer tokens, zero API costs)
- Add side-by-side comparison table showing before/after CodeGraph
- Add real-world benchmark results from Sign in with Apple test
- Add 6-feature grid highlighting key capabilities
- Update all section headers with emojis
- Add badges for npm, license, and Node.js version
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add evaluation test suite with TypeScript and Python fixtures
- Fix MCP server to defer CodeGraph init until rootUri received
- Fix call edge extraction by calling resolveReferences() after indexAll/sync
- Fix glob matching for root-level files (e.g., **/*.py now matches auth.py)
- Fix duplicate node extraction for methods inside classes
- Update context tests to use buildContext for semantic search + graph traversal
- Export unused formatter functions to fix build
Evaluation results:
- TypeScript: 96% precision, 79% recall, 85% F1
- Python: 99% precision, 80% recall, 85% F1
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Colby McHenryandClaude Opus 4.5