code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Filter exposed MCP tools for token-constrained environments by specifying allowed tools via CLI flag or environment variable. Reduce LLM token consumption effectively.
How the MCP HTTP Transport Prevents DNS Rebinding AttacksLearn how the MCP HTTP transport prevents DNS rebinding attacks using strict Host and Origin header validation with the LoopbackOriginGuard ASGI middleware. Secure your applications today.
Framework-Aware PHP Parsing Capabilities in code-review-graph: A Deep Dive into Laravel-Aware Static AnalysisExplore framework-aware PHP parsing in code-review-graph. Discover how it leverages Composer PSR-4, Blade, and Laravel semantics for advanced static analysis and edge creation.
How FTSS Full-Text Search Combines Keyword and Vector SimilarityDiscover how FTSS combines keyword and vector similarity for powerful hybrid search. Learn about the weighted sum formula for semantic and lexical ranking.
How the Memory Loop Persists Q&A Results for Re-Ingestion in code-review-graphDiscover how the memory loop in code-review-graph persists Q&A results using markdown files for efficient re-ingestion and analysis runs.
How to Register Multiple Repositories for Cross-Repo Search in code-review-graphEasily register multiple repositories for cross-repo search in code-review-graph. Add repos to your workspace for unified indexing and seamless searching across your codebase.
How Token Savings Estimate Is Calculated and Verified in Code-Review-GraphLearn how code-review-graph calculates and verifies token savings using naïve standard and graph-based methods. Discover the testing methods for accurate efficiency.
How Edge Confidence Scoring Categorizes Edge Types in Code-Review-GraphDiscover how edge confidence scoring categorizes edge types in code-review-graph into EXTRACTED and INFERRED tiers. Learn about the numeric confidence scores.
Supported Refactoring Operations in tirth8205/code-review-graph: Rename, Dead Code Detection, and SuggestionsDiscover supported refactoring operations in tirth8205/code-review-graph including rename, dead code detection, and AI suggestions. Streamline your code reviews.
How Automatic Wiki Generation Creates Markdown Pages in code‑review‑graphLearn how code-review-graph automatically generates markdown wiki pages using Jinja templates and optional LLM summaries via the generate_wiki command.
How to Export the Code-Review Graph to Neo4j, GraphML, or ObsidianExport your code review knowledge graph to Neo4j, GraphML, or Obsidian using the GraphStore API and CLI. Learn how to visualize code contributions effectively.
How the code-review-graph GitHub Action Performs Local Risk-Scored PR ReviewsDiscover how the code-review-graph GitHub Action delivers local, risk-scored PR reviews. It analyzes code on your CI runner, generating a knowledge graph for accurate risk assessments without external code sharing.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" Maintain an open-source project? Get it listed too →