{
  "schema_version": "1.1",
  "id": "archive:https://github.com/tirth8205/code-review-graph",
  "slug": "code-review-graph-0ag5r2t",
  "url": "https://feed7.dev/p/code-review-graph-0ag5r2t",
  "title": "tirth8205/code-review-graph",
  "why_included": "code-review-graph gives coding agents a local, incrementally updated dependency map over MCP, narrowing review context while exposing affected callers, dependents, and tests.",
  "summary": "code-review-graph parses repositories with Tree-sitter into a persistent local graph, then serves targeted context through MCP. Its six-repository evaluation reports a **~65x median token reduction**, with graph queries typically returning **2,000–3,500 tokens**.",
  "practical_implication": "Use it when reviews or impact analysis repeatedly make agents rediscover a large codebase. Hooks and watch mode update only changed files and their dependents; a two-file edit in a roughly **3,000-file repository took about 2.5 seconds** on the measured hook path.",
  "agent_context": "code-review-graph parses repositories with Tree-sitter into a persistent local graph, then serves targeted context through MCP. Its six-repository evaluation reports a **~65x median token reduction**, with graph queries typically returning **2,000–3,500 tokens**.\n\nUse it when reviews or impact analysis repeatedly make agents rediscover a large codebase. Hooks and watch mode update only changed files and their dependents; a two-file edit in a roughly **3,000-file repository took about 2.5 seconds** on the measured hook path.\n\nThe headline comparison uses whole-corpus reading as an upper bound, not a realistic agent workflow. Reported recall is circular because its ground truth comes from the same graph, while search MRR is **0.35** and flow-detection recall is 33%.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/tirth8205/code-review-graph",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "context",
  "domains": [
    "coding"
  ],
  "topics": [
    "mcp",
    "retrieval",
    "context-engineering"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The headline comparison uses whole-corpus reading as an upper bound, not a realistic agent workflow. Reported recall is circular because its ground truth comes from the same graph, while search MRR is **0.35** and flow-detection recall is 33%."
  ],
  "connected_context": {
    "meaning": "This turns graph-shaped code context from a general retrieval pattern into a persistent, incrementally updated MCP implementation for review and impact analysis. It reinforces bounded evidence retrieval over whole-repository loading, while sharply narrowing the performance claim: the token baseline is unrealistic, graph-derived recall is circular, and weak search and flow results leave practical retrieval quality unresolved.",
    "corpus_size": 386,
    "generated_at": "2026-08-07T11:35:32.706Z",
    "connections": [
      {
        "title": "Graphify-Labs/graphify",
        "source_name": "GitHub",
        "source_url": "https://github.com/Graphify-Labs/graphify",
        "feed7_url": "https://feed7.dev/p/graphify-1e0bs1f",
        "reason": "Both expose repository relationships as queryable agent context; code-review-graph adds measured incremental-update behavior but provides weaker evidence that the retrieved relationships cover real review needs."
      },
      {
        "title": "AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=kRkcNOsRyYg",
        "feed7_url": "https://feed7.dev/p/ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5",
        "reason": "It implements the proposed graph-shaped retrieval surface specifically for source code, while its mixed evaluation results reinforce the candidate’s requirement to benchmark graphs on local data."
      },
      {
        "title": "RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=8oyalrfwgjw",
        "feed7_url": "https://feed7.dev/p/rlm-recursive-language-models-for-large-codebases-shashi-superagentic-ai-1w21nex",
        "reason": "Both keep large repositories outside the main context and return bounded evidence, but code-review-graph relies on a precomputed persistent graph rather than agent-written inspection at query time."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/code-review-graph-0ag5r2t",
    "json": "https://feed7.dev/p/code-review-graph-0ag5r2t.json",
    "markdown": "https://feed7.dev/p/code-review-graph-0ag5r2t.md"
  }
}