RRepoGEO

REPOGEO REPORT · LITE

vitali87/code-graph-rag

Default branch main · commit 3bac7cb1 · scanned 6/26/2026, 10:41:33 AM

GitHub: 2,274 stars · 379 forks

AI VISIBILITY SCORE
27 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
1 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface vitali87/code-graph-rag, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README's introductory paragraph to highlight problem-solution fit

    Why:

    CURRENT
    An accurate Retrieval-Augmented Generation (RAG) system that analyzes multi-language codebases using Tree-sitter, builds comprehensive knowledge graphs, and enables natural language querying of codebase structure and relationships as well as editing capabilities.
    COPY-PASTE FIX
    Code-Graph-RAG is a complete, accurate Retrieval-Augmented Generation (RAG) system designed specifically for complex, multi-language monorepos. It leverages Tree-sitter and knowledge graphs to deeply analyze your codebase, enabling powerful natural language querying for understanding structure and dependencies, and facilitating AI-powered code editing capabilities.
  • mediumreadme#2
    Add a 'Why Code-Graph-RAG?' or 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ## Why Code-Graph-RAG?

Unlike generic RAG frameworks or standalone LLMs, Code-Graph-RAG is an end-to-end system built specifically for code. It provides deep, structural understanding of multi-language monorepos through knowledge graphs, going beyond simple semantic search to enable precise querying of dependencies and relationships. This unique approach empowers more accurate AI-powered code understanding and editing capabilities than general-purpose tools or raw LLMs.
  • lowabout#3
    Refine the repository description to emphasize 'system' and 'complex'

    Why:

    CURRENT
    The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
    COPY-PASTE FIX
    An end-to-end RAG system for your monorepo. Query, understand, and edit complex multi-language codebases with the power of AI and knowledge graphs.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface vitali87/code-graph-rag
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Claude 3
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Claude 3 · recommended 2×
  2. CodeQL · recommended 1×
  3. Lattix Architect · recommended 1×
  4. Sourcegraph · recommended 1×
  5. OpenAI GPT-4 · recommended 1×
  • CATEGORY QUERY
    How can I use AI to understand complex multi-language monorepos and their dependencies?
    you: not recommended
    AI recommended (in order):
    1. CodeQL
    2. Lattix Architect
    3. Sourcegraph
    4. OpenAI GPT-4
    5. Claude 3
    6. Bazel
    7. Understand

    AI recommended 7 alternatives but never named vitali87/code-graph-rag. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What RAG systems help with AI-powered code editing and understanding across multiple languages?
    you: not recommended
    AI recommended (in order):
    1. GitHub Copilot Chat (with GitHub Copilot Enterprise)
    2. Continue.dev (continue-dev/continue)
    3. Cursor
    4. LlamaIndex (run-llama/llama_index)
    5. LangChain (langchain-ai/langchain)
    6. text-embedding-ada-002
    7. e5-large-v2
    8. sentence-transformers/all-MiniLM-L6-v2
    9. Pinecone
    10. Weaviate (weaviate/weaviate)
    11. Chroma (chroma-core/chroma)
    12. Qdrant (qdrant/qdrant)
    13. GPT-4
    14. Claude 3
    15. Llama 3
    16. Sourcegraph Cody (sourcegraph/cody)
    17. Tabnine Chat

    AI recommended 17 alternatives but never named vitali87/code-graph-rag. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of vitali87/code-graph-rag?
    pass
    AI did not name vitali87/code-graph-rag — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts vitali87/code-graph-rag in production, what risks or prerequisites should they evaluate first?
    pass
    AI named vitali87/code-graph-rag explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo vitali87/code-graph-rag solve, and who is the primary audience?
    pass
    AI did not name vitali87/code-graph-rag — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of vitali87/code-graph-rag. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/vitali87/code-graph-rag.svg)](https://repogeo.com/en/r/vitali87/code-graph-rag)
HTML
<a href="https://repogeo.com/en/r/vitali87/code-graph-rag"><img src="https://repogeo.com/badge/vitali87/code-graph-rag.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

vitali87/code-graph-rag — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite