system_pipeline

HowItWorks.json

// Deep-dive technical breakdown of the GitDecode AI code intelligence engine.

HowItWorks.json
JSON · UTF-8
{  "id": 1,  "stepNumber": "01",  "title": "Connect & Import",  "headline": "Shallow clone and workspace detection",  "description": "Paste a public or private GitHub repository URL. GitDecode performs a shallow clone (git clone --depth 1) of the target branch to retrieve the active codebase state. It runs ingestion diagnostics to analyze project files, detect monorepos, locate package configs, and identify all active programming languages.",  "tech": [    "GitHub REST API",    "Shallow Clone (Depth-1)",    "Monorepo Detection",    "Workspace Ingestion"  ],  "codePreview": "$ git clone --depth 1 --branch main https://github.com/owner/repo"}

Shallow clone and workspace detection

GitHub REST APIShallow Clone (Depth-1)Monorepo DetectionWorkspace Ingestion
bash · git-clone
$ gitdecode-cli import --url ▋

Shallow cloning ensures we only pull the metadata and files required for structural analysis, optimizing memory and reducing wait times under 2 seconds.

comparison

Why Vectorless Graph RAG?

Traditional RAG splits code into text chunks and compares them using vector embeddings. This loses structure. GitDecode maps relations.

Traditional Vector RAG

  • ✗Splits functions and classes mid-line based on character count boundaries.
  • ✗Ignores codebase imports, call relationships, and execution pathways.
  • ✗Prone to retrieval hallucinations due to semantic similarity overlap.

GitDecode AST Graph RAG

Active
  • ✓Parses files into syntactically valid AST syntax blocks (methods, exports).
  • ✓Builds a complete, multi-file relational import & call dependency graph.
  • ✓Context window loading using Graph BFS (Depth-1 source + Depth-2 signatures).