Natnael Alemseged
AboutProjectsTestimonialsWork Experience
© 2026 Natnael Alemseged. All Rights Reserved.
Secure Agent Protocol // Latency Critical // Addis Ababa

Brownfield Cartographer

Codebase Intelligence & Lineage Engineer

Multi-agent codebase cartography tool that analyzes local or GitHub repositories with Surveyor and Hydrologist agents to produce module graphs and data lineage artifacts.

"Mapped legacy repositories into graph artifacts that agents can query instead of guessing architecture from raw files."
Brownfield Cartographer module graph and data lineage map
Click to Zoom
Surveyor and Hydrologist agents turning legacy repositories into dependency and lineage graphs

Problem

AI agents waste context and hallucinate architecture in brownfield systems when they lack structural maps of modules, imports, SQL transformations, and data lineage.

Solution

Built a CLI pipeline that clones or reads repositories, extracts AST/SQL/YAML structure, runs survey and lineage passes, and writes schema-versioned cartography artifacts.

Deep Dive

What It Maps

Brownfield Cartographer has two core agents. Surveyor extracts module graphs, PageRank, git velocity, and dead-code candidates. Hydrologist traces data lineage through SQL, Python, dbt, and notebook assets.

Engineering Highlights

  • •Repo ingestion: accepts local paths or GitHub URLs and analyzes them in a temporary workspace.
  • •Graph outputs: writes module and lineage graphs under .cartography for downstream tooling.
  • •Schema versioning: graph artifacts include schema versions and migration guidance as the model evolves.

Tech Stack

PythonAST AnalysissqlglotPydanticCLIGit

Tags

#Code Intelligence#Lineage#Static Analysis#Developer Tools
View GitHub Repo

More Software Software

Case studies in similar engineering domains.

Axiom Ledger

→

Event-sourced lending pipeline for document intake, extraction, credit analysis, fraud, compliance, and decision orchestration over an append-only ledger.

Data Contract Enforcer

→

Schema integrity and lineage attribution system that turns inter-system dependencies into formal contracts, detects schema/type/statistical drift, and reports downstream blast radius.

Document Intelligence Refinery

→

PDF triage and extraction pipeline that detects document origin, layout, and domain, escalates extraction strategies by confidence, builds PageIndex trees, and answers with provenance chains.