Show HN: Enola-A deterministic architecture graph for developers and AI agents
Enola is an open-source architecture engine that indexes codebases into a deterministic knowledge graph, exposing an MCP server. It enables impact analysis, dead code discovery, and dependency analysis across multiple repositories without using an LLM for graph construction. The tool aims to help developers and AI agents understand large, distributed codebases more efficiently.
Background
- **Enola** is a new open-source tool that builds a persistent, deterministic "knowledge graph" of a codebase — mapping function calls, API routes, module dependencies, and more across one or many repositories.
- It exposes an **MCP server** (Model Context Protocol), a standard that lets AI coding agents query external tools. An AI can ask Enola "what depends on this function?" and get exact answers — not LLM guesses.
- Key distinction: Enola uses static analysis (like a compiler), not an LLM, to parse code. The results are deterministic and reproducible, which matters for architectural questions where wrong answers break things.
- Why it matters: As codebases grow faster — partly due to AI-generated code — both humans and AI agents struggle with architectural awareness. Enola aims to give both a reliable, queryable model, so every new coding session doesn't start from scratch rediscovering how the system works.