Tag
Meta published how they mapped their entire 4,100-file, 4-repo pipeline codebase into a navigable graph for AI agents using 50+ agents in one session, cutting tool calls by 40% with zero hallucinated file paths. The 'compass, not encyclopedia' setup produces 59 small context files and is designed to be easily copied for other repos.
A tweet points out that most Claude Code token costs come from re-reading the entire codebase on each edit, and highlights a new category of tools that use codebase mapping, context pruning, and project memory to drastically cut token usage, with a list of 10 tools in the linked article.
Carto is an open-source tool that builds a persistent domain map of a codebase, helping AI agents understand systems and avoid failures like wrong file editing and context overflow, running entirely locally with no data leaks.