Neat

介绍

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.

翻译准备中

取自仓库 README

README

正在加载完整 README。 以下为已保存的摘录。

NEAT solves the AI coding context problem. It constructs a live deterministic model of your codebase — static code and live runtime behavior fused into one graph — and hands your AI agents the grounded, full-stack context they need to query, code, debug, and write rules against it. This achieves the following: • Coding LLMs hallucinate less & are more accurate. • Rather than endlessly grepping files and guessing problems, NEAT provides time-travelling error logs along the model's nodes and edges so the LLM can infer exactly what's wrong.