Graphify Open-Source Tool: Building a Persistent Knowledge Graph for the Entire Repository for Coding Agents to Query
English text is being prepared.
The Graphify open-source project proposes first building a persistent knowledge graph for the entire code repository, then letting coding agents query the graph to modify code, rather than re-running grep and reading files on every task round. It performs local tree-sitter AST parsing on the code, labels edges as EXTRACTED or INFERRED, and outputs artifacts to graph.json, graph.html, and GRAPH_REPORT.md under graphify-out/, after which query, path, and explain can be used for querying. The author points out that whether marketing figures such as a stable 80% cost reduction can be achieved depends on repository size, whether the graph stays fresh, and whether the agent actually connects to graph queries; connection methods include registering a skill via graphify install, or mounting graph.json into Claude Code, Cursor, and Codex via graphify-mcp.
Why read this
AI score 63
The original article breaks down the approach of building a graph for the entire repository and then making it available for coding agents to query, and points out that marketing figures depend on repository size and whether the graph stays fresh.
Topics
Body
Graphify：整仓一次建知识图，少让 Agent 反复 grep
@graphify 的做法：先整仓建持久知识图，再让 coding agent 查图改码，而不每轮任务从头 grep/瞎读文件；省 token、也少迷路；是否真能稳降 80% 花费等营销数字，要看仓规模、图是否保鲜，以及 agent 是否真接进图查询。
开源项目：https://t.co/WppLaXgFx8
三点提炼 1. 持久知识图，不是向量库：对代码做本地 tree-sitter AST（确定性、边标 EXTRACTED / INFERRED）；文档/PDF/多媒体可再走语义层。产物落在 graphify-out/（graph.json + 可点的 graph.html + GRAPH_REPORT.md），之后可 query / path / explain，不必每次重扫全仓。 2. 少反复 grep：口号「map once, not grep forever」；agent 问「认证流怎么走」「A 到 B 几跳」时走图上的 calls/imports/继承等边，而不海量搜字符串。社区检测、god node 等帮助先看见子系统枢纽。 3. 接进 coding agent：uv tool install graphifyy → graphify install 注册 skill，助手里 /graphify .；也可用 graphify-mcp 把已有 graph.json 挂到 Claude Code / Cursor / Codex 等，用 graph_stats、query_graph 一类工具当上下文源。Cloud 另有「常开记忆 / 跨仓」等，与开源 CLI 要分开看。