kunal12203/graperoot

   

为AI编码助手加深背景

网站 ·文档 ·基准测试 ·Discord

---

🌐 用你的语言读这段话： 英语 ·中文 ·西班牙语 ·हिंदी ·法语 ·德语 ·日本語 ·한국어 ·葡萄牙人·Русский ·العربية ·土耳其语·印尼语

---

什么是GrapeRoot？

GrapeRoot 是一个开源启动器，位于你和你的 AI 编码助手之间。它构建一个语义图，涵盖你的代码库——文件、符号、导入、调用链——并在你的 AI 看到之前，预先加载正确的代码到每个提示中。

本仓库中的启动器脚本是Apache 2.0。图引擎（graperoot pip 包）是专有的。

结果是：你的AI花代币推理，而不是探索。

代币节省复利在会话中叠加。图表会记住哪些文件被读取、编辑和查询——每回合成本都会降低。

---

其他工具 vs GrapeRoot

其他工具（CodeGraph、code-graph-mcp 等）给你的 AI 一个图表，让它探索：

你的AI会轮流探索，才能理智思考。

---

GrapeRoot 在你的 AI 看到你的问题之前，预加载了正确的上下文：

没有探索。

---

What is GrapeRoot?

GrapeRoot is an open-source launcher that sits between you and your AI coding assistant. It builds a semantic graph of your codebase — files, symbols, imports, call chains — and pre-loads exactly the right code into every prompt before your AI sees it.

The launcher scripts in this repo are Apache 2.0. The graph engine (graperoot pip package) is proprietary.

The result: your AI spends tokens reasoning, not exploring.

You run: dgc /path/to/project
              ↓
1. Project scanned → semantic graph built (files, symbols, imports)
2. You ask a question
3. Graph identifies the relevant files → packs them into context
4. AI gets your question + the right code already loaded
5. Fewer turns, fewer tokens, better answers

Token savings compound across a session. The graph remembers which files were read, edited, and queried — each turn gets cheaper.

---

Other Tools vs GrapeRoot

Other tools (CodeGraph, code-graph-mcp, and similar) give your AI a graph and let it explore:

You ask a question
  → AI calls search_symbol / get_callers / trace_route
  → AI reads results, decides what else to look up
  → AI calls more tools
  → AI finally has enough context to answer