code-graph

Show HN 介绍 Graphicle，一个用 Rust 编写的单文件程序，将代码仓库映射为代码图并为编码代理（如 Claude Code、Cursor）提供带引用的文件与行号上下文记忆，完全本地运行，无需 API key 或账号。

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.

An indie dev released repopedia, an MIT-licensed, fully local code knowledge-graph tool that builds a SQLite graph from Python/TypeScript repos using tree-sitter, plus an MCP server so coding agents like Claude Code can query call graphs and blast-radius impact directly instead of relying on grep.

StateTape models a repository as a symbol-level code graph and marks which symbols each write changes, allowing coding agents' contexts to be rewritten based on actual code dependencies rather than textual history, improving resolve rates across six coding agents and three edit-heavy benchmarks.

A live code graph tool that combines static analysis and runtime traces to provide full-stack context for AI coding agents, enabling models like Sonnet to outperform Opus in production debugging.

An engineer discusses the limitations of mailbox-based agent messaging and proposes structural addressing over a code graph to compute blast radius for message routing, arguing this is key for scaling beyond three agents.

The author built mex, a tool that helps coding agents preserve repo knowledge instead of re-reading, with v0.7.0 adding a local code graph that reduces context usage by 90.7% while maintaining recall.

CodeGraph is a local-first tool that converts codebases into structured knowledge graphs. It uses Tree-sitter to precisely parse ASTs and supports over 20 languages. Through the MCP protocol, it directly feeds AI coding agents like Claude and Cursor, helping quickly analyze code impact scope while reducing token consumption and tool call frequency.

A weekly roundup of 10 viral AI repositories on GitHub, featuring tools for code visualization, agent skills, video generation, and more.

This tool provides context engineering for AI coding agents by converting any codebase into an interactive graph that agents can query, compatible with Claude Code, Codex, and Antigravity, and is 100% open source.

A tweet highlights four emerging graph knowledge agent tools: Selfgraph, CodeGraph, Understand-Anything, and Graphify, each turning code or data into queryable knowledge graphs.

Atlarix is a desktop environment that pre-parses codebases into a node/edge graph, allowing coding agents to navigate architecture via queries instead of reading raw text, which improves performance of smaller local models.

CodeGraph is an open-source tool that pre-builds a semantic knowledge graph for codebases, allowing Claude Code to query the graph instead of scanning files one by one, thereby significantly reducing tool calls (by 92%) and improving exploration speed (by 71%). It supports 19 programming languages and 13 frameworks.