codebase-intelligence

AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱，精准查询文件结构、依赖关系与改动影响半径。

🌼 AI stack centered on an agent hypervisor. Automates tasks, graph-powered repo wiki, and Q&A, and searches across all your connected tools. Access it from browser, terminal, or API.

Live structural code graph for AI agents — one-curl install wires MCP + an agent skill into Claude Code, OpenCode, Codex and Cursor. Indexes a 96k-file Linux kernel tree in 2m51s on a laptop Intel i7; sub-ms structural queries from a memory-mapped graph.

A comprehensive repository intelligence platform that transforms software projects into actionable insights and a searchable Knowledge Graph for faster understanding, navigation & analysis.

AI-powered codebase intelligence platform replacing vector chunking with Vectorless RAG via AST graph traversal. Features multi-agent LangGraph workflows, interactive Neo4j NVL graph visualizer, 3-hop blast radius analysis, and automated architectural PDF report generation.

Local-first code intelligence over MCP: BM25/FTS5 + AST graph, impact analysis, project memory and safe writes. Text-first by default; optional dense. Works with OpenCode and Zed.

Codebase knowledge graph tool — 36+ languages, 9+ LLM backends, MCP server, 20+ AI assistant integrations

每个 AI agent 都会读文件，但很少有 agent 知道哪些文件总是一起被修改、哪个决定是哪一天做的。repowise 把依赖图、Git 历史和架构决策编成一张可查询的地图，通过 MCP 递到 agent 手里。它回答的不是「这个文件写了什么」，而是「这段代码为什么长这样」。

Give AI coding agents a map before they read your code. Statically maps your codebase structure and dependencies, enriches components with LLM summaries, and links Git commits/Jira tickets to nodes. Optimizes agent context windows and token usage with compact, queryable JSON blueprints.

Code Weave helps you understand a software project without reading every file yourself.

Visual Architecture Yielding Understanding — graph-powered file explorer that flies through code

Git repository intelligence CLI for analyzing contributors, code ownership, hotspots, and codebase risk.

Local-first code graph and change impact analysis for AI coding agents. MCP server, SQLite, tree-sitter. Python and TypeScript. Every edge carries evidence and a confidence label.

Open-source project awareness engine for AI coding tools via compressed codebase context, MCP, and editor integrations.

Event-driven runtime prototype for maintaining accurate shared context about software systems. Local control plane in-process, durable storage and connectors not yet implemented.

Autonomous software engineering pipeline for Claude Code: 11 stages, 64 verification rules, 17 codebase intelligence tools, 5 science-backed git analytics. Findings → PRD → verified PR with zero LLM judges.

An AI-powered, local-first codebase intelligence platform that combines AST analysis, knowledge graphs, semantic code search, GraphRAG, and blast-radius impact analysis to help developers understand codebases and predict change impact.

Understand Any GitHub Repository. Visually. Turn any codebase into an interactive architecture map.

ANVESHA — Universal AI Search Engine

自托管 AI Agent 工作台：RAG、记忆、工具审批、LLMOps、Gemini 与代码库智能。Self-hosted AI Agent workspace with RAG, memory, approvals, LLMOps, Gemini & codebase intelligence.