gitnexus

⏳ CHRONOS — Autonomous Data Incident Root Cause Analysis Agent. Triple-graph architecture (OpenMetadata + Graphiti + GitNexus) powered by LangGraph. Travels through metadata time to find where data quality broke.

Code Graph Nexus: AI-Powered Code Intelligence for Autonomous Agents 2026

Global OpenCode configuration for autonomous coding, research, planning, Macrodata memory, GitNexus code intelligence, Crawl4AI scraping, MCP tools, specialist agents, and reusable skills.

Fork do GitNexus focado em Cursor: hooks postToolUse (gitnexus-hook.cjs), skills em .cursor/, gitnexus setup e testes de hooks; .gitignore para openspec e pastas locais do Cursor. Mantém paridade com o upstream.

AI Agent Instruction Hub — orchestrates context-aware instruction packs for Cursor, Claude Code, Codex, and other MCP-compatible agents.

企业级的 Java TDD 全流程自动化插件。从 MRD 到可跑通测试的代码，全程 AI 驱动，人在关键节点确认。

开源项目分析规则体系 — 结合 GitNexus 知识图谱引擎，AI Agent 统一分析流程

Open-source AI context engine for Unity projects: GitNexus code graph, Unity GUID/fileID scene and prefab graph, Roslyn symbols, runtime evidence, and read-only MCP/Context API for coding agents.

Graph-powered autonomous bug hunter for Claude Code. GitNexus + scientific debugging.

Hunt down social media accounts by username across social networks

Production toolkit for running GitNexus at scale — 26 repos, 43K symbols, 100K edges, zero data loss. Docker, cron, AI agent integration. Featured in GitNexus Community Integrations.

🤖 Just a skill to let AI generate documents based on your source code 🔅

Knowledge graph visualizer — Sigma.js/React UI inspired by GitNexus. Renders 76K+ code nodes from 67 merged repos with search, filtering, and ForceAtlas2/Tree/Circle views.

Configurable workflow harness for Codex and LLM coding agents: repo-aware setup, AI agent instructions, slice manifests, MCP/GitNexus routing, tracker integration, and verification gates for reliable agentic software development.

he ultimate knowledge graph tool for AI agents. Built on the AAG Protocol.

Public registry of code-knowledge graphs for AI agents. Awesome-list 2.0: pointers to schema-validated content, not just links.

An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Authoritative north-stars the agent must cite, a task-core written before compaction eats it, review by an expert in YOUR domain, and an installer that verifies its own claims instead of printing success. Claude Code, Cursor, Zed, Codex.

ByeByeVibe — Spec-Driven Development (SDD) install kit from vibe coding to shippable AI engineering. Control plane (OpenSpec + graphs + gates) for Cursor & Claude Code.

An Always-On Autonomous AI Software Engineering Team built with LangGraph, FastAPI, and Next.js that operates natively within your GitHub repositories.