{"repo":"Qingyon-AI/Revornix","free":true,"listed":false,"github":"https://github.com/Qingyon-AI/Revornix","clone":"git clone https://github.com/Qingyon-AI/Revornix.git","description":"Revornix is an open-source, local-first AI information/markdown workspace. It helps you collect fragmented inputs, turn them into structured knowledge, generate reports with images and podcast audio, and deliver the output through automated notifications.","language":"TypeScript","stars":288,"topics":["ai","news","rag","mcp","revornix","markdown","notes","agent"],"license":null,"category":"mcp-servers","readme_excerpt":"English 中文文档 日本語ドキュメント Reject FOMO! When facing the information stream, be lazy, leave the rest to AI! Revornix is an open-source, local-first AI information workspace. Save the noisy stream of links, papers, audio and screenshots you can't keep up with, and let the platform turn them into structured knowledge, generate reports and podcasts you can actually consume, and deliver the result through notifications when you're ready. The whole stack — web client, gateway, API, async workers, trending feed, docs site — is open and self-hostable. Links - Official site: - Live workspace: (users in mainland China should prefer the local mirror for a more reliable connection) - Documentation: - Environment variables: - Roadmap: Notion roadmap - Community: Discord · WeChat · QQ Why Revornix - One pipeline for noisy information — ingestion → conversion → summary → graph → podcast → notification, all in one place. - Built for AI retrieval quality — chunked vector storage in Milvus paired with a personalized GraphRAG layer on Neo4j. - Open and controllable — runs entirely on your own infrastructure. Your documents, your database, your keys. - Model-flexible — any OpenAI-compatible provider can be wired in, and engines for parsing, embedding, summarising, podcasting and illustration can be swapped independently. - Collaboration-ready — share knowledge sections privately with a team or publish them to the open web. - Public discovery — published documents, sections, creators, labels and tren","default_branch":null,"files":null,"tree":[],"storefront":"/r/Qingyon-AI","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Qingyon-AI/Revornix/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}