[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71211":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":16,"starSnapshotCount":16,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},71211,"reor","reorproject\u002Freor","reorproject","Private & local AI personal knowledge management app for high entropy people.","https:\u002F\u002Freorproject.org",null,"JavaScript",8567,526,53,113,0,4,8,12,39.17,"GNU Affero General Public License v3.0",true,false,"main",[26,27,28,29,30,31,32,33,34,35,36,37],"ai","lancedb","llama","llamacpp","local-first","markdown","note-taking","ollama","pkm","rag","second-brain","vector-database","2026-06-12 02:02:49","\u003Ch1 align=\"center\">Reor Project\u003C\u002Fh1>\n\u003C!-- \u003Cp align=\"center\">\n    \u003Cimg src=\"logo_or_graphic_representation.png\" alt=\"Reor Logo\">\n\u003C\u002Fp> -->\n\n\u003Ch4 align=\"center\">\nPrivate & local AI personal knowledge management app.\u003C\u002Fh4>\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Ftooomm.github.io\u002Fgithub-release-stats\u002F?username=reorproject&repository=reor\">    \u003Cimg alt=\"GitHub Downloads (all assets, all releases)\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Freorproject\u002Freor\u002Ftotal\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fb7zanGCTUY\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002FQBhGUFJYuH?style=flat&compact=true\" alt=\"Discord\">\u003C\u002Fa>\n    \u003Cimg alt=\"GitHub Repo stars\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Freorproject\u002Freor\">\n\n\u003C\u002Fp>\n\n> ### 📢 Announcement\n>\n> We are now on [Discord](https:\u002F\u002Fdiscord.gg\u002Fb7zanGCTUY)! Our team is shipping very quickly right now so sharing ❤️feedback❤️ with us will really help shape the product 🚀\n\n## About\n\n**Reor** is an AI-powered desktop note-taking app: it automatically links related notes, answers questions on your notes and provides semantic search. Everything is stored locally and you can edit your notes with an Obsidian-like markdown editor.\n\nThe hypothesis of the project is that AI tools for thought should run models locally _by default_. Reor stands on the shoulders of the giants [Ollama](https:\u002F\u002Fgithub.com\u002Follama\u002Follama), [Transformers.js](https:\u002F\u002Fgithub.com\u002Fxenova\u002Ftransformers.js) & [LanceDB](https:\u002F\u002Fgithub.com\u002Flancedb\u002Flancedb) to enable both LLMs and embedding models to run locally:\n\n1. Every note you write is chunked and embedded into an internal vector database.\n2. Related notes are connected automatically via vector similarity.\n3. LLM-powered Q&A does RAG on your corpus of notes.\n4. Everything can be searched semantically.\n\n\u003Chttps:\u002F\u002Fgithub.com\u002Freorproject\u002Freor\u002Fassets\u002F17236551\u002F94a1dfeb-3361-45cd-8ebc-5cfed81ed9cb>\n\nOne way to think about Reor is as a RAG app with two generators: the LLM and the human. In Q&A mode, the LLM is fed retrieved context from the corpus to help answer a query. Similarly, in editor mode, the human can toggle the sidebar to reveal related notes \"retrieved\" from the corpus. This is quite a powerful way of \"augmenting\" your thoughts by cross-referencing ideas in a current note against related ideas from your corpus.\n\n### Getting Started\n\n1. Download from [reorproject.org](https:\u002F\u002Freorproject.org) or [releases](https:\u002F\u002Fgithub.com\u002Freorproject\u002Freor\u002Freleases). Mac, Linux & Windows are all supported.\n2. Install like a normal App.\n\n### Running local models\n\nReor interacts directly with Ollama which means you can download and run models locally right from inside Reor. Head to Settings->Add New Local LLM then enter the name of the model you want Reor to download. You can find available models [here](https:\u002F\u002Follama.com\u002Flibrary).\n\nYou can also [connect to an OpenAI-compatible API](https:\u002F\u002Fwww.reorproject.org\u002Fdocs\u002Fdocumentation\u002Fopenai-like-api) like Oobabooga, Ollama or OpenAI itself!\n\n### Importing notes from other apps\n\nReor works within a single directory in the filesystem. You choose the directory on first boot.\nTo import notes\u002Ffiles from another app, you'll need to populate that directory manually with markdown files. Note that if you have frontmatter in your markdown files it may not parse correctly. Integrations with other apps are hopefully coming soon!\n\n### Building from source\n\nMake sure you have [nodejs](https:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload) installed.\n\n#### Clone repo\n\n```\ngit clone https:\u002F\u002Fgithub.com\u002Freorproject\u002Freor.git\n```\n\n#### Install dependencies\n\n```\nnpm install\n```\n\n#### Run for dev\n\n```\nnpm run dev\n```\n\n#### Build\n\n```\nnpm run build\n```\n\n### Interested in contributing?\n\nWe are always on the lookout for contributors keen on building the future of knowledge management. Have a feature idea? Want to squash a bug? Want to improve some styling? We'd love to hear it. Check out our issues page and the [contributing guide](https:\u002F\u002Fwww.reorproject.org\u002Fdocs\u002Fdocumentation\u002Fcontributing) to get started.\n\n## License\n\nAGPL-3.0 license. See `LICENSE` for details.\n\n_Reor means \"to think\" in Latin._\n","Reor 是一款基于AI的个人知识管理应用，旨在为高信息量用户提供私密且本地化的笔记体验。其核心功能包括自动关联相关笔记、基于笔记内容的问答以及语义搜索，所有数据均存储于本地，并通过类似Obsidian的Markdown编辑器进行管理。技术上，Reor利用Ollama、Transformers.js和LanceDB等工具支持本地运行大语言模型与嵌入模型，实现高效的信息处理与检索。该应用非常适合需要深度整合个人信息与想法、同时注重隐私保护的知识工作者或研究者使用，在日常学习、研究或工作中能够显著提升信息管理和利用效率。",2,"2026-06-11 03:36:37","high_star"]