[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-95115":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":9,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":16,"hasPages":16,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":18,"readmeContent":19,"aiSummary":20,"trendingCount":14,"starSnapshotCount":14,"syncStatus":21,"lastSyncTime":9,"discoverSource":22},95115,"magnitude","magnitudedev\u002Fmagnitude","magnitudedev","Open source agent with local models built in. Fully private and offline. Works out of the box on any hardware.",null,"https:\u002F\u002Fgithub.com\u002Fmagnitudedev\u002Fmagnitude","TypeScript",1425,105,0,51.08,false,"main","2026-08-24 04:01:23","\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Flogo-nobg.svg\" alt=\"Magnitude icon\" width=\"120\">\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">Magnitude\u003C\u002Fh1>\n\n\u003Cp align=\"center\">Open source agent with local models built in. Fully private and offline. Works out of the box on any hardware.\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdocs.magnitude.dev\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F📕-Docs-0369a1?style=flat-square&labelColor=0369a1&color=gray\" alt=\"Documentation\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FEHt48pPWdC\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?style=flat-square&logo=discord&logoColor=white&labelColor=5865F2&color=gray\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fx.com\u002Fusemagnitude\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTwitter-Follow-000000?style=flat-square&logo=x&logoColor=white&labelColor=000000&color=gray\" alt=\"Follow Magnitude on Twitter\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmagnitudedev\u002Fmagnitude\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmagnitudedev\u002Fmagnitude\" alt=\"GitHub Repo stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@magnitudedev\u002Fcli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F%40magnitudedev%2Fcli\" alt=\"npm version\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">⭐ Help us reach more developers and grow the Magnitude community. Star this repo!\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fmaglocaldemo.gif\" alt=\"Magnitude running a local model\">\n\u003C\u002Fp>\n\n## Get started\n\n```sh\nnpm install -g @magnitudedev\u002Fcli\ncd your-project\nmagnitude\n```\n\nMagnitude supports macOS and Linux. Windows is supported through WSL.\n\n## Why Magnitude?\n\n- **Fully private and offline** Everything stays on your machine, including the models.\n- **Models for every machine** Profiles your hardware and recommends the best models.\n- **Works out of the box** No Ollama, model server, or inference setup to configure.\n- **Skills** Extend Magnitude to work with Excel, PDFs, Chrome, and more.\n- **Free to run** No token costs, API keys, subscriptions, or rate limits.\n- **Open source** Apache 2.0 licensed, fully inspectable, and yours to modify.\n\n## Add skills\n\nSkills are reusable capabilities for your agent. A good way to get them is [skills.sh](https:\u002F\u002Fwww.skills.sh), a skills directory from Vercel.\n\nSkills we recommend:\n\n```sh\nnpx skills add vercel-labs\u002Fagent-browser   # drive your logged-in Chrome browser\nnpx skills add anthropics\u002Fskills\u002Fxlsx      # read and build Excel spreadsheets\nnpx skills add anthropics\u002Fskills\u002Fpptx      # build PowerPoint decks\nnpx skills add anthropics\u002Fskills\u002Fdocx      # read and write Word documents\nnpx skills add anthropics\u002Fskills\u002Fpdf       # read, fill, and create PDFs\n```\n\n## FAQ\n\n### What is Magnitude?\n\nMagnitude is an open source agent with local models built in. Everything runs directly on your machine.\n\n### How is Magnitude different from Ollama or Hermes?\n\nOllama runs local models. Hermes is an agent that can use local models. Magnitude combines both in one: it profiles your hardware, recommends and downloads models, then configures and runs them inside the agent. Nothing else to set up.\n\n### What hardware do I need?\n\nThere’s no fixed minimum. Magnitude profiles your hardware and recommends the best models for your machine. More memory lets you run larger models.\n\n### Does my data go to the cloud?\n\nNo. Your prompts and files stay on your machine.\n\n### Can Magnitude run completely offline?\n\nYes. Once Magnitude and a model are downloaded, you can use it without an internet connection.\n\n### Can I use models outside the catalog?\n\nYes. You can [download compatible GGUF models from Hugging Face](https:\u002F\u002Fdocs.magnitude.dev\u002Fmodels#download-a-model-outside-the-catalog) and use them in Magnitude.\n\n### Can I use my own inference server?\n\nYes. You can [connect an OpenAI-compatible endpoint](https:\u002F\u002Fdocs.magnitude.dev\u002Fcustom-endpoints) and use its models in Magnitude.\n\n## Learn more\n\n- [Documentation](https:\u002F\u002Fdocs.magnitude.dev)\n- [CLI reference](https:\u002F\u002Fdocs.magnitude.dev\u002Freference)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FEHt48pPWdC)\n- [Report an issue](https:\u002F\u002Fgithub.com\u002Fmagnitudedev\u002Fmagnitude\u002Fissues)\n\n## License\n\nMagnitude is licensed under the [Apache License 2.0](LICENSE).\n","Magnitude 是一个开源自研的本地化 AI 代理工具，内置轻量级模型并完全离线运行。核心功能包括自动硬件识别与模型适配、零配置启动、支持 Excel\u002FPDF\u002FChrome 等多格式技能扩展，技术上基于 TypeScript 实现，无需依赖 Ollama 或外部 API，所有数据与推理全程保留在用户设备端。适用于注重隐私的数据分析、文档处理、自动化办公等本地化 AI 应用场景，尤其适合开发者、研究人员及对数据合规性要求高的个人或小团队使用。",2,"trending"]