[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"navigation":3,"url-settings":80,"blog-\u002Fblog\u002Fnano-models":589,"blog-author-\u002Fblog\u002Fnano-models":1644},{"id":4,"extension":5,"footer":6,"header":66,"meta":77,"stem":78,"__hash__":79},"navigation\u002Fdata\u002Fshared\u002Fnavigation.yml","yml",{"brand":7,"columns":10,"legal":56},{"name":8,"tagline":9},"Pieces","The memory layer for modern work.",[11,26,41],{"title":12,"links":13},"Product",[14,17,21,24],{"label":15,"href":16},"Pieces Desktop","\u002Fdownloads",{"label":18,"href":19,"external":20},"Pieces MCP","url:docs.mcp.overview",true,{"label":22,"href":23,"external":20},"Pieces APIs","url:docs.api",{"label":25,"href":16},"Downloads",{"title":27,"links":28},"Resources",[29,32,35,38],{"label":30,"href":31,"external":20},"Documentation","url:docs.home",{"label":33,"href":34},"Blog","\u002Fblog",{"label":36,"href":37},"Changelog","\u002Fchangelog",{"label":39,"href":40,"external":20},"GitHub","url:github.org",{"title":42,"links":43},"Company",[44,47,50,53],{"label":45,"href":46},"About","\u002Fabout",{"label":48,"href":49},"Enterprise","\u002Fenterprise",{"label":51,"href":52,"external":20},"Discord","url:social.discord",{"label":54,"href":55,"external":20},"X \u002F Twitter","url:social.x",[57,60,63],{"label":58,"href":59,"external":20},"Privacy Policy","url:legal.privacyPolicy",{"label":61,"href":62,"external":20},"Refund Policy","url:legal.refundPolicy",{"label":64,"href":65,"external":20},"Terms of Service","url:legal.terms",{"links":67,"signIn":68,"contact":71,"cta":74},[],{"label":69,"href":70},"Sign in","url:portal.home",{"label":72,"href":73},"Contact sales","url:site.contact",{"label":75,"href":76},"Download","url:routes.downloads",{},"data\u002Fshared\u002Fnavigation","Ia8tCWWqcGvuaIro8jwZ3HH-MwI66yqJpWshASJdYQ0",{"id":81,"extension":5,"links":82,"meta":586,"stem":587,"__hash__":588},"urlSettings\u002Fdata\u002Fshared\u002Furls.yml",[83,87,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155,159,163,167,171,175,179,183,187,191,195,199,203,207,211,215,219,223,227,231,235,238,242,246,249,253,257,261,265,269,273,277,281,285,289,293,297,301,305,309,313,317,321,325,329,333,337,341,345,349,353,357,361,365,369,373,377,381,385,389,393,396,400,404,408,412,416,420,423,426,429,432,436,440,444,448,452,456,460,464,468,472,476,480,484,488,492,495,499,503,507,511,515,519,523,527,531,534,538,542,546,550,553,557,561,565,568,571,575,579,582],{"key":84,"label":85,"href":86},"downloads.desktop","Desktop download page","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Fdownload",{"key":88,"label":89,"href":90},"downloads.macOS.dmgArm64","macOS DMG Apple Silicon","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fpieces_for_x\u002Fdmg-arm64\u002Fdownload",{"key":92,"label":93,"href":94},"downloads.macOS.dmgIntel","macOS DMG Intel","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fpieces_for_x\u002Fdmg\u002Fdownload",{"key":96,"label":97,"href":98},"downloads.macOS.pkg","macOS PKG","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fmacos_packaging\u002Fpkg\u002Fdownload",{"key":100,"label":101,"href":102},"downloads.windows.appinstaller","Windows App Installer","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fappinstaller\u002Fpieces_for_x.appinstaller",{"key":104,"label":105,"href":106},"downloads.windows.exe","Windows EXE","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fpieces_for_x\u002Fwindows-exe\u002Fdownload",{"key":108,"label":109,"href":110},"downloads.windows.suiteManager","Windows Suite Manager","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fpieces_suite_windows\u002Fappinstaller\u002Fdownload",{"key":112,"label":113,"href":114},"downloads.linux.flatpakRepo","Linux Flatpak repository","https:\u002F\u002Fbuilds.pieces.app\u002Fpieces-flatpak-repo\u002Fpieces-flatpak.flatpakrepo",{"key":116,"label":117,"href":118},"downloads.linux.snapDesktop","Linux Snap Desktop","https:\u002F\u002Fsnapcraft.io\u002Fpieces-for-developers",{"key":120,"label":121,"href":122},"downloads.linux.snapPiecesOS","Linux Snap PiecesOS","https:\u002F\u002Fsnapcraft.io\u002Fpieces-os",{"key":124,"label":125,"href":126},"downloads.piecesOS.macOS.dmgArm64","PiecesOS macOS DMG Apple Silicon","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fos_server\u002Fdmg-arm64\u002Fdownload",{"key":128,"label":129,"href":130},"downloads.piecesOS.macOS.dmgIntel","PiecesOS macOS DMG Intel","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fos_server\u002Fdmg\u002Fdownload",{"key":132,"label":133,"href":134},"downloads.piecesOS.windows.appinstaller","PiecesOS Windows App Installer","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fappinstaller\u002Fos_server.appinstaller",{"key":136,"label":137,"href":138},"downloads.piecesOS.windows.exe","PiecesOS Windows EXE","https:\u002F\u002Fbuilds.pieces.app\u002Fstages\u002Fproduction\u002Fos_server\u002Fwindows-exe\u002Fdownload",{"key":140,"label":141,"href":142},"downloads.guides.macOS","macOS installation guide","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Fmacos-installation-guide",{"key":144,"label":145,"href":146},"downloads.guides.windows","Windows installation guide","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Fwindows-installation-guide",{"key":148,"label":149,"href":150},"downloads.guides.linux","Linux installation guide","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Flinux-installation-guide",{"key":152,"label":153,"href":154},"downloads.guides.piecesOS","PiecesOS manual installation","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies\u002Fpieces-os\u002Fmanual-installation",{"key":156,"label":157,"href":158},"extensions.chrome","Chrome extension","https:\u002F\u002Fchrome.google.com\u002Fwebstore\u002Fdetail\u002Fpieces-save-code-snippets\u002Figbgibhbfonhmjlechmeefimncpekepm",{"key":160,"label":161,"href":162},"extensions.firefox","Firefox add-on","https:\u002F\u002Faddons.mozilla.org\u002Fen-US\u002Ffirefox\u002Faddon\u002Fpieces-save-code-from-the-web\u002F",{"key":164,"label":165,"href":166},"extensions.edge","Edge add-on","https:\u002F\u002Fmicrosoftedge.microsoft.com\u002Faddons\u002Fdetail\u002Fpieces-save-code-snippet\u002Fhglfimcdgonaeeobjckfdabcldfidmim",{"key":168,"label":169,"href":170},"extensions.vscode","VS Code extension","https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=MeshIntelligentTechnologiesInc.pieces-vscode",{"key":172,"label":173,"href":174},"extensions.visualStudio","Visual Studio extension","https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=MeshIntelligentTechnologiesInc.PiecesVisualStudio",{"key":176,"label":177,"href":178},"extensions.jetbrains","JetBrains plugin","https:\u002F\u002Fplugins.jetbrains.com\u002Fplugin\u002F17328-pieces--save-search-share--reuse-code-snippets",{"key":180,"label":181,"href":182},"extensions.obsidian","Obsidian plugin","https:\u002F\u002Fobsidian.md\u002Fplugins?id=pieces-for-developers",{"key":184,"label":185,"href":186},"extensions.sublime","Sublime package","https:\u002F\u002Fpackagecontrol.io\u002Fpackages\u002FPieces",{"key":188,"label":189,"href":190},"extensions.neovim","Neovim plugin","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fplugin_neo_vim",{"key":192,"label":193,"href":194},"extensions.jupyterlab","JupyterLab plugin","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fjupyterlab-pieces",{"key":196,"label":197,"href":198},"extensions.cli","Pieces CLI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fpieces-cli\u002F",{"key":200,"label":201,"href":202},"docs.home","Documentation home","https:\u002F\u002Fdocs.pieces.app",{"key":204,"label":205,"href":206},"docs.getStarted","Get started docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces",{"key":208,"label":209,"href":210},"docs.api","API docs","https:\u002F\u002Fdocs.pieces.app\u002Fapi",{"key":212,"label":213,"href":214},"docs.desktop.overview","Desktop overview","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop",{"key":216,"label":217,"href":218},"docs.desktop.onboarding","Desktop onboarding","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Fonboarding",{"key":220,"label":221,"href":222},"docs.desktop.timeline","Desktop timeline docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Ftimeline",{"key":224,"label":225,"href":226},"docs.desktop.summaries","Desktop summaries docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Fsingle-click-summaries",{"key":228,"label":229,"href":230},"docs.desktop.search","Desktop conversational search docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Fconversational-search",{"key":232,"label":233,"href":234},"docs.desktop.drive","Desktop drive docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fdesktop\u002Fdrive",{"key":236,"label":237,"href":86},"docs.desktop.download","Desktop download docs",{"key":239,"label":240,"href":241},"docs.piecesOS.overview","PiecesOS overview docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies",{"key":243,"label":244,"href":245},"docs.piecesOS.details","PiecesOS details docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies\u002Fpieces-os",{"key":247,"label":248,"href":154},"docs.piecesOS.install","PiecesOS install docs",{"key":250,"label":251,"href":252},"docs.piecesOS.quickMenu","PiecesOS quick menu docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies\u002Fpieces-os\u002Fquick-menu",{"key":254,"label":255,"href":256},"docs.piecesOS.storage","On-device storage docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies\u002Fon-device-storage",{"key":258,"label":259,"href":260},"docs.piecesOS.troubleshooting","PiecesOS troubleshooting docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fcore-dependencies\u002Fpieces-os\u002Ftroubleshooting",{"key":262,"label":263,"href":264},"docs.mcp.overview","MCP overview docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp",{"key":266,"label":267,"href":268},"docs.mcp.cursor","MCP Cursor docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fcursor",{"key":270,"label":271,"href":272},"docs.mcp.vscode","MCP VS Code docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fvs-code",{"key":274,"label":275,"href":276},"docs.mcp.claudeDesktop","MCP Claude Desktop docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fclaude-desktop",{"key":278,"label":279,"href":280},"docs.mcp.claudeCode","MCP Claude Code docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fclaude-code",{"key":282,"label":283,"href":284},"docs.mcp.claudeCowork","MCP Claude Cowork docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fclaude-cowork",{"key":286,"label":287,"href":288},"docs.mcp.githubCopilot","MCP GitHub Copilot docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fgithub-copilot",{"key":290,"label":291,"href":292},"docs.mcp.goose","MCP Goose docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fgoose",{"key":294,"label":295,"href":296},"docs.mcp.windsurf","MCP Windsurf docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fwindsurf",{"key":298,"label":299,"href":300},"docs.mcp.zed","MCP Zed docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fzed",{"key":302,"label":303,"href":304},"docs.mcp.jetbrains","MCP JetBrains docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fjetbrains-ides",{"key":306,"label":307,"href":308},"docs.mcp.continueDev","MCP Continue docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fcontinue-dev",{"key":310,"label":311,"href":312},"docs.mcp.cline","MCP Cline docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fcline",{"key":314,"label":315,"href":316},"docs.mcp.raycast","MCP Raycast docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fraycast",{"key":318,"label":319,"href":320},"docs.mcp.rovoDevCli","MCP Rovo Dev CLI docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Frovo-dev-cli",{"key":322,"label":323,"href":324},"docs.mcp.openaiCodexCli","MCP OpenAI Codex CLI docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fopenai-codex-cli",{"key":326,"label":327,"href":328},"docs.mcp.googleGeminiCli","MCP Google Gemini CLI docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fgoogle-gemini-cli",{"key":330,"label":331,"href":332},"docs.mcp.amazonQ","MCP Amazon Q docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Famazon-q-developer",{"key":334,"label":335,"href":336},"docs.mcp.chatgptDev","MCP ChatGPT Developer Mode docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fchatgpt-developer-mode",{"key":338,"label":339,"href":340},"docs.mcp.openclaw","MCP OpenClaw docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fopenclaw",{"key":342,"label":343,"href":344},"docs.mcp.mcpRemote","MCP Remote docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fmcp-remote",{"key":346,"label":347,"href":348},"docs.mcp.ngrok","MCP ngrok docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmcp\u002Fngrok-setup",{"key":350,"label":351,"href":352},"docs.troubleshooting.macOS","macOS troubleshooting docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Ftroubleshooting\u002Fmacos",{"key":354,"label":355,"href":356},"docs.troubleshooting.windows","Windows troubleshooting docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Ftroubleshooting\u002Fwindows",{"key":358,"label":359,"href":360},"docs.troubleshooting.linux","Linux troubleshooting docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fmeet-pieces\u002Ftroubleshooting\u002Flinux",{"key":362,"label":363,"href":364},"docs.privacy","Privacy and security docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fprivacy-security-your-data",{"key":366,"label":367,"href":368},"docs.support","Support docs","https:\u002F\u002Fdocs.pieces.app\u002Fproducts\u002Fsupport",{"key":370,"label":371,"href":372},"portal.home","Pieces portal","https:\u002F\u002Fportal.pieces.app",{"key":374,"label":375,"href":376},"site.home","Website home","https:\u002F\u002Fpieces.app",{"key":378,"label":379,"href":380},"site.about","About page","https:\u002F\u002Fpieces.app\u002Fabout",{"key":382,"label":383,"href":384},"site.features","Features page","https:\u002F\u002Fpieces.app\u002Ffeatures",{"key":386,"label":387,"href":388},"site.plugins","Plugins page","https:\u002F\u002Fpieces.app\u002Fplugins",{"key":390,"label":391,"href":392},"site.contact","Contact page","https:\u002F\u002Fpieces.app\u002Fcontact",{"key":394,"label":36,"href":395},"site.changelog","https:\u002F\u002Fpieces.app\u002Fchangelog",{"key":397,"label":398,"href":399},"site.news","News","https:\u002F\u002Fpieces.app\u002Fnews",{"key":401,"label":402,"href":403},"site.events","Community events","https:\u002F\u002Fpieces.app\u002Fcommunity\u002Fevents",{"key":405,"label":406,"href":407},"site.userStories","User stories","https:\u002F\u002Fpieces.app\u002Fuser-stories",{"key":409,"label":410,"href":411},"site.academy","Academy","https:\u002F\u002Fpieces.app\u002Flearn\u002Facademy",{"key":413,"label":414,"href":415},"site.support","Website support","https:\u002F\u002Fpieces.app\u002Fsupport",{"key":417,"label":418,"href":419},"site.standup","Standup","https:\u002F\u002Fpieces.app\u002Fstandup",{"key":421,"label":33,"href":422},"site.blog","https:\u002F\u002Fcode.pieces.app\u002Fblog",{"key":424,"label":51,"href":425},"social.discord","https:\u002F\u002Fdiscord.gg\u002Fgetpieces",{"key":427,"label":54,"href":428},"social.x","https:\u002F\u002Fx.com\u002Fgetpieces",{"key":430,"label":431,"href":428},"social.twitter","Twitter",{"key":433,"label":434,"href":435},"social.instagram","Instagram","https:\u002F\u002Fwww.instagram.com\u002Fgetpieces\u002F",{"key":437,"label":438,"href":439},"social.tiktok","TikTok","https:\u002F\u002Fwww.tiktok.com\u002F@getpieces",{"key":441,"label":442,"href":443},"social.linkedin","LinkedIn","https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fgetpieces\u002F",{"key":445,"label":446,"href":447},"social.youtube","YouTube","https:\u002F\u002Fyoutube.com\u002F@getpieces",{"key":449,"label":450,"href":451},"github.org","GitHub organization","https:\u002F\u002Fgithub.com\u002Fpieces-app",{"key":453,"label":454,"href":455},"github.support","GitHub support","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fsupport",{"key":457,"label":458,"href":459},"github.issues","GitHub issues","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fsupport\u002Fissues",{"key":461,"label":462,"href":463},"github.discussions","GitHub discussions","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fsupport\u002Fdiscussions",{"key":465,"label":466,"href":467},"github.documentation","GitHub documentation","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fdocumentation",{"key":469,"label":470,"href":471},"github.opensource","GitHub open source","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fopensource",{"key":473,"label":474,"href":475},"github.sdks.python","Python SDK","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fpieces-os-client-sdk-for-python",{"key":477,"label":478,"href":479},"github.sdks.typescript","TypeScript SDK","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fpieces-os-client-sdk-for-typescript",{"key":481,"label":482,"href":483},"github.sdks.dart","Dart SDK","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fpieces-os-client-sdk-for-dart",{"key":485,"label":486,"href":487},"github.sdks.kotlin","Kotlin SDK","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fpieces-os-client-sdk-for-kotlin",{"key":489,"label":490,"href":491},"github.plugins.obsidian","Obsidian plugin repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fobsidian-pieces",{"key":493,"label":494,"href":194},"github.plugins.jupyterlab","JupyterLab plugin repository",{"key":496,"label":497,"href":498},"github.plugins.sublime","Sublime plugin repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fplugin_sublime",{"key":500,"label":501,"href":502},"github.plugins.neovim","Neovim plugin repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fplugin_neovim",{"key":504,"label":505,"href":506},"github.cliAgent","CLI agent repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fcli-agent",{"key":508,"label":509,"href":510},"github.mcpDart","MCP Dart repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fmcp_dart",{"key":512,"label":513,"href":514},"github.awesomePieces","Awesome Pieces repository","https:\u002F\u002Fgithub.com\u002Fpieces-app\u002Fawesome-pieces",{"key":516,"label":517,"href":518},"legal.privacyPolicy","Privacy policy","https:\u002F\u002Fpieces.app\u002Flegal\u002Fprivacy-policy",{"key":520,"label":521,"href":522},"legal.refundPolicy","Refund policy","https:\u002F\u002Fpieces.app\u002Flegal\u002Frefund-policy",{"key":524,"label":525,"href":526},"legal.terms","Terms","https:\u002F\u002Fpieces.app\u002Flegal\u002Fterms",{"key":528,"label":529,"href":530},"legal.security","Legal security","https:\u002F\u002Fpieces.app\u002Flegal\u002Fsecurity",{"key":532,"label":533,"href":447},"videos.youtubeChannel","YouTube channel",{"key":535,"label":536,"href":537},"videos.gettingStartedDesktop","Getting started desktop video","https:\u002F\u002Fyoutu.be\u002FdUr1lRM_TYk",{"key":539,"label":540,"href":541},"videos.snippetDiscovery","Snippet discovery video","https:\u002F\u002Fyoutu.be\u002FG6vb1USw-30",{"key":543,"label":544,"href":545},"sales.bookACall","Book a sales call","https:\u002F\u002Fcalendar.app.google\u002FWVUDtUfNy5Vst3sH7",{"key":547,"label":548,"href":549},"sales.enterprise","Enterprise form","https:\u002F\u002Fgetpieces.typeform.com\u002Fto\u002FaVQFTvpE",{"key":551,"label":552,"href":463},"sales.feedback","Feedback discussions",{"key":554,"label":555,"href":556},"sales.earlyAccess","Early access form","https:\u002F\u002Fgetpieces.typeform.com\u002Fearlyaccess",{"key":558,"label":559,"href":560},"sales.supportEmail","Support email","mailto:support@pieces.app",{"key":562,"label":563,"href":564},"routes.home","Home route","\u002F",{"key":566,"label":567,"href":46},"routes.about","About route",{"key":569,"label":570,"href":16},"routes.downloads","Downloads route",{"key":572,"label":573,"href":574},"routes.pricing","Pricing route","\u002Fpricing",{"key":576,"label":577,"href":578},"routes.security","Security route","\u002Fsecurity",{"key":580,"label":581,"href":49},"routes.enterprise","Enterprise route",{"key":583,"label":584,"href":585},"routes.thankYou","Thank you \u002F download route","\u002Fthank-you",{},"data\u002Fshared\u002Furls","P27xKEauu8D-8sfyr0wR4giF0teFSaCuAQ8kgcICQdI",{"id":590,"title":591,"author":592,"authorPhoto":593,"authorPhotoAlt":594,"authorSlug":595,"body":596,"buttonText":1632,"buttonUrl":206,"category":1633,"date":1634,"description":1635,"draft":1636,"editorsPick":1636,"extension":1637,"featured":20,"image":1638,"imageAlt":594,"meta":1639,"navigation":20,"ogImage":594,"ogImageAlt":594,"path":1640,"seo":1641,"stem":1642,"tags":594,"__hash__":1643},"blog\u002Fblog\u002Fnano-models.md","Nano-Models: a recent breakthrough as the Pieces team brings LTM‑2.5 to life 🎉","Tsavo Knott","https:\u002F\u002Fstorage.googleapis.com\u002Fpieces-marketing-website\u002Fimages\u002Fblog\u002Fscott-hanselman-ai-summit\u002Fauthor.jpeg",null,"tsavo-knott",{"type":597,"value":598,"toc":1610},"minimark",[599,620,623,626,629,632,635,638,641,646,658,742,746,752,755,760,763,871,875,878,918,921,925,928,932,949,953,970,974,991,1002,1006,1013,1143,1147,1150,1154,1157,1270,1275,1301,1306,1331,1335,1338,1435,1440,1457,1462,1485,1506,1510,1515,1522,1527,1536,1541,1553,1558,1578,1582,1595,1598,1601,1604,1607],[600,601,602,603,610,611,615,616,619],"p",{},"In the pursuit of building ",[604,605,609],"a",{"href":606,"rel":607},"https:\u002F\u002Fpieces.app\u002Ffeatures\u002Flong-term-memory",[608],"nofollow","long-term Artificial Memory"," at the OS level, understanding ",[612,613,614],"em",{},"when"," a user wants to retrieve information is just as crucial as ",[612,617,618],{},"what"," they want.",[600,621,622],{},"In the early days, every step of that retrieval pipeline, from intent classification through span extraction, normalization, enrichment, relevance scoring, formatting, and upload, ran through cloud-hosted LLMs.",[600,624,625],{},"That meant 8–11 preprocessing tasks before touching the memory store, another 2–4 post-processing tasks afterward, and finally a round-trip to a remote model to compose the answer.",[600,627,628],{},"The result?",[600,630,631],{},"Cumulative latency that drags time-to-first-token into the seconds, accuracy hurdles at each stage, user data exposed in transit, and token bills that balloon with every query.",[600,633,634],{},"Our breakthrough with LTM-2.5: two purpose-built on-device nano-models that offload temporal understanding entirely to local hardware — one for interpreting the user's temporal intent, the other for extracting the precise time span(s) implied by their language.",[600,636,637],{},"These specialized models are the result of extensive knowledge distillation from larger foundation models, quantized and pruned to run efficiently on consumer hardware.",[600,639,640],{},"Now, the entire 10–15 step pipeline lives on-device, preserving privacy, slashing costs, and taking the deterministic retrieval of long-term context down from seconds to milliseconds in latency.",[642,643,645],"h2",{"id":644},"when-to-leverage-the-temporal-model","When to leverage the temporal model",[600,647,648,649,653,654,657],{},"Our pipeline depends on two critical steps: determining ",[650,651,652],"strong",{},"intent"," first, then generating one or more ",[650,655,656],{},"time ranges"," representative of the user's natural-language query:",[659,660,661,678],"table",{},[662,663,664],"thead",{},[665,666,667,673],"tr",{},[668,669,670],"th",{},[650,671,672],{},"Use Case",[668,674,675],{},[650,676,677],{},"Description",[679,680,681,692,702,712,722,732],"tbody",{},[665,682,683,689],{},[684,685,686],"td",{},[650,687,688],{},"Content Retrieval",[684,690,691],{},"Fetching past events (\"What was I working on just now?\")",[665,693,694,699],{},[684,695,696],{},[650,697,698],{},"Action \u002F Scheduling",[684,700,701],{},"Setting reminders or appointments (\"Remind me in two hours\")",[665,703,704,709],{},[684,705,706],{},[650,707,708],{},"Future Information \u002F Planning",[684,710,711],{},"Forecasting or \"next week\" inquiries (\"What am I doing tomorrow afternoon?\")",[665,713,714,719],{},[684,715,716],{},[650,717,718],{},"Current Status",[684,720,721],{},"Real-time checks (\"What am I doing right now?\")",[665,723,724,729],{},[684,725,726],{},[650,727,728],{},"Temporal – General",[684,730,731],{},"Ambiguous or loosely specified time references (\"Show me last week around Friday evening\")",[665,733,734,739],{},[684,735,736],{},[650,737,738],{},"Non-Temporal",[684,740,741],{},"Queries without a time component (\"Explain the concept of recursion.\")",[642,743,745],{"id":744},"temporal-range-generation","Temporal range generation",[600,747,748,749,751],{},"Once we've determined that a query requires temporal memory access, we need to precisely identify ",[650,750,614],{}," to search in the user's activity timeline.",[600,753,754],{},"This is where our second nano-model comes into play:",[756,757,759],"h3",{"id":758},"range-types-and-boundaries","Range types and boundaries",[600,761,762],{},"The temporal span predictor handles several distinct types of time references:",[659,764,765,789],{},[662,766,767],{},[665,768,769,774,779,784],{},[668,770,771],{},[650,772,773],{},"Range Type",[668,775,776],{},[650,777,778],{},"Example Query",[668,780,781],{},[650,782,783],{},"Generated Span",[668,785,786],{},[650,787,788],{},"Search Strategy",[679,790,791,807,823,839,855],{},[665,792,793,798,801,804],{},[684,794,795],{},[650,796,797],{},"Point-in-time",[684,799,800],{},"\"Show me what I was doing at 2pm yesterday\"",[684,802,803],{},"Single timestamp with narrow context window",[684,805,806],{},"Precise timestamp lookup with small buffer",[665,808,809,814,817,820],{},[684,810,811],{},[650,812,813],{},"Explicit period",[684,815,816],{},"\"What emails did I receive between Monday and Wednesday?\"",[684,818,819],{},"Clearly defined start\u002Fend boundaries",[684,821,822],{},"Bounded range search with exact limits",[665,824,825,830,833,836],{},[684,826,827],{},[650,828,829],{},"Implicit period",[684,831,832],{},"\"What was I working on last week?\"",[684,834,835],{},"Inferred start\u002Fend based on cultural\u002Fcontextual norms",[684,837,838],{},"Automatically expanded to appropriate calendar boundaries",[665,840,841,846,849,852],{},[684,842,843],{},[650,844,845],{},"Relative recent",[684,847,848],{},"\"What was I just doing?\"",[684,850,851],{},"Short window counting backward from current time",[684,853,854],{},"Recency-prioritized retrieval with adaptive timespan",[665,856,857,862,865,868],{},[684,858,859],{},[650,860,861],{},"Fuzzy historical",[684,863,864],{},"\"Show me that article I read about quantum computing last summer\"",[684,866,867],{},"Broad date range with lower confidence boundaries",[684,869,870],{},"Expanded search space with relevance decay at boundaries",[756,872,874],{"id":873},"optimizing-the-temporal-search-space","Optimizing the temporal search space",[600,876,877],{},"The model doesn't just identify time boundaries — it also generates crucial metadata about search strategy:",[879,880,881,888,903,909],"ul",{},[882,883,884,887],"li",{},[650,885,886],{},"Confidence scores"," for timespan boundaries (enabling better retrieval when dates are ambiguous)",[882,889,890,893,894,898,899,902],{},[650,891,892],{},"Periodicity hints"," for recurring events (distinguishing ",[895,896,897],"code",{},"\"my Monday meeting\""," from ",[895,900,901],{},"\"last Monday's meeting\"",")",[882,904,905,908],{},[650,906,907],{},"Time-zone awareness"," for properly interpreting references when users travel",[882,910,911,914,915,902],{},[650,912,913],{},"Contextual weighting"," that prioritizes activity density over raw timestamps (e.g., for ",[895,916,917],{},"\"when I was working on the Smith project\"",[600,919,920],{},"This specialized temporal range extraction eliminates the need to scan the entire memory corpus for each query, dramatically reducing both computational load and latency while improving retrieval precision.",[642,922,924],{"id":923},"intention-differentiation-edge-cases","Intention differentiation & edge cases",[600,926,927],{},"Ensuring we route queries correctly between retrieval and planning:",[756,929,931],{"id":930},"retrieval-vs-planning","Retrieval vs. planning",[879,933,934,942],{},[882,935,936,939,940],{},[895,937,938],{},"\"What was I working on just now?\""," → ",[650,941,688],{},[882,943,944,939,947],{},[895,945,946],{},"\"What am I doing tomorrow afternoon?\"",[650,948,708],{},[756,950,952],{"id":951},"broad-vs-specific","Broad vs. specific",[879,954,955,963],{},[882,956,957,939,960,962],{},[895,958,959],{},"\"Show me last week around Friday evening\"",[650,961,688],{}," with a loose span",[882,964,965,939,968],{},[895,966,967],{},"\"Plan my weekend for next Friday evening\"",[650,969,708],{},[756,971,973],{"id":972},"temporal-vs-non-temporal","Temporal vs. non-temporal",[879,975,976,983],{},[882,977,978,939,981],{},[895,979,980],{},"\"What was the website I was just looking at?\"",[650,982,688],{},[882,984,985,939,988,990],{},[895,986,987],{},"\"Explain the concept of recursion.\"",[650,989,738],{}," (no memory lookup)",[600,992,993,994,997,998,1001],{},"By clearly distinguishing ",[650,995,996],{},"temporal retrieval"," (pulling historical context) from ",[650,999,1000],{},"temporal reference"," (scheduling or future-oriented intent), our on-device pipeline avoids misrouted cloud calls, cuts latency to the millisecond level, and maintains top-tier accuracy without sacrificing privacy or incurring hidden costs.",[642,1003,1005],{"id":1004},"examples-scenarios","Examples & scenarios",[600,1007,1008,1009,1012],{},"Below are representative user queries, each fed into our pipeline along with the user's local time in UTC (e.g. ",[895,1010,1011],{},"2025-04-17T16:43:02.151857+00:00","):",[1014,1015,1016,1050,1085,1114],"ol",{},[882,1017,1018,1021],{},[650,1019,1020],{},"Recent Activity Retrieval",[879,1022,1023,1029,1035,1044],{},[882,1024,1025,1028],{},[650,1026,1027],{},"Query:"," \"Could you tell me what I was just doing?\"",[882,1030,1031,1034],{},[650,1032,1033],{},"Classifier (23 ms):"," Content Retrieval",[882,1036,1037,1040,1041],{},[650,1038,1039],{},"Span Predictor (102 ms):"," ",[895,1042,1043],{},"2025-04-17T16:37:05.603Z – 2025-04-17T16:43:02.151857Z",[882,1045,1046,1049],{},[650,1047,1048],{},"Showcases:"," precise on-device extraction of the last few minutes of activity",[882,1051,1052,1055],{},[650,1053,1054],{},"Future Planning (Nuanced Task)",[879,1056,1057,1062,1068,1076],{},[882,1058,1059,1061],{},[650,1060,1027],{}," \"I will go to the store tomorrow.\"",[882,1063,1064,1067],{},[650,1065,1066],{},"Classifier (21 ms):"," Temporal – General",[882,1069,1070,1040,1073],{},[650,1071,1072],{},"Span Predictor:",[612,1074,1075],{},"N\u002FA",[882,1077,1078,1080,1081,1084],{},[650,1079,1048],{}," correctly ",[650,1082,1083],{},"not"," generating a past time-range for future intentions—an essential nuance",[882,1086,1087,1090],{},[650,1088,1089],{},"\"Just\" Retrieval Consistency",[879,1091,1092,1097,1102,1109],{},[882,1093,1094,1096],{},[650,1095,1027],{}," \"What was the website I was just looking at?\"",[882,1098,1099,1034],{},[650,1100,1101],{},"Classifier (22 ms):",[882,1103,1104,1040,1107],{},[650,1105,1106],{},"Span Predictor (108 ms):",[895,1108,1043],{},[882,1110,1111,1113],{},[650,1112,1048],{}," consistent span output across semantically similar \"just\" queries",[882,1115,1116,1119],{},[650,1117,1118],{},"Long-Range Historical Query",[879,1120,1121,1126,1130,1138],{},[882,1122,1123,1125],{},[650,1124,1027],{}," \"What was I working on last year around Thanksgiving?\"",[882,1127,1128,1034],{},[650,1129,1101],{},[882,1131,1132,1040,1135],{},[650,1133,1134],{},"Span Predictor (88 ms):",[895,1136,1137],{},"2024-11-01T00:00:00Z – 2024-11-30T23:59:59.999999Z",[882,1139,1140,1142],{},[650,1141,1048],{}," broad date-range generation for loosely specified historical periods",[642,1144,1146],{"id":1145},"benchmarks","Benchmarks",[600,1148,1149],{},"Tested on an Apple M1 Max (32 GB) under heavy load (30+ tabs, video, IDEs, messaging) to simulate real-world conditions:",[756,1151,1153],{"id":1152},"classification-results","Classification results",[600,1155,1156],{},"This table compares how well each model identifies the correct temporal intent label for a given sample.",[659,1158,1159,1193],{},[662,1160,1161],{},[665,1162,1163,1168,1173,1178,1183,1188],{},[668,1164,1165],{},[650,1166,1167],{},"Model Name",[668,1169,1170],{},[650,1171,1172],{},"Accuracy",[668,1174,1175],{},[650,1176,1177],{},"F1 (W)",[668,1179,1180],{},[650,1181,1182],{},"Prec (W)",[668,1184,1185],{},[650,1186,1187],{},"Recall (W)",[668,1189,1190],{},[650,1191,1192],{},"Samples\u002FSec",[679,1194,1195,1213,1232,1251],{},[665,1196,1197,1200,1203,1205,1208,1210],{},[684,1198,1199],{},"nano-temporal-intent (TIME Intent)",[684,1201,1202],{},"0.9930",[684,1204,1202],{},[684,1206,1207],{},"0.9931",[684,1209,1202],{},[684,1211,1212],{},"544.41",[665,1214,1215,1218,1221,1224,1227,1229],{},[684,1216,1217],{},"gemini-1.5-flash-002",[684,1219,1220],{},"0.8241",[684,1222,1223],{},"0.8384",[684,1225,1226],{},"0.8834",[684,1228,1220],{},[684,1230,1231],{},"9.14",[665,1233,1234,1237,1240,1243,1246,1248],{},[684,1235,1236],{},"gpt-4o",[684,1238,1239],{},"0.8634",[684,1241,1242],{},"0.8470",[684,1244,1245],{},"0.8698",[684,1247,1239],{},[684,1249,1250],{},"9.40",[665,1252,1253,1256,1259,1262,1265,1267],{},[684,1254,1255],{},"meta-llama\u002FLlama-3.2-3B-Instruct",[684,1257,1258],{},"0.4604",[684,1260,1261],{},"0.4094",[684,1263,1264],{},"0.4080",[684,1266,1258],{},[684,1268,1269],{},"92.43",[600,1271,1272],{},[650,1273,1274],{},"Legend: Classification Models",[879,1276,1277,1283,1289,1295],{},[882,1278,1279,1282],{},[650,1280,1281],{},"nano-temporal-intent (TIME Intent):"," Our on-device nano-model for intent classification—ultra-lightweight and lightning-fast inference.",[882,1284,1285,1288],{},[650,1286,1287],{},"gemini-1.5-flash-002:"," Google's mid-tier large language model via API; good accuracy but higher latency and cost.",[882,1290,1291,1294],{},[650,1292,1293],{},"gpt-4o:"," OpenAI's flagship multimodal LLM; strong performance at premium compute and pricing.",[882,1296,1297,1300],{},[650,1298,1299],{},"meta-llama\u002FLlama-3.2-3B-Instruct:"," A 3 billion-parameter open-weights LLM; lower accuracy but faster than cloud LLMs.",[600,1302,1303],{},[650,1304,1305],{},"Legend: Classification Metrics",[879,1307,1308,1314,1325],{},[882,1309,1310,1313],{},[650,1311,1312],{},"Accuracy:"," Proportion of samples for which the top-prediction matches the true class.",[882,1315,1316,1318,1319,1318,1321,1324],{},[650,1317,1177],{},", ",[650,1320,1182],{},[650,1322,1323],{},"Recall (W):"," Weighted F1-score, precision, and recall across all intent classes (accounts for class imbalances).",[882,1326,1327,1330],{},[650,1328,1329],{},"Samples\u002FSec:"," Number of inference calls the model can process per second. (higher is better)",[642,1332,1334],{"id":1333},"span-prediction-results","Span prediction results",[600,1336,1337],{},"This table measures how precisely each model extracts the correct time-span from text.",[659,1339,1340,1367],{},[662,1341,1342],{},[665,1343,1344,1348,1353,1358,1363],{},[668,1345,1346],{},[650,1347,1167],{},[668,1349,1350],{},[650,1351,1352],{},"E.C.O. Rate",[668,1354,1355],{},[650,1356,1357],{},"Avg IoU",[668,1359,1360],{},[650,1361,1362],{},"Exact Match",[668,1364,1365],{},[650,1366,1192],{},[679,1368,1369,1386,1403,1419],{},[665,1370,1371,1374,1377,1380,1383],{},[684,1372,1373],{},"nano-temporal-span-pred (TIME Range)",[684,1375,1376],{},"0.9450",[684,1378,1379],{},"0.9201",[684,1381,1382],{},"0.8659",[684,1384,1385],{},"785.39",[665,1387,1388,1391,1394,1397,1400],{},[684,1389,1390],{},"gemini-1.5-pro-002",[684,1392,1393],{},"0.2065",[684,1395,1396],{},"0.1865",[684,1398,1399],{},"0.1684",[684,1401,1402],{},"9.35",[665,1404,1405,1407,1410,1413,1416],{},[684,1406,1236],{},[684,1408,1409],{},"0.1767",[684,1411,1412],{},"0.1611",[684,1414,1415],{},"0.1535",[684,1417,1418],{},"9.47",[665,1420,1421,1423,1426,1429,1432],{},[684,1422,1255],{},[684,1424,1425],{},"0.1725",[684,1427,1428],{},"0.1640",[684,1430,1431],{},"0.1517",[684,1433,1434],{},"62.02",[600,1436,1437],{},[650,1438,1439],{},"Legend: Span Models",[879,1441,1442,1448],{},[882,1443,1444,1447],{},[650,1445,1446],{},"nano-temporal-span-pred (TIME Range):"," On-device span extractor optimized for low latency and high IoU.",[882,1449,1450,1318,1452,1318,1454,1456],{},[650,1451,1390],{},[650,1453,1236],{},[650,1455,1299],{}," LLMs & SLMs performing span extraction via API calls.",[600,1458,1459],{},[650,1460,1461],{},"Legend: Span Metrics",[879,1463,1464,1469,1474,1480],{},[882,1465,1466,1468],{},[650,1467,1352],{}," (Exact Coverage Overlap): Fraction of predicted spans that exactly match the gold span boundaries.",[882,1470,1471,1473],{},[650,1472,1357],{}," (Intersection-over-Union): Average overlap ratio between predicted and true spans.",[882,1475,1476,1479],{},[650,1477,1478],{},"Exact Match:"," Strict percentage of samples where predicted span text equals ground truth.",[882,1481,1482,1484],{},[650,1483,1329],{}," Span-prediction throughput on the benchmark hardware. (higher is better)",[1486,1487,1488],"blockquote",{},[600,1489,1490,1493,1494,1497,1498,1501,1502,1505],{},[650,1491,1492],{},"We observed SLMs running in the cloud"," on H100 GPU with vLLM incur $0.018 – $1.90 per run and took 15-25 min of compute time — our cascade delivers structured time-spans offline in ",[650,1495,1496],{},"milliseconds",", with ",[650,1499,1500],{},"zero API cost"," and ",[650,1503,1504],{},"full data privacy",".",[642,1507,1509],{"id":1508},"why-it-matters","Why it matters",[600,1511,1512],{},[650,1513,1514],{},"🏗️ Architectural Specialization",[600,1516,1517,1518,1521],{},"Breaking monolithic LLMs into nano-models for classification vs. span prediction yields ",[650,1519,1520],{},"massive gains"," in both accuracy and speed.",[600,1523,1524],{},[650,1525,1526],{},"🌐 Edge-First AI",[600,1528,1529,1530,1535],{},"Offline inference ",[604,1531,1534],{"href":1532,"rel":1533},"https:\u002F\u002Fpieces.app\u002Fblog\u002Foffline-ai",[608],"keeps sensitive data on-device"," — critical for medical, defense, and privacy-focused applications.",[600,1537,1538],{},[650,1539,1540],{},"💡 Energy & Cost Efficiency",[600,1542,1543,1548,1549,1552],{},[604,1544,1547],{"href":1545,"rel":1546},"https:\u002F\u002Fpieces.app\u002Fblog\u002Fsmall-language-models-outshine-large-language-models-enterprise-users",[608],"Eliminate token fees"," and slash compute budgets. This is the future of ",[650,1550,1551],{},"sustainable",", scaled AI on laptops, wearables, and IoT.",[600,1554,1555],{},[650,1556,1557],{},"🔬 Research Frontiers",[879,1559,1560,1566,1572],{},[882,1561,1562,1565],{},[650,1563,1564],{},"Task-specific:"," distillation, quantization, and final pruning for modular pipelines",[882,1567,1568,1571],{},[650,1569,1570],{},"Adaptive orchestration",": dynamic model selection based on compute availability",[882,1573,1574,1577],{},[650,1575,1576],{},"Hardware\u002Fsoftware:"," co-design for ultra-efficient inference",[642,1579,1581],{"id":1580},"conclusion","Conclusion",[600,1583,1584,1585,1318,1588,1591,1592,1505],{},"This nano-temporal pipeline is one of approximately 11 nano-models we're weaving into LTM-2.5 to make long-term memory formation and retrieval across your entire OS ",[650,1586,1587],{},"blazingly fast",[650,1589,1590],{},"highly accurate",", and ",[650,1593,1594],{},"privacy-first",[600,1596,1597],{},"Innovation isn't about bigger models — it's about smarter, specialized models that deliver tangible benefits in real-world applications.",[600,1599,1600],{},"By focusing on modular, purpose-built AI systems that run entirely on-device, we're redefining what's possible for intelligent, responsive computing that respects user privacy while dramatically reducing cost and latency.",[600,1602,1603],{},"We can't wait to share more as we push the boundaries of on-device AI in the world of OS-level Long-Term Memory.",[600,1605,1606],{},"Lastly, I would be remiss if I didn't mention the obvious: none of this would be possible without the incredible creativity, dedication, and perseverance from the team behind Pieces.",[600,1608,1609],{},"I’ll close with a special shout out to our ML team and a extra special shout out to Antreas Antoniou and Sam Jones for believing in the approach and turning these first-principal theories into breakthroughs ✨",{"title":1611,"searchDepth":1612,"depth":1612,"links":1613},"",2,[1614,1615,1620,1625,1626,1629,1630,1631],{"id":644,"depth":1612,"text":645},{"id":744,"depth":1612,"text":745,"children":1616},[1617,1619],{"id":758,"depth":1618,"text":759},3,{"id":873,"depth":1618,"text":874},{"id":923,"depth":1612,"text":924,"children":1621},[1622,1623,1624],{"id":930,"depth":1618,"text":931},{"id":951,"depth":1618,"text":952},{"id":972,"depth":1618,"text":973},{"id":1004,"depth":1612,"text":1005},{"id":1145,"depth":1612,"text":1146,"children":1627},[1628],{"id":1152,"depth":1618,"text":1153},{"id":1333,"depth":1612,"text":1334},{"id":1508,"depth":1612,"text":1509},{"id":1580,"depth":1612,"text":1581},"Get started","Product Updates","2025-04-17T00:00:00.000Z","Discover the latest breakthrough in AI with Nano-Models as the Pieces Team unveils LTM‑2.5. A game-changer for AI-powered development!",false,"md","https:\u002F\u002Fstorage.googleapis.com\u002Fpieces-marketing-website\u002Fimages\u002Fblog\u002Fnano-models\u002Fhero.png",{},"\u002Fblog\u002Fnano-models",{"title":591,"description":1635},"blog\u002Fnano-models","5haJpujWqr9UXo9jhAjvmOsKWtK6VzXYwNLrmY26LCQ",{"id":1645,"title":592,"body":1646,"description":1650,"draft":1636,"extension":1637,"meta":1653,"navigation":20,"path":1654,"photo":1655,"photoAlt":594,"seo":1656,"stem":1657,"__hash__":1658},"authors\u002Fauthors\u002Ftsavo-knott.md",{"type":597,"value":1647,"toc":1651},[1648],[600,1649,1650],{},"Founder and CEO of Pieces, Tsavo is a seasoned entrepreneur and adept at scaling technical products, evidenced by a reach of over 100,000 users across 27 countries in 18 languages. His previous companies, Runtime and MeshMyCampus, have been open-sourced to Google Chrome and acquired by Idera. In the public sector, Tsavo also serves on the State Committee for Computer Science in Ohio and helped contribute to the upcoming 1% for CS Bill.",{"title":1611,"searchDepth":1612,"depth":1612,"links":1652},[],{},"\u002Fauthors\u002Ftsavo-knott","https:\u002F\u002Fstorage.googleapis.com\u002Fpieces-marketing-website\u002Fimages\u002Fauthors\u002Ftsavo-knott.png",{"title":592,"description":1650},"authors\u002Ftsavo-knott","ixnEcreSWukc0HHLf2DcraSN8P-1EyddtcBC8JG2EDY"]