[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:trellis":3},"\u003Cp align=\"center\">\n\u003Cpicture>\n\u003Csource srcset=\"assets\u002Ftrellis.png\" media=\"(prefers-color-scheme: dark)\">\u003C\u002Fsource>\n\u003Csource srcset=\"assets\u002Ftrellis.png\" media=\"(prefers-color-scheme: light)\">\u003C\u002Fsource>\n\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fmindfold-ai\u002Ftrellis\u002FHEAD\u002Fassets\u002Ftrellis.png\" alt=\"Trellis Logo\" width=\"500\" \u002F>\n\u003C\u002Fpicture>\n\u003C\u002Fp>\u003Cp align=\"center\">\n\u003Cstrong>An out-of-the-box engineering framework for AI coding.\u003C\u002Fstrong>\u003Cbr \u002F>\n\u003Csub>AI writes code fast, but every session it starts from scratch — no memory of your project, your conventions, or your team's requirements. Trellis persists specs, tasks, and memory into your repo, so any coding agent works to your engineering standards.\u003C\u002Fsub>\n\u003C\u002Fp>\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmindfold-ai\u002Ftrellis\u002Fblob\u002FHEAD\u002FREADME_CN.md\" rel=\"nofollow ugc noopener\">简体中文\u003C\u002Fa> •\n\u003Ca href=\"https:\u002F\u002Fdocs.trytrellis.app\u002F\" rel=\"nofollow ugc noopener\">Docs\u003C\u002Fa> •\n\u003Ca href=\"https:\u002F\u002Fdocs.trytrellis.app\u002Fstart\u002Finstall-and-first-task\" rel=\"nofollow ugc noopener\">Quick Start\u003C\u002Fa> •\n\u003Ca href=\"https:\u002F\u002Fdocs.trytrellis.app\u002Fadvanced\u002Fmulti-platform\" rel=\"nofollow ugc noopener\">Supported Platforms\u003C\u002Fa> •\n\u003Ca href=\"https:\u002F\u002Fdocs.trytrellis.app\u002Fstart\u002Freal-world-scenarios\" rel=\"nofollow ugc noopener\">Use Cases\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@mindfoldhq\u002Ftrellis\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@mindfoldhq\u002Ftrellis.svg?style=flat-square&color=2563eb\" alt=\"npm version\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@mindfoldhq\u002Ftrellis\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdw\u002F@mindfoldhq\u002Ftrellis?style=flat-square&color=cb3837&label=downloads\" alt=\"npm downloads\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmindfold-ai\u002FTrellis\u002Fblob\u002Fmain\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-AGPL--3.0-16a34a.svg?style=flat-square\" alt=\"license\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmindfold-ai\u002FTrellis\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmindfold-ai\u002FTrellis?style=flat-square&color=eab308\" alt=\"stars\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdocs.trytrellis.app\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-trytrellis.app-0f766e?style=flat-square\" alt=\"docs\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002FtWcCZ3aRHc\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?style=flat-square&logo=discord&logoColor=white\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmindfold-ai\u002FTrellis\u002Fissues\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fmindfold-ai\u002FTrellis?style=flat-square&color=e67e22\" alt=\"open issues\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmindfold-ai\u002FTrellis\u002Fpulls\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-pr\u002Fmindfold-ai\u002FTrellis?style=flat-square&color=9b59b6\" alt=\"open PRs\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Fmindfold-ai\u002FTrellis\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAsk-DeepWiki-blue?style=flat-square\" alt=\"Ask DeepWiki\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fchatgpt.com\u002F?q=Explain+the+project+mindfold-ai\u002FTrellis+on+GitHub\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAsk-ChatGPT-74aa9c?style=flat-square&logo=openai&logoColor=white\" alt=\"Ask ChatGPT\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fmindfold-ai\u002Ftrellis\u002FHEAD\u002Fassets\u002Ftrellis-demo.gif\" alt=\"Trellis workflow demo\" width=\"100%\" \u002F>\n\u003C\u002Fp>\u003Ch2>Why Trellis?\u003C\u002Fh2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Capability\u003C\u002Fth>\n\u003Cth>What it changes\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>\u003Cstrong>Auto-injected specs\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Write conventions once in \u003Ccode>.trellis\u002Fspec\u002F\u003C\u002Fcode>, then let Trellis inject the relevant context into each session instead of repeating yourself.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Task-centered workflow\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Keep PRDs, implementation context, review context, and task status in \u003Ccode>.trellis\u002Ftasks\u002F\u003C\u002Fcode> so AI work stays structured.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Project memory\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Journals in \u003Ccode>.trellis\u002Fworkspace\u002F\u003C\u002Fcode> preserve what happened last time, so each new session starts with real context.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Team-shared standards\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Specs live in the repo, so one person's hard-won workflow or rule can benefit the whole team.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Multi-platform setup\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Bring the same Trellis structure to 20 AI coding platforms instead of rebuilding your workflow per tool.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2>Prerequisites:\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Node.js\u003C\u002Fstrong> >= 18\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Python\u003C\u002Fstrong> >= 3.9\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Quick Start\u003C\u002Fh2>\n\u003Cpre>\u003Ccode class=\"language-bash\"># 1. Install Trellis\nnpm install -g @mindfoldhq\u002Ftrellis@latest\n\n# 2. Initialize in your repo\ntrellis init -u your-name\n\n# 3. Or initialize with the platforms you actua\n\u003C\u002Fcode>\u003C\u002Fpre>\n",1785276851359]