[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75750":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":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},75750,"lavish-axi","kunchenguid\u002Flavish-axi","kunchenguid","HTML is the new markdown. Lavish is the new editor for your HTML artifacts.","",null,"JavaScript",358,25,101,4,0,47,194,256,207,94.24,"MIT License",false,"main",[],"2026-06-12 04:01:18","\u003Ch1 align=\"center\">lavish-axi\u003C\u002Fh1>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkunchenguid\u002Flavish-axi\u002Factions\u002Fworkflows\u002Fci.yml\"\n    >\u003Cimg alt=\"CI\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fkunchenguid\u002Flavish-axi\u002Fci.yml?style=flat-square&label=ci\"\n  \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkunchenguid\u002Flavish-axi\u002Factions\u002Fworkflows\u002Frelease-please.yml\"\n    >\u003Cimg alt=\"Release\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fkunchenguid\u002Flavish-axi\u002Frelease-please.yml?style=flat-square&label=release\"\n  \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Flavish-axi\"\n    >\u003Cimg alt=\"npm\" src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Flavish-axi?style=flat-square\"\n  \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows-blue?style=flat-square\"\n    >\u003Cimg alt=\"Platform\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows-blue?style=flat-square\"\n  \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fx.com\u002Fkunchenguid\"\n    >\u003Cimg alt=\"X\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FX-@kunchenguid-black?style=flat-square\"\n  \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FWsy2NpnZDu\"\n    >\u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1439901831038763092?style=flat-square&label=discord\"\n  \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">For when a rich editor is not rich enough.\u003C\u002Fh3>\n\n\u003Cp align=\"center\">\n  \u003Cimg alt=\"Lavish Editor demo\" src=\"lavish-editor-marketing\u002Frenders\u002Flavish-editor-marketing.gif\" width=\"960\" \u002F>\n\u003C\u002Fp>\n\nHTML is the new markdown. Lavish is the new editor for your HTML artifacts.\n\nAgents are good at producing rich HTML artifacts, but the human-agent collaboration loop on such artifacts is lacking and falls back into screenshots and long responses for “tell me what to change.”\nThat loses the thing HTML is best at: interactivity.\n\nLavish Editor opens agent-generated HTML files in a local browser, lets you pinpoint elements or selected text and send feedback to the agent to address.\n\n- **Local only** - Work with your local HTML artifacts with a local CLI. Zero cloud dependency.\n- **Human-AI collaboration** - Annotate elements, selected text ranges, and send messages to the agent without leaving Lavish Editor.\n- **Battery included** - Lavish Editor teaches your agent good visualization for common use cases such as technial plans, design explorations and more out of the box.\n\nLavish Editor is an [AXI](https:\u002F\u002Faxi.md), which means -\n\n- It's just a CLI any capable agent can run without setup.\n- No skills required. Agents learn to use AXIs by using them.\n- It's optimized for agent ergonomics. TOON output, long polling, and contextual disclosure making it highly token efficient.\n\n## Quick Start\n\nJust tell your agent:\n\n```sh\nUse `npx lavish-axi` to write a technical plan for what we discussed.\n```\n\n## Install\n\n**npm**\n\n```sh\nnpm install -g lavish-axi\n```\n\n**From source**\n\n```sh\ngit clone https:\u002F\u002Fgithub.com\u002Fkunchenguid\u002Flavish-axi.git\ncd lavish-axi\npnpm install --frozen-lockfile\npnpm run build\npnpm link\n```\n\n## How It Works\n\n```\n┌───────────────┐\n│ Agent writes  │\n│ artifact.html │\n└───────┬───────┘\n        ▼\n┌────────────────────────┐\n│ lavish-axi \u003Cfile_path> │\n│ opens local browser UI │\n└───────┬────────────────┘\n        ▼\n┌────────────────────────┐\n│ Human annotates text   │\n│ or elements, or        │\n│ sends chat feedback    │\n└───────┬────────────────┘\n        ▼\n┌────────────────────────┐\n│ lavish-axi poll waits  │\n│ and returns prompts    │\n└────────────────────────┘\n```\n\n- **File-path identity** - Sessions are keyed by the canonical HTML file path, so agents do not need opaque IDs.\n- **Portable artifacts** - The artifact runs in an iframe while Lavish injects a small SDK for annotations, snapshots, and feedback controls. Lavish does not inject any design system, so the saved HTML file renders identically whether you open it through `lavish-axi` or directly in a browser. Run `lavish-axi design` for a copy-pasteable CDN snippet to opt in to Tailwind CSS v4 + DaisyUI v5, or use any other design system (or none).\n- **Live reload** - Lavish watches the HTML artifact file by default. To also reload on sibling asset changes, add `data-lavish-live-reload-root` to the root element or `\u003Cmeta name=\"lavish-live-reload\" content=\"root\">`.\n- **Feedback controls** - Mark buttons, choices, and other interactive elements with `data-lavish-action` so Lavish does not annotate them, then call `window.lavish.queuePrompt()` or `window.lavish.sendQueuedPrompts()` from the control handler.\n- **Agent presence** - The browser shows when no agent is listening, keeps queued feedback for the next successful `lavish-axi poll` send even across reloads, and only blocks sending while the agent is working on delivered feedback.\n- **Precise targets** - Text annotations include selected text plus range anchors, so agents are not limited to whole-element selectors.\n- **Local-first state** - Session state stays under `.lavish-axi\u002F` in the workspace.\n\n## CLI Reference\n\n| Command                       | Description                                                  |\n| ----------------------------- | ------------------------------------------------------------ |\n| `lavish-axi`                  | Show current sessions and usage guidance.                    |\n| `lavish-axi \u003Chtml-file>`      | Open or resume a Lavish Editor session.                      |\n| `lavish-axi poll \u003Chtml-file>` | Long-poll until the user sends feedback or ends the session. |\n| `lavish-axi end \u003Chtml-file>`  | End a session.                                               |\n| `lavish-axi playbook [id]`    | List focused artifact guidance or show one playbook.         |\n| `lavish-axi design`           | Show CDN snippet + DaisyUI component reference (opt-in).     |\n| `lavish-axi server`           | Run the local Lavish Editor server.                          |\n\nKnown playbook IDs: `diagram`, `table`, `comparison`, `plan`, `diff`, `input`, `slides`.\n\n### Flags\n\n| Command                  | Flag                  | Description                                                                                                                                                                                                                         |\n| ------------------------ | --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `lavish-axi \u003Chtml-file>` | `--no-open`           | Ensure the server\u002Fsession exists without opening another browser window.                                                                                                                                                            |\n| `lavish-axi poll`        | `--agent-reply \"...\"` | Show the agent's reply in the existing browser chat before polling again.                                                                                                                                                           |\n| `lavish-axi poll`        | `--timeout-ms \u003Cms>`   | Test\u002Fdebug escape hatch only; agents should normally omit it.                                                                                                                                                                       |\n| `lavish-axi server`      | `--verbose`           | Log session and watcher events to stderr; can also be enabled with `LAVISH_AXI_DEBUG=1`. Detached server output is appended to `~\u002F.lavish-axi\u002Fserver.log` (or `LAVISH_AXI_STATE_DIR\u002Fserver.log`) for startup and crash diagnostics. |\n\n## Development\n\n```sh\npnpm run check          # Run all verification commands\npnpm run build          # Bundle the publishable CLI, chrome, and design assets\npnpm test               # Run node:test tests\npnpm run lint           # Run ESLint\npnpm run format:check   # Check Prettier formatting\npnpm run typecheck      # Run TypeScript checkJs validation\n```\n","Lavish-axi 是一个用于编辑HTML内容的新工具，旨在提供比传统富文本编辑器更丰富的交互体验。它支持本地操作，无需依赖云服务，通过命令行界面启动，能够打开并编辑由AI生成的HTML文件，并允许用户直接在界面上标注需要修改的部分，从而与AI代理进行高效协作。此外，该编辑器内置了多种可视化模板，适用于技术规划、设计探索等场景。Lavish-axi 作为AXI（Agent eXtension Interface）的一员，意味着任何具备基本能力的AI代理都可以轻松运行此工具，而无需额外配置或技能学习。",2,"2026-06-11 03:53:12","CREATED_QUERY"]