| 2026-04-03T03:31:33.222Z | message | assistant | - | - | 现在我已获取足够的信息。让我整理一份完整的调研报告。 --- # OpenClaw 可视化工具调研报告 ## 1. 概述 OpenClaw 的"可视化"不是指传统的 BI 仪表盘或数据分析图表工具，而是一个**面向 AI Agent 的多层级视觉输出体系**，核心围绕 **Canvas（画布）** 和 **浏览器控制** 两大能力构建，同时配合图片生成/分析工具，让 Agent 能够创建和操控可视化内容。 ## 2. 已有功能列表 ### 2.1 Canvas 画布系统（核心可视化工具） | 功能 | 说明 | |------|------| | `canvas present` | 在连接的 Node 设备上展示 HTML 内容 | | `canvas navigate` | 导航到新的 URL 或本地路径 | | `canvas eval` | 在画布中执行 JavaScript | | `canvas snapshot` | 截取画布截图（PNG/JPG） | | `canvas hide` | 隐藏画布 | | **A2UI 协议** | 通过 JSONL 推送声明式 UI（v0.8），支持 `beginRendering`、`surfaceUpdate`、`dataModelUpdate`、`deleteSurface` | | **Live Reload** | 文件变更自动刷新画布，支持开发调试 | | **HTML/CSS/JS** | 完整的 Web 前端能力，可以渲染任何 HTML 内容 | **架构**：Canvas Host（HTTP:18793）... |
| 2026-04-03T03:30:36.194Z | tool_event | toolResult | tool | - | 20:- The **canvas host** is served by the Gateway HTTP server under: 21: - `/__openclaw__/canvas/` (agent-editable HTML/CSS/JS) 45:- Expose commands like `canvas.*`, `camera.*`, `screen.record`, `location.get`. |
| 2026-04-03T03:30:36.190Z | tool_event | toolResult | tool | - | 6: - You want a canvas-ready viewer URL or a rendered diff file 21:- a gateway viewer URL for canvas presentation 30:2. Call `diffs` with `mode: "view"` for canvas-first flows. 76: - opens `details.viewerUrl` with `canvas present` 371:- Prefer `mode: "view"` for local interactive reviews in canvas. |
| 2026-04-03T03:30:36.186Z | tool_event | toolResult | tool | - | --- title: "Diffs" summary: "Read-only diff viewer and file renderer for agents (optional plugin tool)" read_when: - You want agents to show code or markdown edits as diffs - You want a canvas-ready viewer URL or a rendered diff file - You need controlled, temporary diff artifacts with secure defaults --- # Diffs `diffs` is an optional plugin tool with short built-in system guidance and a companion skill that turns change content into a read-only diff artifact for agents. It accepts either: - `before` and `after` text - a unified `patch` It can return: - a gateway viewer URL for canvas presentation - a rendered file path (PNG or PDF) for message delivery - both outputs in one call When en... |
| 2026-04-03T03:30:32.702Z | tool_event | toolResult | tool | - | /app/docs/tools/pdf.md /app/docs/images /app/docs/nodes/images.md /app/docs/zh-CN/nodes/images.md |
| 2026-04-03T03:30:32.699Z | tool_event | toolResult | tool | - | /app/docs/tools/skills.md /app/docs/tools/plugin.md /app/docs/tools/capability-cookbook.md /app/docs/tools/tavily.md /app/docs/tools/skills-config.md /app/docs/tools/diffs.md /app/docs/tools/multi-agent-sandbox-tools.md /app/docs/tools/pdf.md /app/docs/tools/index.md /app/docs/ja-JP/index.md |
| 2026-04-03T03:30:32.687Z | tool_event | toolResult | tool | - | 66:| `image` / `image_generate` | Analyze or generate images | | 69:For image work, use `image` for analysis and `image_generate` for generation or editing. If you target `openai/*`, `google/*`, `fal/*`, or another non-default image provider, configure that provider's auth/API key first. |
| 2026-04-03T03:30:14.621Z | tool_event | toolResult | tool | - | 27:- Agent actions (click/type/drag/select), snapshots, screenshots, PDFs. 39:openclaw browser --browser-profile openclaw snapshot 360:openclaw browser --browser-profile user snapshot --format ai 369:- `snapshot` returns refs from the selected live tab 397:- Existing-session screenshots support page captures and `--ref` element 398: captures from snapshots, but not CSS `--element` selectors. 436:- Snapshot/screenshot: `GET /snapshot`, `POST /screenshot` 456:Some features (navigate/act/AI snapshot/role snapshot, element screenshots, PDF) require 458:error. ARIA snapshots and basic screenshots still work for openclaw-managed Chrome. 484:- For advanced actions (click/type/snapshot/PDF), it u... |
| 2026-04-03T03:30:14.617Z | tool_event | toolResult | tool | - | { "url": "https://cn.bing.com/search?q=openclaw+visualization+canvas+dashboard", "finalUrl": "https://cn.bing.com/search?q=openclaw+visualization+canvas+dashboard", "status": 200, "contentType": "text/html", "title": "\n<<<EXTERNAL_UNTRUSTED_CONTENT id=\"15205dc2370bfa8c\">>>\nSource: Web Fetch\n---\nopenclaw visualization canvas dashboard - Search\n<<<END_EXTERNAL_UNTRUSTED_CONTENT id=\"15205dc2370bfa8c\">>>", "extractMode": "markdown", "extractor": "readability", "externalContent": { "untrusted": true, "source": "web_fetch", "wrapped": true }, "truncated": false, "length": 3098, "rawLength": 2327, "wrappedLength": 3098, "fetchedAt": "2026-04-03T03:30:14.554Z", "tookMs": 784, "text": "SE... |
| 2026-04-03T03:30:10.497Z | tool_event | toolResult | tool | - | sh: 1: cn.bing.com/search?q=openclaw+visualization+canvas+dashboard: not found Command not found |
| 2026-04-03T03:30:10.493Z | tool_event | toolResult | tool | - | 495:- `skills search [query...]`: search ClawHub skills. 496:- `skills install <slug>`: install a skill from ClawHub into the active workspace. 497:- `skills update <slug|--all>`: update tracked ClawHub skills. 508:Tip: use `openclaw skills search`, `openclaw skills install`, and `openclaw skills update` for ClawHub-backed skills. |
| 2026-04-03T03:30:06.894Z | tool_event | toolResult | tool | - | /app/docs/tools/skills.md:220:If you want stock image generation/editing inside OpenClaw itself, use the core /app/docs/tools/skills.md:221:`image_generate` tool with `agents.defaults.imageGenerationModel` instead of a /app/docs/tools/skills.md:225:For native image generation/editing, use `image_generate` with /app/docs/tools/skills.md:226:`agents.defaults.imageGenerationModel`. If you pick `openai/*`, `google/*`, /app/docs/tools/plugin.md:14:skills, speech, image generation, and more. Some plugins are **core** (shipped /app/docs/tools/plugin.md:254:| `registerImageGenerationProvider` | Image generation | /app/docs/tools/capability-cookbook.md:19:Use this when OpenClaw needs a new domain ... |
| 2026-04-03T03:30:06.888Z | tool_event | toolResult | tool | - | /app/docs/web/index.md:2:summary: "Gateway web surfaces: Control UI, bind modes, and security" /app/docs/web/index.md:5: - You want the browser Control UI and config editing /app/docs/web/index.md:11:The Gateway serves a small **browser Control UI** (Vite + Lit) from the same port as the Gateway WebSocket: /app/docs/web/index.md:16:Capabilities live in [Control UI](/web/control-ui). /app/docs/web/index.md:26:The Control UI is **enabled by default** when assets are present (`dist/control-ui`). /app/docs/web/index.md:102:- For non-loopback Control UI deployments, set `gateway.controlUi.allowedOrigins` /app/docs/web/index.md:106:- With Serve, Tailscale identity headers can satisfy Control UI... |
| 2026-04-03T03:30:06.885Z | tool_event | toolResult | tool | - | control-ui.md dashboard.md index.md tui.md webchat.md |
| 2026-04-03T03:30:03.628Z | tool_event | toolResult | tool | - | /app/docs/tools/tavily.md:26:2. Generate an API key in the dashboard. /app/docs/tools/brave-search.md:16:2. In the dashboard, choose the **Search** plan and generate an API key. /app/docs/tools/brave-search.md:89:- Each Brave plan includes **\$5/month in free credit** (renewing). The Search plan costs \$5 per 1,000 requests, so the credit covers 1,000 queries/month. Set your usage limit in the Brave dashboard to avoid unexpected charges. See the [Brave API portal](https://brave.com/search/api/) for current plans. /app/docs/tools/brave-search.md:90:- The Search plan includes the LLM Context endpoint and AI inference rights. Storing results to train or tune models requires a plan with expli... |
| 2026-04-03T03:30:03.624Z | tool_event | toolResult | tool | - | /app/skills/gh-issues/SKILL.md:470: "body": "## Summary\n\n{one_paragraph_description_of_fix}\n\n## Changes\n\n{bullet_list_of_changes}\n\n## Testing\n\n{what_was_tested_and_results}\n\nFixes {SOURCE_REPO}#{number}" /app/skills/xurl/SKILL.md:244:### Social Graph /app/skills/skill-creator/scripts/init_skill.py:50:- Example: Brand styling with "Brand Guidelines" -> "Colors" -> "Typography" -> "Features" /app/skills/skill-creator/scripts/init_skill.py:101:- Typography: Font files (.ttf, .woff2) /app/skills/skill-creator/scripts/init_skill.py:178:- Typography: custom-font.ttf, font-family.woff2 /app/skills/skill-creator/scripts/init_skill.py:184:- Images: .png, .jpg, .svg, .gif /app/skills/sk... |
| 2026-04-03T03:30:03.621Z | tool_event | toolResult | tool | - | /app/docs/concepts/architecture.md:22: - `/__openclaw__/a2ui/` (A2UI host) /app/docs/cli/index.md:1081:- `nodes canvas a2ui push --node <id|name|ip> (--jsonl <path> | --text <text>) [--invoke-timeout <ms>]` /app/docs/cli/index.md:1082:- `nodes canvas a2ui reset --node <id|name|ip> [--invoke-timeout <ms>]` /app/docs/nodes/index.md:201:### A2UI (Canvas) /app/docs/nodes/index.md:204:openclaw nodes canvas a2ui push --node <idOrNameOrIp> --text "Hello" /app/docs/nodes/index.md:205:openclaw nodes canvas a2ui push --node <idOrNameOrIp> --jsonl ./payload.jsonl /app/docs/nodes/index.md:206:openclaw nodes canvas a2ui reset --node <idOrNameOrIp> /app/docs/nodes/index.md:211:- Only A2UI v0.8 JSONL is... |
| 2026-04-03T03:29:58.315Z | tool_event | toolResult | tool | - | - iOS node with pairing, Canvas, camera, screen recording, location, and voice - Android node with pairing, chat, voice, Canvas, camera, and device commands **Tools and automation:** - Browser automation, exec, sandboxing - Web search (Brave, Perplexity, Gemini, Grok, Kimi, Firecrawl) |
| 2026-04-03T03:29:57.374Z | tool_event | toolResult | tool | - | 6: - You want a canvas-ready viewer URL or a rendered diff file 21:- a gateway viewer URL for canvas presentation 30:2. Call `diffs` with `mode: "view"` for canvas-first flows. 76: - opens `details.viewerUrl` with `canvas present` 371:- Prefer `mode: "view"` for local interactive reviews in canvas. |
| 2026-04-03T03:29:57.371Z | tool_event | toolResult | tool | - | /app/docs/nodes/index.md:2:summary: "Nodes: pairing, capabilities, permissions, and CLI helpers for canvas/camera/screen/device/notifications/system" /app/docs/nodes/index.md:5: - Using node canvas/camera for agent context /app/docs/nodes/index.md:12:A **node** is a companion device (macOS/iOS/Android/headless) that connects to the Gateway **WebSocket** (same port as operators) with `role: "node"` and exposes a command surface (e.g. `canvas.*`, `camera.*`, `device.*`, `notifications.*`, `system.*`) via `node.invoke`. Protocol details: [Gateway protocol](/gateway/protocol). /app/docs/nodes/index.md:16:macOS can also run in **node mode**: the menubar app connects to the Gateway’s WS server ... |
| 2026-04-03T03:29:57.368Z | tool_event | toolResult | tool | - | /app/docs/concepts/agent-workspace.md:116:- `canvas/` (optional) /app/docs/concepts/agent-workspace.md:117: - Canvas UI files for node displays (for example `canvas/index.html`). /app/docs/concepts/architecture.md:20:- The **canvas host** is served by the Gateway HTTP server under: /app/docs/concepts/architecture.md:21: - `/__openclaw__/canvas/` (agent-editable HTML/CSS/JS) /app/docs/concepts/architecture.md:45:- Expose commands like `canvas.*`, `camera.*`, `screen.record`, `location.get`. /app/docs/concepts/features.md:65:- iOS node with pairing, Canvas, camera, screen recording, location, and voice /app/docs/concepts/features.md:66:- Android node with pairing, chat, voice, Canvas, camer... |
| 2026-04-03T03:29:46.737Z | tool_event | toolResult | tool | - | --- summary: "OpenClaw capabilities across channels, routing, media, and UX." read_when: - You want a full list of what OpenClaw supports title: "Features" --- # Features ## Highlights <Columns> <Card title="Channels" icon="message-square"> WhatsApp, Telegram, Discord, and iMessage with a single Gateway. </Card> <Card title="Plugins" icon="plug"> Add Mattermost and more with extensions. </Card> <Card title="Routing" icon="route"> Multi-agent routing with isolated sessions. </Card> <Card title="Media" icon="image"> Images, audio, and documents in and out. </Card> <Card title="Apps and UI" icon="monitor"> Web Control UI and macOS companion app. </Card> <Card title="Mobile nodes" icon="smart... |
| 2026-04-03T03:29:46.733Z | tool_event | toolResult | tool | - | --- summary: "OpenClaw tools and plugins overview: what the agent can do and how to extend it" read_when: - You want to understand what tools OpenClaw provides - You need to configure, allow, or deny tools - You are deciding between built-in tools, skills, and plugins title: "Tools and Plugins" --- # Tools and Plugins Everything the agent does beyond generating text happens through **tools**. Tools are how the agent reads files, runs commands, browses the web, sends messages, and interacts with devices. ## Tools, skills, and plugins OpenClaw has three layers that work together: <Steps> <Step title="Tools are what the agent calls"> A tool is a typed function the agent can invoke (e.g. `exe... |
| 2026-04-03T03:29:46.729Z | tool_event | toolResult | tool | - | --- summary: "Agent-controlled Canvas panel embedded via WKWebView + custom URL scheme" read_when: - Implementing the macOS Canvas panel - Adding agent controls for visual workspace - Debugging WKWebView canvas loads title: "Canvas" --- # Canvas (macOS app) The macOS app embeds an agent‑controlled **Canvas panel** using `WKWebView`. It is a lightweight visual workspace for HTML/CSS/JS, A2UI, and small interactive UI surfaces. ## Where Canvas lives Canvas state is stored under Application Support: - `~/Library/Application Support/OpenClaw/canvas/<session>/...` The Canvas panel serves those files via a **custom URL scheme**: - `openclaw-canvas://<session>/<path>` Examples: - `openclaw-canva... |
| 2026-04-03T03:29:46.726Z | tool_event | toolResult | tool | - | # Canvas Skill Display HTML content on connected OpenClaw nodes (Mac app, iOS, Android). ## Overview The canvas tool lets you present web content on any connected node's canvas view. Great for: - Displaying games, visualizations, dashboards - Showing generated HTML content - Interactive demos ## How It Works ### Architecture ``` ┌─────────────────┐ ┌──────────────────┐ ┌─────────────┐ │ Canvas Host │────▶│ Node Bridge │────▶│ Node App │ │ (HTTP Server) │ │ (TCP Server) │ │ (Mac/iOS/ │ │ Port 18793 │ │ Port 18790 │ │ Android) │ └─────────────────┘ └──────────────────┘ └─────────────┘ ``` 1. **Canvas Host Server**: Serves static HTML/CSS/JS files from `canvasHost.root` directory 2. **Node B... |
| 2026-04-03T03:29:42.152Z | tool_event | toolResult | tool | - | /app/docs/platforms/mac/canvas.md /app/skills/canvas/SKILL.md /app/node_modules/@napi-rs/canvas-linux-x64-gnu/README.md /app/node_modules/@napi-rs/canvas/README.md |
| 2026-04-03T03:29:41.263Z | tool_event | toolResult | tool | - | /app/docs/tools/diffs.md:6: - You want a canvas-ready viewer URL or a rendered diff file /app/docs/tools/diffs.md:21:- a gateway viewer URL for canvas presentation /app/docs/tools/diffs.md:30:2. Call `diffs` with `mode: "view"` for canvas-first flows. /app/docs/tools/diffs.md:76: - opens `details.viewerUrl` with `canvas present` /app/docs/tools/diffs.md:371:- Prefer `mode: "view"` for local interactive reviews in canvas. /app/docs/tools/pdf.md:83:- Extraction fallback requires `pdfjs-dist` (and `@napi-rs/canvas` for image rendering). /app/docs/tools/index.md:63:| `canvas` | Drive node Canvas (present, eval, snapshot) | | /app/docs/tools/index.md:119:| `group:ui` | browser, canvas | |
| 2026-04-03T03:29:41.260Z | tool_event | toolResult | tool | - | /app/docs/tools/diffs.md /app/docs/tools/pdf.md /app/docs/tools/index.md /app/docs/ja-JP/index.md /app/docs/help/debugging.md /app/docs/help/faq.md /app/docs/help/troubleshooting.md /app/docs/concepts/agent-workspace.md /app/docs/concepts/architecture.md /app/docs/concepts/features.md /app/docs/concepts/multi-agent.md /app/docs/concepts/delegate-architecture.md /app/docs/pi.md /app/docs/cli/nodes.md /app/docs/cli/index.md /app/docs/vps.md /app/docs/index.md /app/docs/nodes/index.md /app/docs/nodes/camera.md /app/docs/nodes/troubleshooting.md |
| 2026-04-03T03:29:40.330Z | tool_event | toolResult | tool | - | SKILL.md |
| 2026-04-03T03:29:34.739Z | tool_event | toolResult | tool | - | /app/docs/tools/tavily.md /app/docs/tools/brave-search.md /app/docs/tools/diffs.md /app/docs/tools/browser.md /app/docs/tools/pdf.md /app/docs/tools/index.md /app/docs/tools/perplexity-search.md /app/docs/tools/exa-search.md /app/docs/ja-JP/index.md /app/docs/ja-JP/start/wizard.md /app/docs/ja-JP/start/getting-started.md /app/docs/help/debugging.md /app/docs/help/faq.md /app/docs/help/troubleshooting.md /app/docs/docs.json /app/docs/brave-search.md /app/docs/concepts/agent-workspace.md /app/docs/concepts/architecture.md /app/docs/concepts/features.md /app/docs/concepts/multi-agent.md |
| 2026-04-03T03:29:34.007Z | tool_event | toolResult | tool | - | /app/extensions/minimax/README.md /app/extensions/tlon/README.md /app/extensions/sglang/README.md /app/extensions/bluebubbles/README.md /app/extensions/msteams/CHANGELOG.md /app/extensions/zalouser/README.md /app/extensions/zalouser/CHANGELOG.md /app/extensions/vllm/README.md /app/extensions/twitch/README.md /app/extensions/twitch/CHANGELOG.md /app/extensions/nostr/README.md /app/extensions/nostr/CHANGELOG.md /app/extensions/qwen-portal-auth/README.md /app/extensions/llm-task/README.md /app/extensions/voice-call/README.md /app/extensions/voice-call/CHANGELOG.md /app/extensions/diffs/README.md /app/extensions/ollama/README.md /app/extensions/matrix/CHANGELOG.md /app/extensions/lobster/READ... |
| 2026-04-03T03:29:33.989Z | tool_event | toolResult | tool | - | 1password apple-notes apple-reminders bear-notes blogwatcher blucli bluebubbles camsnap canvas clawhub coding-agent discord eightctl gemini gh-issues gifgrep github gog goplaces healthcheck himalaya imsg mcporter model-usage nano-pdf node-connect notion obsidian openai-whisper openai-whisper-api openhue oracle ordercli peekaboo sag session-logs sherpa-onnx-tts skill-creator slack songsee sonoscli spotify-player summarize things-mac tmux trello video-frames voice-call wacli weather xurl |
| 2026-04-03T03:29:33.986Z | tool_event | toolResult | tool | - | assets auth-credential-semantics.md automation brave-search.md channels ci.md cli concepts date-time.md debug diagnostics docs.json gateway help images index.md install ja-JP logging.md nav-tabs-underline.js network.md nodes perplexity.md pi-dev.md pi.md platforms plugins prose.md providers reference security start style.css tools tts.md vps.md web whatsapp-openclaw-ai-zh.jpg whatsapp-openclaw.jpg zh-CN |
| 2026-04-03T03:29:33.925Z | message | assistant | - | - | Let me research OpenClaw's visualization tools comprehensively. I'll start by exploring the local filesystem and then try external resources. |
| 2026-04-03T03:29:15.838Z | message | user | - | - | [Fri 2026-04-03 11:29 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status. [Subagent Task]: ## 任务：调研 OpenClaw 可视化工具 ### 背景 用户想了解 OpenClaw 的可视化工具，需要进行全面调研。 ### 调研方向 #### 1. OpenClaw 官方文档 - 查看 `/app/docs` 目录下的文档 - 重点找可视化相关的功能说明 #### 2. OpenClaw 源码 - 查看 `/app` 目录结构，找可视化相关代码 - 搜索 canvas、dashboard、visualization、ui 等关键词 #### 3. 已安装的 Skills - 查看 `/app/skills` 目录，看有没有可视化相关的 skill #### 4. OpenClaw 社区 - 查看 https://docs.openclaw.ai 文档（如果可访问） - 查看 https://github.com/openclaw/openclaw 源码 #### 5. canvas 工具 - 我有一个 canvas 工具可用，查看其功能 ### 输出要求 1. OpenClaw 可视化工具概述 2. 已有功能列表 3. 可用性评估 4. 建议 |