Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design
Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design
Whiteboard: An open-source canvas for thoughtful software design Download for macOS · Download for Fedora · Website · Discord
Whiteboard 是一个开源桌面应用,旨在让开发者与 AI 智能体(Agents)能够在同一个工作空间中共同架构软件。Whiteboard 可以接入你现有的工具(如 Claude Code、Codex 等),并为你的智能体提供一个 SDK,使其能够在应用内的画布上绘图,从而直观地描述其工作内容。以下是一个 1 分钟的演示视频,详细介绍了更多功能:https://www.youtube.com/watch?v=ChPn3ftULWE
Quickstart
Download Whiteboard and open the app. Connect Claude Code, Codex, or another coding agent from the welcome screen. Ask your agent to review your current branch against up-to-date main and open the result in Whiteboard.
快速入门
下载并打开 Whiteboard 应用。在欢迎界面连接 Claude Code、Codex 或其他编码智能体。让你的智能体对比当前分支与最新的主分支(main),并将结果在 Whiteboard 中打开。
Guidance
In our experience, Whiteboard works best with models like GPT-6 Sol and Claude Opus 5.5 for their intelligence, cost, and speed tradeoff. Here are a few example prompts of how to use Whiteboard effectively. We are working hard to make sure the right choices are baked in by default to the system prompt - part of why this system is open source! - but in the meantime:
指导建议
根据我们的经验,Whiteboard 与 GPT-6 Sol 和 Claude Opus 5.5 等模型配合使用效果最佳,因为它们在智能程度、成本和速度之间取得了良好的平衡。以下是一些如何有效使用 Whiteboard 的提示词示例。我们正在努力确保将最佳实践默认集成到系统提示词中——这也是该系统开源的原因之一!在此期间,你可以参考以下用法:
For a new API change: “hey, this stack of commits is set up so i can get an [api] to do [objective] i’d like to see: proposed api examples motivations for this (if available to you in context/in the repo) and then we can dive into implementation + explaining how things worked.”
针对新的 API 变更: “嘿,这组提交是为了实现 [目标] 而设置的 [API],我希望看到:建议的 API 示例、实现此目标的动机(如果上下文或仓库中有相关信息),然后我们可以深入探讨实现细节并解释其工作原理。”
For a change to add telemetry: “cna you explain to me the telemetry changes form the newest posthog pr [link] — what are we tracking, how can we build good dashboards or product waterfalls from it? what do we do for hangs, errors, crashes etc… use whiteboard”
针对添加遥测(Telemetry)的变更: “你能向我解释一下最新 PostHog PR 中的遥测变更吗?我们正在追踪什么?我们如何利用它构建好的仪表板或产品瀑布图?对于卡顿、错误、崩溃等情况我们该怎么处理……请使用 Whiteboard 展示。”
If you see anything you don’t like, highlight it in your clipboard and give it your agent, and it can re-draw on the Whiteboard to suit your needs!
如果你看到任何不满意的地方,将其复制到剪贴板并提供给你的智能体,它就能在 Whiteboard 上重新绘制以满足你的需求!
Why does this exist?
为什么会有这个项目?
Diagrams that lead to code Pure HTML tools didn’t provide easy affordances to connect a spec or diagram to code; this is especially tricky since tradeoffs are often only discovered after a first pass at implementation. In Whiteboard, when you click on visualizations like a sequence diagram, an entity relationship diagram, or a quote from the agent’s trace, you can jump to the underlying code directly. When navigating code, you get keybindings and LSP support from VSCode out of the box.
通向代码的图表 纯 HTML 工具无法提供将规范或图表与代码关联的便捷方式;这一点尤为棘手,因为权衡(tradeoffs)往往是在初步实现后才被发现的。在 Whiteboard 中,当你点击序列图、实体关系图或智能体追踪记录中的引用时,可以直接跳转到对应的底层代码。在浏览代码时,你可以直接获得 VSCode 的快捷键支持和 LSP 支持。
Semantic diff viewer Raw diff views can be very noisy, so we wrote a semantic, AST-aware diff viewer in Rust so you can only view the code changes which are relevant to you. We’ve set up some sane defaults: large added functions are summarized as pseudocode, and things like unit tests and documentation changes are collapsed / hidden. This is all customizable with a WASM-based plugin system.
语义化差异查看器 原始的差异(diff)视图可能非常杂乱,因此我们用 Rust 编写了一个具备 AST(抽象语法树)感知能力的语义化差异查看器,让你只查看与你相关的代码变更。我们设置了一些合理的默认值:新增的大型函数会被概括为伪代码,而单元测试和文档变更等内容会被折叠或隐藏。这一切都可以通过基于 WASM 的插件系统进行自定义。
Decision log We found it difficult to reason about what set of decisions our agents made autonomously & how that impacts a change. So we built tools for agents to query and link their own traces on the Whiteboard, so you can visualize the requirements that you set, understand how they were implemented, and understand what decisions the agent made autonomously.
决策日志 我们发现很难推断智能体自主做出了哪些决策,以及这些决策如何影响代码变更。因此,我们为智能体构建了工具,使其能够在 Whiteboard 上查询并链接自己的追踪记录。这样你就可以可视化你设定的需求,理解它们是如何实现的,并了解智能体自主做出了哪些决策。
Open source, on your machine
Whiteboard is MIT-licensed and runs against your local checkouts. A hosted product for teams is planned, and everything will always remain self-hostable.
开源,运行在你的机器上
Whiteboard 采用 MIT 协议开源,并在你的本地代码库上运行。我们计划推出面向团队的托管产品,但所有功能将始终保持可自托管。
Known limitations
- You cannot currently edit files in Whiteboard. If this is something that you find yourself wanting to do, please file an issue!
- Working and browsing files across multiple repos in a single review isn’t well supported.
- While you can share reviews between machines with the share button, updates made after a review is shared don’t appear for others. You would need to re-share the review.
已知局限性
- 目前无法在 Whiteboard 中直接编辑文件。如果你有此需求,请提交 Issue!
- 在单次评审中跨多个仓库工作和浏览文件的支持尚不完善。
- 虽然你可以通过分享按钮在不同机器间分享评审,但在分享后进行的更新不会自动同步给他人。你需要重新分享评审。
Contributing
Contributions and feedback are welcome. Read CONTRIBUTING.md for setup and the pull request workflow, and follow the Code of Conduct. Report vulnerabilities as described in SECURITY.md. Questions? Ask on Discord.
贡献
欢迎贡献代码和反馈。请阅读 CONTRIBUTING.md 了解设置和 Pull Request 工作流程,并遵守行为准则。请按照 SECURITY.md 中的说明报告漏洞。有问题吗?请在 Discord 上提问。
Privacy
Whiteboard runs against local checkouts. Anonymous telemetry does not include your code, diffs, Whiteboard text, prompts, or model output. Read the privacy overview, inspect the complete telemetry reference, or turn telemetry off at any time.
隐私
Whiteboard 在本地代码库上运行。匿名遥测数据不包含你的代码、差异、Whiteboard 文本、提示词或模型输出。你可以阅读隐私概览、查看完整的遥测参考,或随时关闭遥测功能。
License
Whiteboard is available under the MIT License. The vendored Code - OSS fork retains Microsoft’s MIT license and third-party notices; see apps/review-desktop/LICENSE and apps/review-desktop/UPSTREAM.
许可证
Whiteboard 采用 MIT 许可证。所集成的 Code-OSS 分支保留了微软的 MIT 许可证和第三方声明;详情请参阅 apps/review-desktop/LICENSE 和 apps/review-desktop/UPSTREAM。
On vendoring Code OSS
With everyone using dedicated agent TUIs and desktop apps, we only use our text editors for reviewing line-by-line diffs now, so we figured why not have a text editor meant for reviewing code. In that case, might as well start off with the most successful open source editor out there as a baseline. We vendor Code OSS unlike other forks that maintain patches because coding agents have a hard time with patches and there’s a lot of stuff from stock VS Code (i.e., ~45% of the codebase is Copilot these days 😬) that we don’t need. We regularly monitor upstream Code OSS and merge in security/feature patches as they come in.
关于集成 Code OSS
随着大家都在使用专用的智能体 TUI 和桌面应用,我们现在只用文本编辑器来逐行查看差异。因此我们想,为什么不开发一个专门用于代码评审的文本编辑器呢?既然如此,不如直接以目前最成功的开源编辑器作为基准。与其他维护补丁的分支不同,我们直接集成(vendor)了 Code OSS,因为编码智能体很难处理补丁,而且原生 VS Code 中有很多我们不需要的东西(例如,如今约 45% 的代码库是 Copilot 😬)。我们会定期监控上游的 Code OSS,并在安全/功能补丁发布时进行合并。
Influences
- Understanding is the new bottleneck — a great overview of the constraints of modern software engineering.
- Vibe Legacy Code and Vibe Code — do a great job describing how AI-generated code fits into the pre-2025 notion of software engineering.
- Karpathy on agents: On LLM agents, On agents as “junior engineer savants”
影响与参考
- 理解力是新的瓶颈 —— 对现代软件工程局限性的精彩概述。
- Vibe Legacy Code 和 Vibe Code —— 很好地描述了 AI 生成的代码如何融入 2025 年之前的软件工程概念。
- Karpathy 关于智能体的观点:关于 LLM 智能体,关于智能体作为“初级工程师天才”。