Show HN: Stagewise – frontend coding agent for real codebases
Hacker News (score: 16)Description
We’re compatible with any framework and any component library. Think of it like a v0 of Lovable that works locally and with any existing codebase.
You can spawn the agent into locally running web apps in dev mode with `npx stagewise` from the project root. The agent lets you then click on HTML Elements in your app, enter prompts like 'increase the height here' and will implement the changes in your source code.
Before stagewise, we were building a vertical SaaS for logistics from scratch and loved using prototyping tools like v0 or lovable to get to the first version. But when switching from v0/ lovable to Cursor for local development, we felt like the frontend magic was gone. So, we decided to build stagewise to bring that same magic to local development.
The first version of stagewise just forwarded a prompt with browser context to existing IDEs and agents (Cursor, Cline, ..) and went viral on X after we open sourced it. However, the APIs of existing coding agents were very limiting, so we figured that building our own agent would unlock the full potential of stagewise.
Since our last Show HN (https://news.ycombinator.com/item?id=44798553), we launched a few very important features and changes: You now have a proprietary chat history with the agent, an undo button to revert changes, and we increased the amount of free credits AND reduced the pricing by 50%. We made a video about all these changes, showing you how stagewise works: https://x.com/goetzejulian/status/1959835222712955140/video/....
So far, we've seen great adoption from non-technical users who wanted to continue building their lovable prototype locally. We personally use the agent almost daily to make changes to our landing page and to build the UI of new features on our console (https://console.stagewise.io).
If you have an app running in dev mode, simply `cd` into the app directory and run `npx stagewise` - the agent should appear, ready to play with.
We're very excited to hear your feedback!
More from Hacker
IRHash: Efficient Multi-Language Compiler Caching by IR-Level Hashing
IRHash: Efficient Multi-Language Compiler Caching by IR-Level Hashing
Show HN: Typed-arrow – compile‑time Arrow schemas for Rust
Show HN: Typed-arrow – compile‑time Arrow schemas for Rust Hi community, we just released <a href="https://github.com/tonbo-io/typed-arrow" rel="nofollow">https://github.com/tonbo-io/typed-arrow</a>.<p>When working with arrow-rs, we noticed that schemas are declared at runtime. This often leads to runtime errors and makes development less safe.<p>typed-arrow takes a different approach:<p>- Schemas are declared at compile time with Rust’s type system.<p>- This eliminates runtime schema errors.<p>- And introduces no runtime overhead — everything is checked and generated by the compiler.<p>If you’ve run into Arrow runtime schema issues, and your schema is stable (not defined or switched at runtime), this project might be useful.
Show HN: ASCII Tree Editor
Show HN: ASCII Tree Editor Show HN: ASCII Tree Editor<p>I've created a web-based editor for ASCII file directory trees called asciitreeman. It's designed to make it easier to edit and reorganize the output of the tree command.<p>You can try it out here: <a href="https://reorx.github.io/asciitreeman/" rel="nofollow">https://reorx.github.io/asciitreeman/</a><p>And the source code is on GitHub: <a href="https://github.com/reorx/asciitreeman" rel="nofollow">https://github.com/reorx/asciitreeman</a><p>Some of the key features include visual tree editing with drag-and-drop-like operations, real-time sync where changes are immediately reflected in the ASCII output, keyboard shortcuts for navigation (J/K or arrow keys), and auto-saving your work to local storage.<p>What's interesting is that I used Claude Code to "vibe-code" this project in a very short amount of time. It was a fun experiment in AI-assisted development. For those curious about the process, I've included the prompts and specifications I used in the source code. You can check them out in the spec.md and CLAUDE.md files in the repository.<p>Hop you find it useful!
Show HN: Real-time privacy protection for smart glasses
Show HN: Real-time privacy protection for smart glasses I built a live video privacy filter that helps smart glasses app developers handle privacy automatically.<p>How it works: You can replace a raw camera feed with the filtered stream in your app. The filter processes a live video stream, applies privacy protections, and outputs a privacy-compliant stream in real time. You can use this processed stream for AI apps, social apps, or anything else.<p>Features: Currently, the filter blurs all faces except those who have given consent. Consent can be granted verbally by saying something like "I consent to be captured" to the camera. I'll be adding more features, such as detecting and redacting other private information, speech anonymization, and automatic video shut-off in certain locations or situations.<p>Why I built it: While developing an always-on AI assistant/memory for glasses, I realized privacy concerns would be a critical problem, for both bystanders and the wearer. Addressing this involves complex issues like GDPR, CCPA, data deletion requests, and consent management, so I built this privacy layer first for myself and other developers.<p>Reference app: There's a sample app (./examples/rewind/) that uses the filter. The demo video is in the README, please check it out! The app shows the current camera stream and past recordings, both privacy-protected, and will include AI features using the recordings.<p>Tech: Runs offline on a laptop. Built with FFmpeg (stream decode/encode), OpenCV (face recognition/blurring), Faster Whisper (voice transcription), and Phi-3.1 Mini (LLM for transcription analysis).<p>I'd love feedback and ideas for tackling the privacy challenges in wearable camera apps!
Show HN: I built a biological network visualization tool
Show HN: I built a biological network visualization tool I've been working on nodes.bio - an interactive tool for visualizing biological networks and systems thinking. The tool features interactive network visualization powered by Cytoscape.js, with real-time graph editing and manipulation capabilities. It supports JSON import/export and provides a responsive design that works seamlessly on the desktop (mobile-friendly version coming later).<p>The tech stack combines modern frontend technologies with robust backend architecture. The frontend uses Next.js 14 with TypeScript and Cytoscape.js for the visualization engine. The backend is built with FastAPI and Python.<p>The featured demo showcases a Traumatic Brain Injury Nasal Spray mechanism of action visualization, demonstrating the tool's capability to handle complex biological pathway mapping.<p>You can explore the live demo at <<a href="https://nodes.bio" rel="nofollow">https://nodes.bio</a>> to see the TBI Nasal Spray visualization in action, along with other biological network examples.<p>I'd love feedback on the visualization capabilities or any suggestions for biological data integration. What do you think?
China Dominates 44% of Visible Fishing Activity Worldwide
China Dominates 44% of Visible Fishing Activity Worldwide
No other tools from this source yet.