greentfrapp

Actually it's something like a researcher-focused app that allows you to open Jupyter notebooks, code snippets, PDFs, right next to the chat window pane.

Let's say you're working on protein design and you want to view the 3D structure of the protein, you can have the agent build a pane for that in the app, and you can ask the agent to help customize it as well.

It has a chat interface, but also lets you split the window into different sub-windows that can open different interfaces, like a Jupyter notebook (with a working kernel), a code editor, or a file browser. You can also ask the agent to create custom interfaces, like a protein structure visualizer, or an SQLite viewer, or just a simple place to manage your citations.

Under the hood it's running on your local Claude Code instance, I'll probably be adding support for other APIs through Open Router soon.

Yup, the layouts and panes are persistent and also have state.

I believe currently it would work if you've already set up the MCPs via Claude Code, because it's running off your local Claude Code under the hood. But I'll look into surfacing the MCPs like in the Claude app.

Thanks for sharing emacs + gptel! I'll find some time to try it out

By checkpoints do you mean versioning and rollback?

Yeah I know people who think that chat is the last UI we'll ever need, but I really think there's so much that can be done with malleable interfaces.

The demo and videos are really cool! Just a few guardrails might make this a lot more usable as an actual IDE.

I will! Thanks for the rec

Hi HN, I built Panel because research work means switching all the time between a chat with an agent, the papers I'm reading, the notebook I'm running and the data files I'm looking at.

Panel is a local web app with dockable panes made with dockview. You get chat, files, PDFs, markdown and Jupyter notebooks.

The agent can also create custom panes on request, like a protein structure viewer or an SQLite browser.

There's also an early "Module" system. Modules are like Skills, but with typed inputs, outputs and intermediates, so a long job shows its progress and its results can feed the next step. Right now the working one is a literature review, with an early version for hypothesis generation.

How it's built: a Vue + dockview frontend and a Python (FastAPI) sidecar that drives the agent backends. Everything runs on your machine.

Honest limits for now: - Full support is Claude Code only, so you need it installed and signed in. Codex and other harnesses are not supported yet. - Still very rough around the edges, I've been adding to it as I use it myself. Feedback welcome!

MIT licensed.