Show HN: Baton – A desktop app for developing with AI agents

Looks like it could be extremely useful. I'm developing one thing at a time - small projects - but I'll keep this in mind for when things grow!

Some changes within pre-existing codebases (oh hey, we need feature or mechanism X).

An entirely new internal system with LLM code review, DB migration tracking, time tracking, standups and Teams integration.

A new system that trains neural nets to recognize crops based on Sentinel-2 satellite data (the neural net works okay, mowing and ploughing is harder with a mostly heuristic approach since I don't really have labels).

A new system to migrate somewhere between 1000-2000 forms between proprietary solutions where a team of people have spent a year with limited progress, whereas I'm generating the codegen tool that does most of the work, with the remainder being left up to AI.

A new project linting tool with Go + goja to allow writing rules for validating project stuff in ECMAScript, a bit like ESLint just stack agnostic and can be deployed as a 10 MB executable, to also control stuff like architecture and project conventions that the other tools aren't really geared towards.

Also wrote an OpenAI/Ollama/Claude proxy that allows using on-prem models running on another server through Ollama/llama.cpp and also using AWS Bedrock models when permissions are configured.

Also a bunch of Ansible configuration for stuff like a self-hosted Sentry instance, debugging that piece of shit would be so hard and annoying without something that I can throw logs at (because for some reason they think that having 70 containers running for what should amount to one piece of software is okay).

Also wrote a personal tool that lets me use VLM and Whisper and PySceneDetect and some other stuff to produce EDL so I can take a 3 hour long video and cut it down to 1 hour with LLMs using the transcripts/timestamps (aligned with words, so not too many awkward cuts) that I can then import into DaVinci Resolve for further editing.

Also migrated the apps I host from Contabo VPSes to Proxmox VMs (Hetzner dedicated server from the auction) and went from Docker Swarm + Portainer to pure Docker Compose, also moved from Drone CI to Woodpecker CI and also got rid of the old deprecated Bitnami container images.

Also migrated my homepage from an ancient Ruby and Rails version to more modern ones.

Also wrote a few scripts to replace YOURLS with just an Apache install, the config for which I can automatically append new shortened links to.

I don't even need worktrees or custom skills for most of this, just Claude Code and a subscription, since paying per token would make me go broke.

Everyone is building the things that are just stop gaps: tui/terminal/cli as foundation for UI, worktree instead of jj workspaces. Rust, tauri or python. You all will discover that after the easy fun parts are done you are rebuilding an IDE and at that point why not try to make Vscode better.

- vscode can run as a webapp in a container no electron needed

- vscode supports workspaces, main arguments i hear is vscode assumes one project per window which is just not the case. i have a folder with all my projects/repos that is open as one workspace in vscode

- visualJJ is the best worktree/workspace manager that no one is talking about, i wish it was open source but there is currently no alternative i am aware of

Not many parts are missing to make this perfect for the use cases all the agent managers try to address, but unlike all these hacks this can evolve one extension at a time and i dont have to throw away all the things that my vscode setup has

Spreading agents across git worktrees sounds awesome right up until the merge step. Sure, they're isolated on the filesystem, but when five parallel Claudes rewrite the exact same base class or interface for their own local needs, you're gonna end up with a merge conflict no neural net could ever untangle. All that saved time will just get burned manually rebasing this parallel chaos. Props for a cool pet project, but conceptually this is an architectural dead end

[dead]