DevSwarm 2.0, fix parallel Claude Code sprawl
Mike, cofounder of DevSwarm here. I’ve been using Claude Code heavily for the last few months (multiple Max plans). Running sessions in parallel across git branches or worktrees is fast, but it breaks down quickly in practice because of sprawl. Terminals everywhere, editor windows everywhere, and you lose track of basics like which agent is on which branch and what is ready for review. DevSwarm is what we built to solve that. The core abstraction is simple: workspace equals branch. Each workspace runs its agent session(s) and keeps the state visible. In 2.0 we added a full VS Code IDE…
What it does
In the maker’s words, at launch
Mike, cofounder of DevSwarm here. I’ve been using Claude Code heavily for the last few months (multiple Max plans). Running sessions in parallel across git branches or worktrees is fast, but it breaks down quickly in practice because of sprawl. Terminals everywhere, editor windows everywhere, and you lose track of basics like which agent is on which branch and what is ready for review. DevSwarm is what we built to solve that. The core abstraction is simple: workspace equals branch. Each workspace runs its agent session(s) and keeps the state visible. In 2.0 we added a full VS Code IDE embedded in each workspace, so editing, terminals, diffs, and git controls stay in one window while you jump between parallel branches. I’d love blunt feedback from people doing parallel workflows: • What breaks first for you past 2 parallel sessions? • What would you need for this to be production-grade? Tests, debugging, extensions, PR flow? Video: https://www.youtube.com/watch?v=MqRkSRee6HE Download: https://devswarm.ai/download
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
