Alternatives
Products that do what ChatML - Run Claude Code Parallel Sessions in a Desktop app does
Hey HN, Over the past 10 months I've been using Claude Code heavily, and one limitation kept coming up: you can really only run one coding agent at a time. While one agent is refactoring something, the rest of the repo is basically blocked unless you start manually juggling branches and working directories. The core issue is that AI coding agents operate directly in your filesystem. If two agents run in the same working directory they quickly start stepping on each other’s changes. Git worktrees turned out to be a surprisingly good primitive for solving this. So I built ChatML, a Desktop app…
- 1
- 2
- 3SR
Hello all, I'm a software developer. Over the last few months more and more of my work has turned into using coding agents instead of typing the whole code myself. Usually a few claude sessions at once, sometimes codex, one per feature or per revealed bug. I ran them in a split terminal for a few weeks, and quickly spotted two main problems. The first is that I couldn't easily tell which agent was stuck waiting on me and which was still working, so I'd cycle through sessions and checking on them. The second one: agents sharing a single branch step on each other. Two of them could be editing…
Jul 2026 · shikigami.dev
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13D2
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…
Feb 2026
- 14BE
I realised I was working on more parallel tasks with coding agents, but git branches became a huge bottleneck. Tried Git Butler but it just complicated things further. Found git worktrees as a solution but the git API was a bit too complicated for day to day. So thought I'll vibe-code this simple CLI utility to manage the process. It technically works with any setup – claude/codex/gemini + cursor/vim/whatever. Just manages git worktrees inside your repo and sets up your dev environment how you like it. Nothing fancy, just something I built to scratch my own itch. Figured…
2025 · github.com
- 15OA
I've been running Claude Code and Codex together every day. At some point I figured out you can use tmux to let them talk to each other, so I started doing that. Once they could coordinate, I kept adding more agents. Before long I had a whole team working together. But any time I rebooted my machine, the whole thing was gone. Not just the tabs. The way they were wired up, what each one was doing, all of it. Nothing I'd found treats your agent setup as a topology, as something with a shape you can save and bring back. So I built OpenRig, a multi-agent harness. A harness wraps a model. A "rig"…
Apr 2026 · github.com
- 16CR
Hey HN, what I wanted to build here is a proper universal layer for persisted agentic sessions, that could be seamlessly interacted both via web and a messenger (Telegram). I really like what's done so far and would be nice to hear some feedback from you. The interesting thing is that I started to use Chatcode during its development as soon it was possible, so used this tool to build itself. I know that there could be trust/privacy concerns, because it relies on a gateway that you need to install on your machine in order to work, but: 1. You can use it on any machine, just have some…
Jun 2026 · chatcode.dev
- 17IB
The main goal of this was to be able to not just run multiple Claude Code sessions at once, but actually manage them and keep track of what I was doing. Sometimes this is multiple attempts on the same task, sometimes I work several tasks at once. Really I was just sick of twiddling my thumbs waiting for the coding agent to finish, and I wanted it to be easy to work on/review/test another change while I waited.
2025 · github.com
- 18AP
I've been working on this internal project initially both to learn more Vibe-Coding but also to help our teams and projects to use AI more efficiently. As more people used it, it grew to support multiple teams/projects to analyze their Claude Code conversation and optimize them over time (understanding how to write better conversation with Claude Code and share knowledge between them) With time we added support for multiple Claude account management and monitor usage/rate limit. This is a simple project but has proved to be quite useful for our company. We have reached 5000+…
2025 · github.com
- 19
- 20CC
I’ve found coding agents to be great at 1/ finding everything they need across large codebases using only bash commands (grep, glob, ls, etc.) and 2/ building new things based on their findings (duh). What if, instead of a codebase, the files were all your workplace docs? There was a `Google_Drive` folder, a `Linear` folder, a `Slack` folder, and so on. Over the last week, we put together Craft to test this out. It’s an interface to a coding agent (OpenCode for model flexibility) running on a virtual machine with: 1. your company's complete knowledge base represented as…
Jan 2026
- 21MA
This weekend I built a multi-agent coding system which, quite unexpectedly, beat Claude Code on Stanford's Terminal Bench! The architecture is straightforward, consisting of an orchestrator agent that deploys explorer & coder subagents to complete complex terminal based tasks, utilising an intelligent context sharing mechanism along the way which makes it all work. The repo has a lot of technical details, and all the code and prompts for you to play around with if you'd like! I had a lot of fun making this, I hope you have fun reading the README, using it yourself, or even extending it! As…
2025 · github.com
- 22RC
The magic in AI coding assistants isn't the code -- it's the prompts. I studied the externally observable behavior of Claude Code and recreated it from scratch in Python with the exact same behaviors. It works with any model -- OpenAI, Gemini, Claude. What's surprising: 1. You can keep the core agent really simple, just 280 lines of Python. As long as it supports hooks, custom sub-agents and Model Context Protocol (MCP), then all the rest of the coding-assistant-specific behavior and tools can be factored out into a separate MCP server. 2. The magic is in the prompts (1200 lines of…
2025 · github.com
- 23RA
Hey HN, I built SuperHQ, an app that lets you run coding agents in local sandboxes (powered by Shuru). No custom UI wrapping the agents, they run as CLI/TUI like they were designed to. It just provides you the tools most of us (okay, maybe just me?) needed for running multiple coding agents in parallel without worrying about breaking your system or work environment. Each agent runs in its own microVM. You mount your projects in, writes go to a tmpfs overlay so your host is never touched, and you get a unified diff view to accept or discard changes. API keys never enter the sandbox, they…
Apr 2026 · superhq.ai
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →