Shikigami, run AI coding agents in parallel, each in a Git worktree
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…
What it does
In the maker’s words, at launch
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 the same file with different ideas - a nice recipe for a mess. So I built my own solution - Shikigami. It's a desktop app that runs agents side by side, each one in its own git worktree. Same repository, separate working directories, so they can all run at once without touching each other's edits. Every agent has a real PTY session. The sessions are resumable too, you can quit the app, come back tomorrow, and a long conversation is where you left it. The app has a second mode: a Monaco editor with the full file tree, diff viewer, git history and per-line blame. You flip between the agent grid and the editor from a pill in the middle of the title bar, and the agents keep running while you read. When one finishes a turn or needs input, a desktop notification takes you straight to that session. There's language intelligence built in too: diagnostics, go-to-definition, find-references and completion for PHP 8.1-8.5 and TypeScript/JavaScript - both are still improving to provide better dx. My mostly used stack at work is a Symfony app and docker containers, so the app has a docker integration builtin (service tree, per-service logs, a container shell, start/stop). Another integration is mysql and redis support - databases/tables preview, custom sql queries and redis keys inspection. It's free. You don't need an account, no sign-up and no cloud, so agents and worktrees stay on your machine. macOS (signed .dmg, Apple Silicon and Intel) and Linux (AppImage). No Windows build yet. What you see today stays free. At some point I'd like to earn something from it, probably paid add-ons on top, or an option to support the project like Signal does. I haven't decided yet. The source is private for now, so if that's a dealbreaker, fair enough - I understand that. That's why I started a dedicated YouTube channel so you can see who are you dealing with. The app is still in the BETA phase, you can expect bugs, but I fix them fast. I have live streams on YT, and there's a discord server if you'd rather complain in real time. I'd appreciate feedback, especially from anyone running more than two or three agents at once. Thanks, Igor
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
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
