Codelegate, keyboard-driven coding agent orchestrator GUI for Mac/Linux
Do we really need another agent orchestrator? Probably not. But I couldn't find one that matched how I actually work with coding agent CLIs, so I built my own. Codelegate is a desktop app (Tauri 2 + React + xterm.js) that organizes agent sessions into a keyboard-first workspace. I built it to solve a few specific frustrations: 1. I want to navigate everything with both hands on the keyboard. Sessions switch with `Alt+1..9`, panes with `Alt+A/G/T`. No mouse required. 2. I work on the same repo in parallel using Git worktrees. Codelegate has a built-in worktree flow: create an…
What it does
In the maker’s words, at launch
Do we really need another agent orchestrator? Probably not. But I couldn't find one that matched how I actually work with coding agent CLIs, so I built my own. Codelegate is a desktop app (Tauri 2 + React + xterm.js) that organizes agent sessions into a keyboard-first workspace. I built it to solve a few specific frustrations: 1. I want to navigate everything with both hands on the keyboard. Sessions switch with `Alt+1..9`, panes with `Alt+A/G/T`. No mouse required. 2. I work on the same repo in parallel using Git worktrees. Codelegate has a built-in worktree flow: create an isolated branch per agent, auto-cleanup on session end. 3. I want to keep using my CLI tools (zellij, etc.) alongside agents, not replace them. 4. I need it on both macOS and Linux. Each session gives you three panes: Agent, Terminal, and Git. The Git pane handles diff review with syntax highlighting, bulk stage/unstage, commit, and amend. Sessions are grouped by repository in the sidebar. Currently supports Claude Code and Codex CLI, but anything that runs in a shell can work. This is v1.0.0 and it only covers the agent CLIs and features I use the most. It's licensed under GPLv3, so it's meant to be forked and shaped into your own workflow. Hope you enjoy using it or making it your own!
Does the same job
all alternatives →
- SRShikigami, run AI coding agents in parallel, each in a Git worktreeJul 2026 · shikigami.dev · ▲7
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…
- FBFirst background agents in Jetbrains IDEs [video]2025 · youtube.com · ▲9
TLDR: made the first background coding agent that has an isolated workspace and runs locally Howdy - I’m Kevin, co-founder of Firebender, and we built the first background coding agent in android studio / Jetbrains! Why not just use Cursor background agents or OpenAI Codex? Both of these require setting up a cloud container and cloning your existing developer environment, and maintaining it. Then when you want to iterate on changes as AI inevitably makes a mistake, you either throw away the work, or have to pull down the branch and clean it up. This feels really clunky. With Firebender,…
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 · 16d 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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
