Analysis updated 2026-05-18
Run several AI coding agents side by side without juggling terminal tabs.
Organize agent sessions into named groups like Work or Experiments.
Restart your machine and pick up every agent session exactly where it left off.
Connect to a remote server over SSH and run an agent there from the same window.
| eranif/kennel | aerl-official/aerl-c-framework | antoxa2584x/shar-psp | |
|---|---|---|---|
| Stars | 4 | 4 | 4 |
| Language | C++ | C++ | C++ |
| Setup difficulty | easy | easy | hard |
| Complexity | 2/5 | 2/5 | 5/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Download the installer for your platform and launch it, no build step needed.
Kennel is a desktop app for people who run AI coding assistants like Claude Code, Kiro CLI, or OpenAI Codex from the command line. Instead of juggling a dozen terminal tabs and losing track of which agent is waiting on you, Kennel puts every agent session into one window with a sidebar you can organize. Each running agent is called a session, and sessions live inside groups you name yourself, such as Work or Experiments. You can collapse a group when you are not using it and reopen it later. The sidebar shows a spinner on any session that is still busy, so you can tell at a glance which agents are working and which are done and waiting for you. The standout feature is persistence. If you close Kennel or restart your computer, every session comes back exactly where it left off, using each tool's own resume option, such as Claude's continue flag or Kiro's resume flag. You do not have to remember what you were doing or retype context. Each session runs as a real terminal window, so anything that works in your normal shell, colors, prompts, and interactive input, works the same way inside Kennel. Beyond the three agents it ships with, you can define your own through a short setup wizard, pointing it at any executable, whether that program runs on your own machine or on a remote server you connect to over SSH. Setup involves choosing local or remote, naming the agent and its launch command, and optionally setting a custom shell and environment variables. Kennel is built in C++, distributed as installers for Windows, macOS, and Linux, and released under the BSD 3-Clause license, which is permissive and allows free use including commercial use.
A desktop app that runs multiple AI coding CLI agents (Claude Code, Codex, etc) as organized, resumable terminal sessions in one window.
Mainly C++. The stack also includes C++, OpenGL, SSH.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.