Manage multiple running AI coding sessions across different projects from one dashboard
Fork an in-progress Claude Code or Codex session to a different AI provider for a second opinion
Sync new commits from your main session into a forked session as work continues
Hand a fork's finished work back as a reviewable summary with merge commands
| pointvis/forklane | 0xallam/my-recipe | 0xhassaan/nn-from-scratch | |
|---|---|---|---|
| Stars | 0 | — | 0 |
| Language | Python | Python | Python |
| Last pushed | — | 2022-11-22 | — |
| Maintenance | — | Dormant | — |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 3/5 | 2/5 | 4/5 |
| Audience | developer | general | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Python 3.10+, tmux, and git, agent features rely on CLIs you already have installed and logged in.
forklane is a dashboard, run inside tmux, for managing coding sessions with AI agents like Claude Code, Codex, or Kimi across several projects at once. It shows a list of your project workspaces, whether each one is running or stopped, and lets you attach, start, or stop a session for each one. It is written as a single Python file using only the standard library, so there is no background process, no API keys to manage, and nothing extra to configure beyond installing it. The main feature is forking a session. If you want a second opinion from a different AI model while keeping your original conversation going, forklane can write a summary of your current session into a file, create a separate copy of your project's code using a git worktree, and start the other AI provider there with that summary as its starting point. This way two agents can work on the same project at the same time without stepping on each other's files. You can also scope a fork to only work inside certain folders, such as a tests folder. As your original session keeps making progress, you can sync those new changes into the fork so it can see what has happened since it started. When the fork's work is done, you can hand it back, which writes a summary of what changed and gives you the commands needed to review and merge it yourself. The tool never merges, pushes, or deletes anything automatically, it only prepares the information and leaves the decision to you. forklane supports Claude Code and Codex out of the box, and you can add other command line AI tools yourself by telling forklane how to launch, log in, and resume them. All settings are stored in plain configuration files in your home folder. This project requires Python 3.10 or newer, tmux, and git to be installed. It is released under the MIT license, meaning you can use, modify, and share it freely.
A tmux dashboard for running and forking AI coding agent sessions like Claude Code and Codex across projects, so a second AI can work in parallel and hand its changes back for review.
Mainly Python. The stack also includes Python, tmux, git.
Use, modify, and distribute this code freely, including commercially, as long as you keep the license 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.