Coding agents

Bowline works with the coding agents you already run

bowline works with the coding agents you already run rather than replacing them. It is the layer underneath that gives every agent the same real ~/Code, its config, and its .env on whatever machine or host it runs on.

One workspace, every agent

Agents run on laptops, remote build boxes, and short-lived hosts. bowline keeps one real ~/Code (source, opaque Git state, uncommitted work, and .env) in sync across all of them, so an agent starts against the same tree everywhere and its edits sync back. Pick your agent for the specifics.

Claude Code

CLI

Anthropic

On a fresh remote or ephemeral host, claude has no repo, no login, and no .env. You re-clone, sign in again (or export ANTHROPIC_API_KEY), and copy secrets before it can do anything. Every edit it makes is stranded on that box until you commit and push.

Bowline for Claude Code →

Cursor

IDE

Anysphere

Cursor runs on your desktop, so every machine you open it on needs its own clone, its own .env, and a fresh codebase re-index. Your uncommitted edits and local env do not follow you between a laptop and a second machine.

Bowline for Cursor →

OpenAI Codex CLI

CLI

OpenAI

A new host needs ~/.codex/auth.json (or OPENAI_API_KEY), the repo, and your .env before codex will run. A fresh box means signing in again, another clone, and copied secrets. The sandbox's writes stay on that machine.

Bowline for OpenAI Codex CLI →

aider

CLI

Open source

aider is git-aware and reads .env for keys, but on a new machine or remote host you still need the repo cloned, the .env present, and your uncommitted work. aider only commits the files it changes; your .env and other work-in-progress never travel with Git.

Bowline for aider →

ready when you are

Your ~/Code, on every machine and every agent.

Install bowline and your projects follow you. It just works.

Get started

$curl -fsSL https://install.bowline.sh | sh

macOS app · Linux CLI. Then run bowline login.