How to coordinate Claude Code and Codex on one project

Coordinating Claude Code and Codex on one project requires a shared cloud workspace and an authoritative file locking system. On Murmell, both agents run in parallel cloud terminals while The Board prevents simultaneous writes to the same paths.

Step by step

Open a shared workspace. Launch a project on the Murmell canvas. A dedicated cloud sandbox and private Git repository are initialized immediately.
Authenticate both providers. Connect your Anthropic credentials for Claude Code and your OpenAI credentials for Codex. Both agents use your existing accounts without token markups.
Launch both agent terminals. Open a Claude Code window and an OpenAI Codex window side by side on the canvas. Each agent accesses the exact same project directory.
Separate work by module. Instruct Claude Code to refactor backend services while directing Codex to build user interface components or integration tests.
Let The Board manage reservations. When either agent touches a file, it reserves the path. The server refuses concurrent writes until the active holder finishes and releases the lock.

Why run two different models together

Different AI coding agents possess complementary strengths. Developers frequently prefer Anthropic Claude Code for architectural reasoning, complex refactoring, and multi-file logic, while using OpenAI Codex in the cloud for rapid test suite generation and API endpoint scaffolding.

Running them on a single workstation requires juggling separate terminals, local environment variables, and multiple Git checkouts. On the multi-agent canvas, both agents run simultaneously in persistent cloud sandboxes.

Practical task allocation

The most effective workflow assigns distinct subdirectories to each agent. For example:

Claude Code operates on src/core/ and database schema migrations.
Codex implements unit tests under test/ and documentation in docs/.

Because both agents share the same project directory, Codex reads newly created interfaces immediately without waiting for branch merges or remote pushes.

Real-time coordination via The Board

File collisions are resolved before writes reach the filesystem. When Claude Code opens a source file, it acquires a live reservation. Codex sees the lock status on the canvas and queues its modification. Read our deep dive into multiple AI agents on one repo to explore the reservation ledger.

Collaborative visibility

You and your team can monitor both agent terminals simultaneously from any browser. Follow our guide on how to share a coding session to invite collaborators to the canvas.

Straight answers

Can Claude Code and Codex edit the same file at once?

No. The Board enforces single-holder write access. If Codex attempts to write to a path Claude Code is editing, Codex waits until the file is released.

Do I need separate Git branches for each agent?

No. Both agents work directly on the shared checkout. File reservations prevent collisions during execution, eliminating late merge conflicts.

What happens if an agent attempts an unreserved write?

The server creates an automatic collision snapshot before applying changes, ensuring prior work is never overwritten without a backup.