Multi-agent browser canvas
Open multiple coding agents in the same project and manage them from one shared canvas rather than separate local sessions.
Murmell
Freemium
Murmell is a browser-based canvas for running AI coding agents in shared cloud sandboxes. It helps developers coordinate Claude Code, Codex, Kimi, and OpenCode on one project without local setup or file collisions.
What is Murmell?
Murmell is a browser-based canvas for running several AI coding agents on one shared project directory in the cloud. It is built around a live workspace where agents can work in parallel and other people on the link can watch the session as it happens.
The product’s core purpose is to make multi-agent coding safer and easier to coordinate. Murmell uses file reservations, shared terminals, and persistent cloud sandboxes so teams can avoid overlapping edits, keep a session in sync, and work without setting up the agents locally.
What can Murmell do?
Real-time file locking
Agents reserve file paths before editing, which helps prevent simultaneous writes to the same file.
Persistent cloud sandboxes
Projects run on cloud machines managed by Murmell, so the workspace is not tied to one developer’s laptop.
Shared live collaboration
Everyone with access to the canvas can see the same terminals, cursors, and live previews while work is underway.
Supported command-line agents
The site names Claude Code, OpenAI Codex, Kimi, and OpenCode as supported agents, with more mentioned on the homepage.
Guided workflows
Murmell publishes numbered guides for common tasks such as using Claude Code without local installation, splitting work across several agents, and sharing a session live.
Use Cases
“Coordinate several agents on one codebase”
Use Murmell when you want different agents to work on separate parts of the same repository at the same time, with reservations reducing the chance of file collisions.
“Run Claude Code from a browser”
The guides describe opening a real Claude Code terminal from the browser, which is useful when you want to use the agent without installing it locally.
“Let teammates watch active development”
Share a canvas link so another person can observe the same terminals, cursors, and previews without refreshing or replaying the session.
“Keep a project running in the cloud”
Use the persistent cloud sandbox when you want the workspace to live on Murmell’s machines rather than on a developer laptop.
“Organize agent-driven refactors”
The examples on the homepage show tasks like checkout recovery, preview refactoring, and design-system updates handled by separate agents in the same room.
Frequently Asked Questions
Which AI coding agents does Murmell support?
The site explicitly names Claude Code, OpenAI Codex, Kimi, and OpenCode, and the homepage also says “and more.”
Does Murmell run agents locally or in the cloud?
According to the site, agents run on dedicated cloud machines managed by Murmell, while the local machine is only used for the browser.
How does Murmell reduce file conflicts?
Murmell uses a reservation system: an agent claims the file paths it is about to edit before writing, so other agents wait until those paths are released.
Can other people watch a session without joining as editors?
Yes. The site says a canvas can be shared as a link and watched live, with no need to replay or refresh the session to stay in sync.
Is pricing publicly listed?
The site indicates Starter is free forever and mentions paid Pro and Builder plans, but the dedicated pricing page fetched for this review returned a 404, so the public pricing information is limited in the collected pages.
Quick Facts
- Category
- Developer Tool
- Product type
- Browser-based AI coding canvas
- Primary users
- Developers working with AI coding agents
- Supported agents
- Claude Code, OpenAI Codex, Kimi, OpenCode
- Hosting model
- Persistent cloud sandboxes
- Website
- murmell.com
Murmell Traffic Analysis
Traffic data is for reference only.
- Domain Rating
- 26
Murmell Alternatives
Solo
soloterm.com
Solo is a desktop workspace for running AI coding agents alongside your local stack, helping developers watch processes, restart crashes, and coordinate workflows.
port22
www.tryport22.com
port22 is an iOS app and macOS agent for monitoring and controlling coding-agent sessions running in a terminal. It streams transcripts to iPhone, sends input alerts, and supports Claude Code, Codex, and OpenCode.
Catenary
thecatenary.app
Catenary is a local-first desktop IDE for running and coordinating multiple AI coding agents on an infinite canvas. It helps developers keep terminals, editors, browsers, worktrees, and agent context visible in one workspace.
Evlat
evlat.kalaomer.com
Evlat is a quiet macOS status strip for monitoring Claude Code, Codex, and Antigravity sessions, plus long-running commands. It highlights sessions that need your response and shows activity from local or SSH-connected machines.
oMLX
omlx.ai
oMLX is a native macOS LLM inference server built on MLX for running compatible language, vision-language, embedding, and reranker models locally on Apple Silicon. Designed for coding-agent workflows, it works with Claude Code, OpenClaw, Cursor, and OpenAI-compatible clients.
Air
air.dev
JetBrains Air runs coding agents in parallel, keeps tasks isolated, and lets you review changes in one workspace. Supports Codex, Claude Agent, Gemini CLI, and Junie on macOS and Linux; Windows coming soon.