Workflows for AI agents and tools

Build a workflow.
Let your agents run it.

Tell your assistant what to do, which steps to follow, and which checks must pass. It builds a workflow. Muxlio runs it across agents and tools, saves progress, and lets you follow the results.

Claude · Codex · Cursor · Kiro · command-line tools

EXAMPLE: IMPLEMENT FEATURES DURABLE
For each feature: implement → review → test → fix if needed → commit after checks pass.
01ImplementMake the change and record the workAGENT
02ReviewInspect the change and address issuesAGENT
03Verify & repairRun checks; fix failures and try againCHECKS
04Commit locallyYou review the commit and choose when to pushYOURS
THE IMPLEMENT-FEATURES RECIPE

How I use Muxlio to implement features

I use this recipe to develop Muxlio itself. The workflow handles one feature at a time and runs the repository’s build and tests before creating a local commit.

01 · YOU⌘

Build the workflow with your assistant

Describe the steps and checks you want. Your assistant authors and validates a workflow, then starts a run with your inputs. Check the plan before starting the run.

DESCRIBE → BUILD → VALIDATE → RUN
02 · MUXLIO⇢

Implement, review, test, fix

An agent implements the feature. A review step inspects and improves the change. Build and test commands run. If a check fails, an agent gets the failure report, fixes it, and the checks run again.

Until checks pass
testfixretest
03 · YOU◷

Review the result

After checks pass, the recipe creates a local commit and moves to the next feature. Inspect the diff, review notes, test output, and run history. You decide whether to push.

CHECKS PASS → LOCAL COMMIT → NEXT FEATURE
HOW I USE IT

I run feature work overnight.

I run Muxlio on a Mac mini and start workflows through my assistant. In the morning, I check the commits and reports. If a run stopped, I read the error and decide what to do next. The chat can be closed while it runs.

You choose where it runs: your workstation, another computer, or a server. Keep the execution machine running and use the UI or your assistant to check progress.

✓See what happenedLive logs, review notes, check results, and attempts
✓See what needs attentionA failed or paused run keeps its progress and reason
✓Review before pushingThe recipe creates local commits; you choose when to push
GET STARTED

Install Muxlio, then start the service.

Use Homebrew on macOS or Linux. It installs the CLI, adapters, UI, and MCP server without a manual checkout.

brew tap Muxlio/muxlio https://github.com/Muxlio/muxlio
brew install --HEAD Muxlio/muxlio/muxlio
muxlio version

Then, from the workspace you want to use:

muxlio init --client kiro --scope project
muxlio service start

init prepares your workspace configuration, credentials, agent instructions, and MCP settings. Fresh configs enable the bundled executors, including command. service start starts the coordinator, worker, UI, and MCP listener together.

Connect your assistant with the MCP guide. Ask it to build a workflow for your task, validate it, and show you the plan before running it. You do not need Muxlio's source repository to use the installed service. The worker needs the files and tools your workflow uses.

For the feature example, the workflow and its verification commands are in the implement-features recipe. Use it as a starting point and adapt the steps, agents, and checks to your work. The Docker Sandbox walkthrough shows two dependent features running against one branch in a private clone with Claude Code, Codex, Cursor, and command execution available on the sbx worker. Select localhost for the host checkout or sandbox for the Docker checkout. Follow a run in the UI at http://localhost:7600 or ask your assistant for its status.

EXPLORE MUXLIO

Guides and reference

Build your own workflows with the CLI and SDK reference ↗