Open source
Open Multi Agent: Approve Every Agent Action
Open Multi Agent is a self hosted coding library for building agent teams inside your own program. Consequential actions pause for a durable human approval, and each run keeps a journal you can verify offline. MIT licensed.
Watch on YouTube · Watch on TikTok
The story
What the video said
This open source GitHub project turns a goal you type into a team of agents that plan and run tasks for you. You stay in charge of every step they take.
You want your AI coding tool to write files and run shell commands on its own, but you do not want it to touch anything important without asking you first.
Open Multi Agent is an open source coding library for building agent teams inside your own program. You give it your own model keys and your own tools.
When an agent wants to write a file or run a command, the run can pause and wait for your approval. Each run also keeps a journal you can check offline.
So you get agent teams that plan and act, with a human approval gate and a run record you can verify later. That is the whole point of the project.
This page was generated from the Ming Dao AI publication record.
Ming Dao AI is independent and unaffiliated with GitHub or the featured project. Read our editorial policy.