Mozaik
TypeScript runtime for self-organizing AI agents
134 followers
TypeScript runtime for self-organizing AI agents
134 followers
Mozaik enables autonomous agent teams to work concurrently, react to events, communicate intelligently, and decide how collaboration should unfold during execution.
Self-organizing agents are interesting, but the practical test is whether a human can understand why work moved from one agent to another. I would make ownership, handoff reason, and stop conditions visible before optimizing for autonomy.
Mozaik
@krekeltronics Yes, over the next weeks and months we want to understand the right balance for humans: what needs to remain visible and controllable, and what can be left to agent autonomy.
We are modeling a concept called Interception, which gives users space to influence execution at important decision points. The idea is to let humans make high-level decisions without forcing them to micromanage every interaction between agents.
Control can also come from the runtime environment itself. For example, if you add a reviewer agent with the right tools, other agents can recognize when to delegate work to it.
the agents actually talking to each other mid-task felt weirdly alive, like watching a small team figure things out on its own
Mozaik
@saniye0ike Exactly. We are not excluding agents from following a workflow and collaborating through it. Mozaik is simply a more abstract layer where the workflow does not have to be hardcoded manually and can emerge through agent communication at runtime.
Setup was fast and watching the agents hand off tasks without me prompting them felt surprisingly natural. The event-driven reactions remind me of having a small team that actually talks to each other.
Mozaik
@ufukamac8zz Yes, that was exactly our starting point: why shouldn’t agents behave more like humans?!
Mozaik
Thank you to everyone who supported Mozaik and raised such thoughtful questions about observability, cost, control, shared state, and safe agent autonomy.
We summarized the most important lessons from the launch here:
https://mozaik.jigjoy.ai/blog/what-we-learned-from-launching-mozaik-on-product-hunt
Miodrag, the idea of letting a bunch of helpers sort out who does what on the fly, the way a good team naturally does, is oddly delightful. It feels much closer to how real work actually happens.
Mozaik
@raphael_kamm Yes! We’re really excited to work on this idea!
Mozaik
Top 3 things to do if you wanna make intelligent agentic systems:
Stop hardcoding agent collaboration
Stop hardcoding agent collaboration
Stop hardcoding agent collaboration
https://mozaik.jigjoy.ai/
Mozaik
For everyone who believes AI is already smart enough to organize agents at runtime—rather than forcing developers to manually define every workflow—star Mozaik on GitHub: https://github.com/jigjoy-ai/mozaik