Mozaik enables autonomous agent teams to work concurrently, react to events, communicate intelligently, and decide how collaboration should unfold during execution.
Congrats on the launch. Self-organizing teams live or die on shared state design. We run a multi-agent system in production (Elixir GenServers, a similar concurrency model to what you are doing in TypeScript) and the pattern that saved us was a central coordinator owning durable memory that agents read and write through, rather than agents passing context peer to peer. It kills most duplicate work before it happens, and it gives you one place to audit why an agent decided anything. The event-reactive angle is the right call too, polling loops burn tokens doing nothing. Curious whether agent memory in Mozaik survives process restarts or lives and dies with the run.
Thank you to everyone who supported Mozaik and raised such thoughtful questions about observability, cost, control, shared state, and safe agent autonomy.
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.
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.
Pretty cool idea. How does it handle conflicts when two agents try to modify the same shared state?
Not having to draw the full graph up front makes sense.
One thing I'm not sure about though. When one agent fires an event and another one picks it up, how does the second agent know what the event actually means? Like is there some kind of schema they both agree on ahead of time, or is the LLM just reading the event name and figuring it out? Because I could see two agents both reacting to something called "data_ready" but one thinks it means raw data and the other thinks it's already cleaned.
We run a lot of coding agents concurrently at my company and the thing I'd worry about here is cost, not just correctness. A fixed DAG means you can roughly predict how many LLM calls a workflow burns. Once agents are deciding at runtime whether and how to communicate, that overhead becomes a lot less predictable - a bad interaction pattern could quietly multiply your token spend without anyone noticing until the bill shows up. Is there any built-in visibility into inter-agent communication volume/cost, or is that left entirely to the developer to instrument themselves?
A live visualizer showing each agent's current task, message queue, and decision rationale in real time would be huge. When something goes sideways, it is way easier to debug collaboration logic if you can see what each agent is thinking at the moment rather than digging through logs after the fact.
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.
the agents actually talking to each other mid-task felt weirdly alive, like watching a small team figure things out on its own
Mozaik being a TypeScript runtime for self-organizing AI agents makes me curious about the boundaries of the runtime. Is the main focus on agent coordination, task planning, memory/state, or giving developers a safer execution model for agents? Since it’s listed under Developer Tools and Engineering & Development, I’d be interested to know what a first integration looks like for an existing TS project.
Letting the runtime decide collaboration instead of hardcoding a workflow graph is the interesting bet here — most agent frameworks make you draw the DAG up front. When agents self-organize at runtime, what stops two of them from looping or deadlocking on the same task, and is there an execution budget or supervisor that halts a run? And does the runtime state live in-process or in something external I can inspect and replay a run from?
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
Top 3 things to do if you wanna make intelligent agentic systems:
“TypeScript runtime for self-organizing AI agents”
Mozaik launched on Product Hunt on July 6th, 2026 and earned 120 upvotes and 27 comments, placing #11 on the daily leaderboard. Mozaik enables autonomous agent teams to work concurrently, react to events, communicate intelligently, and decide how collaboration should unfold during execution.
Mozaik was featured in Developer Tools (515.4k followers), Artificial Intelligence (473.1k followers) and SDK (791 followers) on Product Hunt. Together, these topics include over 181k products, making this a competitive space to launch in.
Who hunted Mozaik?
Mozaik was hunted by Miodrag Vilotijević. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Mozaik stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Miodrag Vilotijević
Congrats on the launch. Self-organizing teams live or die on shared state design. We run a multi-agent system in production (Elixir GenServers, a similar concurrency model to what you are doing in TypeScript) and the pattern that saved us was a central coordinator owning durable memory that agents read and write through, rather than agents passing context peer to peer. It kills most duplicate work before it happens, and it gives you one place to audit why an agent decided anything. The event-reactive angle is the right call too, polling loops burn tokens doing nothing. Curious whether agent memory in Mozaik survives process restarts or lives and dies with the run.