We build agents (that build agents)ⁿ: AI that builds better and more specialized versions of itself.

Our mission is to make sure anyone can build an agent that outperforms a frontier lab’s generalist agent on the challenges you care about. The best agent for your challenge should be yours to build: you know the space better than anyone, and the hardest problems require knowledge that never made it onto the internet, such as a science lab’s decade of failed experiments, or a factory’s quirks that only the night shift knows.

The richness of the world’s problems can only be matched by the richness of the intelligences that tackle them. We believe in a Cambrian explosion of agents, instead of a monoculture everyone has to settle for. Your doctor isn’t your lawyer, so why should your agent be both?

Getting there means democratizing recursive self-improvement (RSI). Today, AI that improves AI is concentrated in a handful of well-resourced labs. We want to put that ability in your hands: you build the agents that keep getting better, instead of hoping a future product release will solve your problems. Our goal is to give everyone the power to shape agents for what matters to them.

People are at the center of how our agents improve. Humans are a special case of agents in our self-improving multi-agent system, working alongside the AI agents. They choose which challenges matter, define what “better” means, and recognize when an agent is gaming its own metrics. People’s taste and preferences give self-improvement its direction.

If you’d like to become a MakerMakerMaker, reach out. For anything else, contact us.