Eidosoma studies collective intelligence in cells, regeneration, and artificial life — using AI scientists to extend computational biological research.
Biology is the last great frontier of intelligence, and it is one we are barely learning to listen to. For centuries we have treated cells as chemistry. They are also decision-makers — solving problems together, in a language we are just beginning to read.
Eidosoma exists to build the collaborators that will help us read that language — and eventually, converse with it. Our AI Scientist is part of that lab: research infrastructure designed to extend exploration while keeping science human-directed.
Eidosoma conducts computational biological research as a continuous loop between human judgement and machine exploration. Our AI scientists help design, execute, and revisit experiments across three interlocking research directions.
Cells talk to each other through many channels — chemical signalling, mechanical forces, and bioelectricity. Building on the work of Michael Levin and others, we model these signals as a substrate for distributed cognition — how a collection of cells 'decides' the shape of a limb, an organ, or a tumour.
Regeneration, cancer, and aging are three modes of the same distribution — tissues losing, regaining, or drifting from the ability to agree on what they are. We search for bioelectric and molecular interventions that nudge a system back toward its target morphology.
We grow open-ended populations of simulated organisms, protocells, and neural substrates — testing how agency, memory, and morphology co-evolve, and what the strongest candidates can teach us about the origins of mind.
The Eidosoma AI Scientist is part of the lab's research infrastructure. It reads across the literature, proposes hypotheses, writes and runs computational experiments, and returns its results to human scientific review — expanding the space we can investigate without surrendering scientific direction, taste, or judgement.
The lab's AI Scientist draws on a set of composable research modules. Below are three of the core ones. Tap to unfold.
The CIP follows preprints, patents, code, conference schedules, registries, and lab notes, then filters and cross-references them against the lab's active questions. Novelty, surprise, and contradiction are prioritised over volume.
The ECM decomposes a research question into runnable experiments, spawns a team of specialised AI coders, reviews their pull requests, and orchestrates execution on the cluster. It keeps a full experiment graph — every run, every parameter, every negative result — so that nothing is ever re-discovered by accident.
Good science rarely comes from climbing the steepest gradient. The Evolution Engine maintains a living archive of diverse candidates — models, protocols, organisms, hypotheses — and keeps exploring the space of what has not yet been tried. Underneath: MAP-Elites, novelty search, and open-ended divergence.

Robert has spent three decades at the intersection of AI, ALife, and collective intelligence — designing systems that help groups of humans, and now groups of cells, think better together. Eidosoma is his answer to a question he has been carrying for years: what would a biology laboratory look like if it worked alongside a collective mind that kept learning?
We welcome conversations with researchers and labs working across bioelectricity, regeneration, artificial life, and AI-enabled science.