Domain-specialized agents that compress the digital R&D loop from months toward days — literature, characterization analysis, cross-technique validation, reporting.
A materials R&D team spends enormous time searching fragmented literature and databases, designing experiments, optimizing synthesis and process parameters, and turning raw instrument output into defensible decisions. Each full pass — hypothesis to validated result — takes months. That bottleneck compounds across a lab, a company, a decade of needed breakthroughs.
General tools don't speak the instrument file formats — .rasx, .mpr, .vms, BELMaster CSV.
They don't know the characterization conventions, and can't run the analysis on real data.
They can't reach the right scientific databases — crystal structures, diffraction references, the literature.
They never hold the project — context is lost the moment the session ends.
Materials science needs domain-specialized agents with the right tools, data access, and project memory — not a general chatbot.
Create a project, bring your data, and work alongside an AI agent specialized for materials science. It reads and writes the project's files, runs real analysis in a sandbox, searches the literature, consults 33 materials skills, and keeps the whole project in context across sessions. It is not a chatbot with a science skin — it is the place the research lives.
Pt-MoS₂.rasx — identified 2H-MoS₂ (002) at 14.4°. Pt (111) present, weak — consistent with low loading. Cross-checking S 2p in the XPS now.Illustrative — workspace shown is a design preview.
The end state is the full autonomous research loop. We've mapped it as ten nodes — four work today, on real data. The platform fills in the rest, node by node.
We're claiming the path, not the destination.
.rasx, .mpr, .vms, BELMaster CSV and more. Generic AI tools simply cannot open these files.Stoich targets the slow, expensive parts of the materials R&D loop — characterization analysis, literature triage, cross-technique validation today; experiment design and protocol tooling next. The same agents serve a corporate R&D group, a national lab, or a hard-tech startup.
Every project compounds into a provenance-rich record of how a material was actually made — the dataset that trains the autonomous lab.
Six things we're committed to — and a few we're still poking at. Roadmap commits move into the loop only when they run on real data.
Open the demo project — real multi-technique characterization data for a Pt-MoS₂ catalyst. Then bring your own.