Matha Labs / Product roadmap
Start with human activity intelligence and a focused desktop robot. Build useful enterprise data and integrations, then expand into mobile assistance and a place for robots to return.
Updated September 21, 2026
Future dates are proposed planning targets. Scope and timing depend on prototype results, partner requirements, funding, and validation.
Verified starting point
The deployed glasses HUD provides a compact display interface and D-pad navigation. Its current data is mock; activity capture, camera/microphone integrations, and the live companion-data path remain development work.
Open the glasses HUDMatha Labs v8 shipped the public lab and product site with illustrated robot interaction, a published changelog, and a page-view counter. The illustrations demonstrate intended interactions rather than connected hardware.
Read the release historySeptember 2026 / In development
The website includes a working data example, source directory, and configured account flows. Activity models, physical robot integration, and production enterprise collections are still in development. Our first hardware priority is a simpler desktop arm.
September 21, 2026
One public robot episode produces 303 curated records, 151 separately generated records, playable workflow videos, and provenance downloads.
Inspect the working exampleSeptember 21, 2026
Google and email/password providers are configured in a new Matha Labs project. Create an account or sign in through the account page; email signup/sign-in passed a temporary-account test.
Open account accessSeptember 21, 2026
Fifteen externally published datasets are searchable by task and research area, with publisher, access, and licensing links.
Browse the directoryActivity, object, and intent understanding; glasses interfaces and companion capture; an initial shared robot SDK and account experience.
Curated source discovery, scoped enterprise collections, and early labeling and simulation demonstrations. Real samples and generated examples stay separately identified.
An open-source 3D-printable design, component selection, assembly planning, and a focused set of desktop tasks to validate.
Proposed milestones
Make the first data workflow repeatable and prepare a shared robot SDK preview using a simulator. Prototype first-person capture through a compatible device or companion camera.
Evidence to review: reproducible exports, command permissions, simulator behavior, and capture limitations.
Assemble and validate the physical desktop arm, connect capture and replay, and scope initial enterprise activity collections. Evaluate SAM-assisted labels and generated variations against agreed task and quality criteria.
Evidence to review: physical task results, participant permissions, annotation quality, provenance, and a working integration guide.
Broaden supported tasks based on pilot results. Explore a smaller mobile robot arm for selected cleaning or yard assistance and begin AI-shed research around compatible docking, charging, and tool storage.
Evidence to review: transfer to new activities, human review results, and mobile-task feasibility.
Develop an AI shed concept around compatible docking, charging, and tool storage for a mobile arm or humanoid. Use the robot’s actual dimensions and operating needs to guide the design.
Evidence to review: compatibility, approach and docking trials, charging integration, and tool access.
Preserve the earlier four-arm backpack studies and revisit them after simpler systems demonstrate practical utility. Wearable hardware remains later research.
Progress depends on demonstrated usefulness and independent mechanical and operational validation.
Bring a specific activity, dataset need, or compatible robot integration. We’ll define the scope and the evidence that would make it worthwhile.