Building in the open

Updates.

What we are building, in the order we build it. Milestones, research direction, and shipped work \u2014 without the internals.

  1. April 2026Research

    Landscape rebuilt as a data hub

    The AI for Science Landscape now tracks structured entity metadata, autonomy-stack roles, dimensional scores, ecosystem events, science-relevant AGI benchmarks, and source-backed citations. The page is designed to evolve toward a benchmark-institute style public dataset.

  2. April 2026Milestone

    First end-to-end autonomous research run

    ALP's agent swarm designed an experiment, executed it, and verified the results without human intervention. The research report was generated autonomously. A write-up is in preparation.

  3. April 2026Product

    scivity.org launches

    Public site live. Includes the AI for Science Landscape — an open, continuously updated map of the field, free to reuse under CC BY 4.0.

  4. March 2026Research

    Verification pipeline complete

    Every finding that leaves the platform now passes through multiple independent checks for novelty, statistical validity, and reproducibility. Verification is the piece most prior autonomous-science systems have lacked — it is how claims become trustworthy.

  5. February 2026Research

    Multi-agent swarm deliberation

    Explorer, Exploiter, and Critic agents now debate hypotheses before compute is spent. Weak ideas get filtered out at the planning stage, not after hours of wasted experiments.

  6. January 2026Origin

    Scivity Labs begins

    Founded to build the operating system for autonomous science — AI-native infrastructure where agents design, execute, and verify scientific experiments end-to-end.

Updated as the work happens. For technical depth, reach out directly.