Science, Open to All

Open-Science v0.36.0

Review risky Notebook runs before execution, translate full PDFs across sessions, discover cancer proteomics and linkage-disequilibrium data, add Claude Haiku 5.5, and select all in library toolbars.

• Reviewable Notebook execution

  Screen every Notebook run for risky code before dispatch, show a focused source-line review card when needed, and retain a durable receipt

• Resumable shared PDF translation

  Translate a full PDF with paragraph-level checkpoints and resume across sessions in original, translation, or side-by-side compare modes

• Connector reach

  Discover cancer proteomics studies, biospecimens and quantitative file metadata through a new PDC connector, and run population-specific Ensembl linkage-disequilibrium queries

• Claude Haiku 5.5

  Choose Claude Haiku 5.5 from the bundled Anthropic model catalog, with its 1M-token context window

• Page-level select all

  Select all records loaded on the current Literature Library or Inbox page from its batch toolbar

Articles & guides

Read & watch

Product overview

What it does

• Package and continue with .science — Carry selected conversation branches, file and artifact versions, Notebook records, and verification evidence to another project or computer for review, handoff, or archiving. Import packages as read-only records, or create a writable copy to continue the work.
• Open architecture — Connect multiple model providers, agent frameworks, custom gateways, reusable Skills, and scientific connectors in an Apache-2.0 codebase.
• Execute research workflows — Run Python, R, and shell workflows directly so agents can perform computational tasks, not only suggest code.
• Manage the literature — Import references by identifier or file, organize collections, compare and merge duplicates, retrieve open-access PDFs where available, and format citations.
• Preserve traceable artifacts — Keep reports, tables, figures, and notebooks as immutable versions with available links to inputs, code, execution history, environment details, conversation branches, and reviewer evidence.
• Control the infrastructure — Keep project state on your machine by default and govern file, command, network, connector, and compute access through permissions. Connect locally deployed models or external services when configured.