Anthropic Launches Claude Science, an AI Workbench for Scientific Research

Anthropic has rolled out Claude Science, an AI workbench aimed at researchers, representing a notable advance in using artificial intelligence to speed up scientific discovery. The app is built to bring together the tools and packages scientists routinely rely on, produce outputs with a clear audit trail, and offer flexible access to computing power.

Fragmented Workflows, Unified Environment

Scientific research often means hopping between different databases, file formats, and tools like PubMed, Jupyter, R, and cluster terminals. Claude Science pulls these scattered pieces into a single research environment, letting scientists handle everything from literature analysis to executing multi-step research and polishing figures and manuscripts for publication, all in one place.

Every output inside Claude Science comes with an auditable history, making validation and reproducibility straightforward. Much like a Jupyter Notebook, it can be run locally on macOS or Linux, or accessed remotely via SSH or an HPC login node.

Agent-Driven Collaboration

Users work with a generalist coordinating agent that taps into over 60 curated skills and connectors, pre-configured for fields such as genomics, single-cell biology, proteomics, structural biology, and cheminformatics. These agents can spawn sub-agents and interact with specialist agents that users create themselves. A dedicated reviewer agent checks citations and calculations, flagging and fixing errors on its own.

Claude Science generates rich scientific artifacts, including 3D protein structures, genome browser tracks, and chemical structures. Each output is paired with the exact code and environment used to produce it, alongside a plain-language explanation and the full message history, making validation and reproducibility easier.

Compute Management and Scalability

The platform can manage computing resources across a user's laptop, HPC cluster, or cloud GPU providers. When scaling up analyses, Claude Science drafts a plan, asks for permission before tapping into new resources, and lets users review or revoke any decision before the job runs. It supports HPC clusters via SSH and on-demand compute through services like Modal.

Because its agents operate inside a running session that retains context in memory, large datasets only need to be loaded once. The platform runs on the user's existing infrastructure, ensuring sensitive data never leaves trusted systems.

Domain-Ready on Day One

Claude Science comes pre-configured for biology and chemistry research, connecting to over 60 scientific databases, including UniProt, PDB, Ensembl, Reactome, ClinVar, ChEMBL, and GEO. It also integrates with NVIDIA's BioNeMo Agent Toolkit to connect natively with life science models and libraries such as Evo 2, Boltz-2, and OpenFold3.

Researchers can tailor the platform by saving pipelines as reusable skills or linking their preferred tools via connectors, settings that future sessions will automatically inherit.

Early Adopter Results

During beta testing, researchers used Claude Science for tasks ranging from single-cell RNA sequencing analysis to CRISPR screen design and protein structure prediction. Manifold Bio used the platform to nominate targets for tissue-targeting medicines. At the Allen Institute, Jérôme Lecoq built a multi-agent template to write long-form reviews, slashing a process that previously took up to two years to a fraction of the time. Stephen Francis, a UC San Francisco epidemiologist, used Claude Science to accelerate glioma molecular epidemiology studies, cutting analysis time by roughly 90 percent while producing results independently validated by his group.

Availability and Grants

Claude Science is available in beta on macOS and Linux for Claude Pro, Max, Team, and Enterprise users. Team and Enterprise accounts require administrator approval. Anthropic is offering discounted Team plans for academic and nonprofit research labs.

The company is also supporting up to 50 AI for Science projects with up to $30,000 in credits, with Modal providing up to $2,000 in compute for select projects. Applications are open through July 15, 2026, with projects running from September 1 to December 1, 2026.