Science just got an open agent harness before it got a killer app. langchain's deep life sci, out…
science just got an open agent harness before it got a killer app. langchain's deep life sci, out september 17, plugs agents into over 600,000 clinical trial records and 29 million pubmed abstracts.
the lab assistant is now a template anyone can fork.
Context
LangChain's blog of 17 September 2026 introduces Deep Life Sci, an open-source agentic assistant for clinical and lab scientists built on its Deep Agents harness as a template for companies to adopt and modify. It cites clinical trial records from over 600,000 registered studies on ClinicalTrials.gov, 29 million paper abstracts through PubMed and 12 million full-text articles on PubMed Central, gives each agent a LangSmith sandbox, ships a default eval set and runs traced in the user's own LangSmith account. The langchain-samples/deep-life-sci repository is MIT licensed, created 2 September 2026, with 30 stars when read, and its README says over 8 million full texts.
The 600,000 and 29 million are first-party. The PubMed Central figure is 12 million in the blog and 8 million in the README and was not reconciled. Running it as shipped needs a LangSmith account and sandbox, so open does not mean free of that dependency. The blog gives example workflows and no benchmark, user study or accuracy result, and reduced documentation time is a possibility the vendor states and not a measured result. It is a reference template in a samples organization, and the repo's creation date is not release proof. That science got an open harness before a killer app is the author's opinion.
Watch next
- Release tags, the default eval set contents and any reported evaluation results.
Sources
- An agent harness for life sciences (LangChain, 17 Sep 2026)langchain.com
- langchain-samples/deep-life-sci (GitHub)github.com
- langchain-ai/deepagents (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 12:04 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →