Insilico Medicine releases open-source Longevity Grok AI system with 30 agents
Insilico Medicine launched Longevity Grok, an open-source AI system on November 6, 2026, designed to organize health records, suggest interventions, and score biomarker results using up to 30 AI agents integrated with Grok Bot. Developed with Harvard Medical School’s David Sinclair, the system pairs a personal assistant (PLSI) with an optional opt-in aging-research network (Longevity…
Key points
- Longevity Grok uses up to 30 AI agents on Grok Bot to analyze health records and propose interventions
- Optional research network shares pseudonymous data with strict deidentification, excluding names, exact dates, and free text
- System explicitly excludes clinical use—no diagnoses, treatments, or prescriptions—while enabling N-of-1 experiment tracking
The system ingests fragmented health data—including FHIR records, methylation data, and Grok-extracted JSON—normalizing it into an append-only event log. PLSI orchestrates eight core bots, 13 specialists, and team-specific tools for clinics and labs, with separate memories and contexts. Predictions are scored against follow-up data, turning interventions into verifiable N-of-1 experiments. While free under an MIT license, it requires a Grok Bot account and starts with an individual tier, with physician and researcher tools rolling out by invitation. The project’s code was already public by October 30, 2026, but the announcement formalized its release as a product.
Insilico Medicine Announces Open-Source Longevity Grok AI System
Unite.AI · 6 November 2026
Loading the full article…
This text was published by Unite.AI and written by Rafi Cortez, AI & Longevity / Human Health, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- PSI proves Aaronson-Ambainis conjecture using Anthropic’s non-public model · 1 src
- Mit develops CheMeleon model that outperforms other methods · 1 src
- OpenAI releases BioBasicsBench benchmark; GPT‑6 Astra scores 66.7% on wet‑lab tasks · 1 src
- Baseten releases Serverless Loops for open-model fine-tuning with per-token billing · 1 src
- Ro launches research lab to analyze patient data for clinical insights · 1 src
Comments
via GitHub Discussions