Lovable for Science
Open-source platform extending research workflows with modular skills for AI agents. Install capabilities as npm packages.
Overview
As co-founder and CPO at Sundial Scientific, I led the launch of Lovable for Science — an open-source platform that extends research workflows with modular skills for AI agents. You install capabilities as npm packages, expanding what your agent can do, from review and analysis to running experiments.
Key points
AI Literature Review Agent
Built a proof-of-concept tool using AI agents to automate literature review workflows. Submitted to the Agents for Science conference.
8 Papers Submitted
Submitted 8 research papers exploring AI agent capabilities for scientific workflows.
Sakana AI Scientist Integration
Created a chat interface for Sakana's AI Scientist agent, making autonomous research accessible through conversation.
Fine-tuning Agent
Built an agent using the Tinker API that lets users fine-tune models through natural chat conversations.
Skills Marketplace
Designed and shipped the skills marketplace — letting developers publish and install agent capabilities as npm packages.
More research
Building AI agents at Sully, which gives health systems more capacity for care: agents for the front desk, the visit, and everything after, connected to the EHR.
Infrastructure that helps the Department of War find and field technology already proven in university research labs.
A constrained, semi-autonomous coordination agent for scientific research teams. Accepted at the ICML 2026 AI for Science Workshop.