We chose eLabFTW for our AI lab build

We have the advantage of starting a lab at the moment Artificial Intelligence is arriving on the scene. We can build our workflows around AI from the ground-up and be part of this emerging computational paradigm.

The lab notebook is naturally one of the first decisions new labs need to make. When I started as an undergraduate, everything went into paper notebooks. I color-coded by hand and taped experiment printouts onto the pages.

I generated a few linear feet of notebooks as a PhD student, but they stayed with the lab when I graduated. That made sense: research is collaborative, and my notes were part of a larger investigative program. Other researchers could continue using my data when relevant to their own projects.

Our requirements

In Kupalab, we’re planning to host our electronic notebook on a local lab server, with encrypted cloud backups. Researchers will be able to search across experiments, add results directly from the instruments and follow how a project develops. We want to make it easier to find old experiments and trace the genealogy of new observations back to their source.

We also want to use AI to help search and compare experiments as the lab grows. That takes more than adding a chatbot later: our data needs to be structured in formats we can export and use with other tools, and our electronic lab notebook needs to connect to those tools.

One connection we cared about is MCP, an emerging standard for AI assistants to communicate with software tools. We wanted to choose the LLM ourselves, including the option to run one locally. We also want to keep our data close, in systems we can control, and retain practical freedom to move it if our needs change. Exports and an API can help keep our records portable.

Our options

We looked at Benchling, Scispot, SciSure/eLabNext, LabArchives, SciNote, RSpace and eLabFTW. Each offered a different balance of features, hosting, cost and openness to the kind of AI connection we wanted.

Benchling was an attractive name to investigate. But during our evaluation, its MCP server was not available with Benchling for Academics. Benchling’s documentation described the MCP option for Enterprise users, and setting it up required Benchling Chat to be enabled. That put the route we wanted behind a commercial offering, beyond what made sense for a small academic lab starting from scratch. We set it aside.

Scispot’s hosted approach seemed less suited to our preference for keeping control of where the main records live. For LabArchives and SciNote, we could not confirm a clear, supported route to the AI connection we wanted. Our shortlist narrowed to open-source RSpace and eLabFTW, both of which we could host ourselves and build on. SciSure/eLabNext remains a commercial alternative if a managed service proves the better fit.

Cost matters when a lab is just getting started. We’re stretching departmental research funds and asking colleagues with resources to spare to help equip the lab. eLabFTW’s software has no license fee; the server, backups and maintenance still take resources, but skipping a commercial subscription is a very attractive price point for us. The API gives us a starting point to build or adapt an AI connection, though that work is still ahead of us. With eLabFTW’s large community of engaged users, we expect the ecosystem’s AI integrations to evolve rapidly.

We’re excited to have made this choice, and a little trepidatious too. Choosing a lab notebook is a serious commitment: it shapes our daily work, preserves our findings and affects how future members of the lab shape their contributions.

Fortunately, eLabFTW offers exports in several formats and a public API. We hope these options will make it easier to take our records with us if our needs change or we decide to move in a different direction. That gives us room to start, learn from experience and adapt as the lab grows.

Are you integrating AI with your electronic lab notebook? I’d love to hear what criteria shaped your choice and how the integration is going. We’re early in building Kupalab and would especially welcome input from current eLabFTW users: how have you found the development community, and what efforts to connect eLabFTW with AI are you following or trying? Your experience could help us make better decisions as we build. Comment below: