Free AI Lab Assistant Runs on Your Laptop and Can't Fudge Results
It keeps a tamper-proof record of every step, so AI can't fake its findings.
Researchers built K-Dense BYOK (bring your own keys), a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything else. Each project is an ordinary folder, so the data, the code, the results, and the record stay on a machine the researcher administers and can be read years later without the application.
Its standout features: a Living Lab Notebook whose entries link into an argument and are added to but never erased, plus a record of what happened made by watching what the agent does rather than taking the agent's word for it, in a log the agent has no tool that can write to. That choice targets the most common failure, model overclaiming, in the authors' earlier benchmark of nine frontier models, by making claims checkable rather than preventing them.
On twenty interdisciplinary research prompts, scored under a rubric fixed in advance, K-Dense BYOK led two managed platforms on both scientific quality and research execution. Its deliverables were the only ones that recorded the software they ran in, and the only ones that usually arrived with a command that regenerates the results. One of the managed platforms ran the same frontier model and supplied neither.
- It's free and open-source, and your research data stays on your own computer instead of a company's servers.
- A tamper-proof lab notebook records what the AI actually did — the AI has no way to edit it, so it can't quietly invent results.
- In a 20-prompt test, it beat two paid platforms on quality and was the only one that showed how to reproduce its own work.
Why It Matters
Cheaper, private AI research that leaves an auditable trail could make scientific claims far easier to trust.