
The Millimetre Problem: Introducing the lab-hardware-cad Agent Skill
Introducing lab-hardware-cad, an open-source Agent Skill that turns any AI agent into a CAD engineer for lab hardware, benchmarked over 98 geometry-scored runs.
K‑Dense builds AI agents that autonomously execute complex work across science, engineering, healthcare, and finance — delivered as a hosted platform, enterprise deployments, and a growing suite of free, open-source tools.
Trusted by researchers from


Our Products
From our flagship hosted research agent to free open-source tools you can run today — every K‑Dense product is built to accelerate real research.
Research. Analyze. Synthesize.
Our hosted AI research agent with access to 250+ databases, hundreds of thousands of on-demand tools, and native support for 200+ scientific data formats. Autonomously executes complex tasks across science, engineering, healthcare, finance, and beyond.
The research agent, deployed your way
K-Dense for organizations: private deployments, custom integrations with your internal data and tools, dedicated support, and the security and compliance controls your team requires.
80 minds, one question
A free AI research tool that turns one question into 80 perspectives in under a minute. Philosophers, scientists, AI researchers, and founders answer live in parallel — each in their own voice, with cited sources and a cross-persona consensus. Built on our open-source Mimeographs library.
Your local AI co-scientist
A free, open-source research assistant called Kady that runs on your desktop and uses your own API keys. It can answer directly, delegate bigger tasks to specialist agents, run multiple chats in parallel, and switch across tool-capable OpenRouter or local Ollama models.
Research-backed scientific writing
A deep research and writing tool for publication-ready papers, reports, posters, grant proposals, literature reviews, and other academic documents. It researches before writing, supports real-time literature lookup, verifies citations, converts documents, and can run as a Claude Code plugin, Python package, or native CLI.
141 ready-to-use scientific skills
A comprehensive collection of scientific and research skills for any AI agent that supports the open Agent Skills standard. Covers biology, chemistry, medicine, cancer genomics, drug-target binding, molecular dynamics, RNA velocity, geospatial science, time series forecasting, 78+ scientific databases, and more.
Partners
What Researchers Say
“This platform is essentially providing me a dozen PhDs and postdocs in my pocket. I see myself as the PI, asking questions to my postdocs, and my postdocs just keep giving me the information. It’s a postdoc that never says ‘I don’t know.’”
“You upload a bunch of Excel spreadsheets and, without too much description, it figures out where the fold change is and then goes and does all the statistics. I thought it might struggle with figuring out all these columns, but it was remarkably good with that. It’s also much better at finding references than ChatGPT.”
“I was very impressed with the original reports it was able to generate — the workflow was solid in terms of the actual analysis it was doing. A workflow like that by hand would take me a week, two weeks. I didn’t mind letting it go off and think for seven hours, because the output was such high quality.”
Open Source
We ship 10 open-source libraries, skills, and tools that anyone can use — with or without a K‑Dense account. From agent skills for scientific computing to a full desktop research assistant.
From the Blog
Stay up to date with AI research automation tips and product updates

Introducing lab-hardware-cad, an open-source Agent Skill that turns any AI agent into a CAD engineer for lab hardware, benchmarked over 98 geometry-scored runs.

K-Bench 01 is our internal benchmark built from 178 real scientific tasks. Nine frontier models ran them end to end; only one clears the acceptability bar.

K-Dense and Litmus Science are connecting AI-powered research with on-demand lab execution, helping scientists move from questions to evidence faster.
Backed by