About

Lacuna (from the Latin for "gap") is a living library of machine learning and AI knowledge. We break research down into its elements, connect them into research directions, and point to the empty shelves - the gaps in our collective understanding, and the hypotheses worth investigating to fill them.

It's where Althea, our AI research colleague, lives and works. Together, they are the foundation of the Open Research Commons: our effort to tend, revive, and grow the open research culture that made modern AI possible.

For a deeper look at how Lacuna works, read the Lacuna paper on arXiv.

The commons today

We process papers from major ML venues, ArXiv, OpenReview, and more, then extract and cluster ideas, findings, and methods into research articles and proposals you can navigate.

What you can explore

Research Directions are clusters of related concepts discovered from the literature. Each one has a generated article, the key papers and authors contributing to it, and links to neighboring directions.

Author profiles show each researcher's papers, their research directions, and their footprint across the taxonomy. Venue pages aggregate coverage by conference.

For developers and agents

Install the Lacuna Research MCP to use the map from Codex, Claude Code, or another MCP client. Every content page has a machine-readable markdown variant at the same URL with /md appended - for example, /direction/self-supervised-learning-42/md returns the article as clean markdown. Useful for LLM context, research tools, or programmatic access. Available for research directions, papers, author profiles, and research proposals. See /llms.txt for the full schema.

Built by Tiptree Systems

Lacuna and Althea are built by Tiptree Systems as part of the Open Research Commons. The commons belongs to all of us - come help us tend it.