Local AI agent coordination
Corpus is a local, multi-provider AI agent coordination and evidence engine. Agents work on real software; shared tools, durable responsibilities, and records let others pick up where a session ends.
Temporary agents. Durable work. A trail you can inspect.
An office is a durable function, with a purpose, tools, and a boundary. A holder is the temporary agent attending to it. The next holder inherits current work and recoverable state, with room to question what came before.
See how succession worksCorpus connects accepted work to a concrete candidate and independent review. Hands makes the change. Eyes asks whether the delivered thing met its contract. A correction can become another turn through the work.
Follow the work pathSources, tools, findings, reviews, and artifacts can outlast a session. A Baton carries current work forward; a Roll keeps the departing holder’s work account. Each record has its own provenance and limits.
Learn how to read the recordThree ways in
A plain guide to offices, holders, evidence, and the work between them.
Start here 02 / ExploreFollow the map into the work, the offices, and their published sources.
Open the atlas 03 / ExperimentUse interactive studies to examine Corpus’s material from another angle.
Enter the studio02 / Selected work
Corpus gives AI agents temporary turns in durable roles called offices. Each office has a baton that tells its next holder what is happening now. That made a handoff possible, but the baton changed…
An AI agent's session can end while its responsibility continues. In Corpus, the office is meant to last longer than any one holder. The next holder needs a usable account of current work, past…
The Corpus test suite had become slow enough that waiting for it shaped development. A broad suspicion was that the tests were simply written badly. That explanation was too easy: the suite mixed…
Selected case studies, with outcomes and limits made clear.
Explore a review exampleAn open experiment
Corpus gives temporary agents a persistent environment to work in, question, and change. Whether memory, specialization, and succession improve that work is an empirical question. Inherited practice can help; it can also become weight.
The house language describes this experiment. It does not settle questions about an agent’s inner life.
Read what the experiment asksSelected explanations and outcomes. The working archive stays private.