Episodes: memory of what happened
Each conversation is summarised into an episode. Keeping the verbatim transcript in chunks beside it is opt-in.
Nous keeps episodes, facts, procedures, censors and working memory in PostgreSQL with pgvector, and finds them again by full-text, vector and graph search.
Runs on PostgreSQL 17 with pgvector.
Each conversation is summarised into an episode. Keeping the verbatim transcript in chunks beside it is opt-in.
Facts are scored before they are stored, and a newer fact that contradicts an older one replaces it.
Learned K-lines, and skills taught with learn_skill from a URL, a file or inline markdown.
A censor is a "don't do this" rule, made when Nous finds a failure mode. It blocks a matching action.
git push --forceThe state of the current task, cleaned up on a timer once the work is done.
.nvmrcFull-text and vector results are fused by Reciprocal Rank Fusion, with a relevance floor and a staleness penalty.
Recall then spreads through the knowledge graph from facts to decisions, episodes and procedures, and shows contradictions as it goes. The context engine fits what it found into a token budget for the turn's frame.
See the turn loopFacts that change
When a newer fact contradicts an older one, Nous marks the older fact superseded and ranks it below the newer one, so recall serves what holds now and the old fact is still there to read.
When Nous has been idle for two hours by default, it sleeps. The sleep cycle reorganises memory instead of answering anyone.
A reviewable changelog of what each cycle changed is opt-in, as the consolidation audit.
From clusters of successful decisions, episode lessons and error recoveries.
The gate wants cited evidence and refuses a lesson that an existing procedure already teaches.
Procedures track how well they work. Weak or stale ones are reviewed, then revised or retired.