Jev in production › Agent context and memory
Local compiler over Markdown knowledge bases for agent retrieval; enzyme compile runs its selection step on Jev (typesafe/jev-1.13) through OpenRouter, with output in about 0.5s. 350x cheaper than frontier models (author).

Enzyme compiles your notes and other knowledge sources into a local index that:
1. Uses temporally grounded context sampling that captures the contextual use of tags and wikilinks, or natural accumulation in folders (i.e. pseudo-Zettelkasten) 2. With this context, it "dreams" questions in the background (called catalysts) and embeds them. At query time, each question finds its nearest docs, so it avoid needing to "dream" full summaries. (see note) 3. Keeps refreshing, but separates new doc ingestion (local, fast) from catalyst evolution (cheap, periodic)
For the project's own README, linking back here: