Persistent memory for eve agents
- Source
- vercel.com
- Author
- Andrew Barba
- Date

Context
Vercel's eve agents can retain information across conversations through named memory slots. Each slot specifies both a storage provider and a scope, such as an individual authenticated user. Before a turn, eve retrieves relevant saved information and adds it to the model's .
The announcement distinguishes remembering from updating: depending on the provider, changes can be saved automatically after a turn, through tools the uses, or through both. For agents deployed on Vercel, the built-in file provider uses a private Vercel Blob store, so saved memories persist across restarts and deployments. Developers therefore configure both where memory lives and which conversations share it.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
“eve agents can now retain context across sessions and use it in future conversations.”
“Before each turn, eve retrieves relevant memory and adds it to the model's context.”
articleFilesystem-Based Memory for LLM Agents: Organization, Evolution, and SustainabilitySizhe Zhou, Sheldon Yu, Hui Wei, Junda Wu, Siru Ouyang, Yizhu Jiao, Shijia Pan, Julian McAuley, Yu Zhang, Tong Yu, Jiawei Han
articleMem0 joins the Vercel MarketplaceHedi Zandi
articleDetailed Guide to Agent Memoryvasa_
Checking sign-in…
Loading comments…
