New York City, NY, June 15, 2026 (GLOBE NEWSWIRE) — Weaviate, the company behind the open-source AI-native database, announced the general availability of Engram, its managed memory and context service for agentic applications. Engram is available now in Weaviate Cloud, including a free tier.
As organizations move AI agents into production, most hit the same limitation of agents not being able to reliably remember users across sessions, learn from feedback, or share context when a task spans several agents. Teams use workarounds that do not scale well with real-world complexity, such as replaying entire conversation histories into models, hand-curating files, or building custom memory systems. Engram treats memory as first-class infrastructure alongside storage and retrieval.
Engram keeps memory actively maintained rather than accumulating. Instead of piling up an ever-growing context, it runs asynchronous pipelines that extract facts, reconcile them against what’s already known, handling deduplication and updates to persist clean and structured memories. The pipelines are fire-and-forget: applications hand off raw events and keep working while memory is built durably in the background. Memories are served back through Weaviate’s hybrid search, so teams get a memory layer powered by the retrieval stack they already trust.
Scoping is fundamental to Engram: memories are isolated per project, per user, and per property, so the right context reaches only the right caller. Common use cases such as personalization, continual learning, and multi-agent shared state ship as ready-made templates, and teams can customize projects to fit their needs.
“Memory is the difference between an agent that answers a question and an agent that gets better at its job,” said Bob van Luijt, CEO and co-founder, Weaviate. “With Engram, every team gets a production-grade memory layer without building or operating one themselves on infrastructure they already trust.”
Engram is generally available today in Weaviate Cloud. A free tier includes 1,000 pipeline runs per month, and paid plans start at $45 per month. Documentation, an architecture deep dive, and a quickstart tutorial are available here.
About Weaviate
Weaviate is the company behind the open-source AI-native vector database used by developers to build AI applications at scale. The Weaviate platform spans the Weaviate Database, Query Agent, and Engram. Weaviate is open-source and downloaded more than 150 million times per month.
Official website – https://weaviate.io/
