Give the next session somewhere to start.
Persistent memory for agents, built on RedDB and planned as a managed service.
Planned service. No self-service deployment yet; we onboard early users by email.
- 01 Messages
- 02 Retained memory
- 03 Relevant context
What is planned
Built around your workload.
Teams whose agents need context across sessions.
- Capture useful context
- The proposed pipeline extracts and embeds memories from application messages.
- Retrieve what matters
- Use semantic retrieval to bring relevant stored context into a new session.
- Control what is retained
- Tenant isolation, retention and deletion must be qualified before managed access opens.
How it works
Managed long-term memory for your agents: messages go in, durable memories come out, and the next session starts with the context that matters.
- 01
Write messages
Your agent sends the conversation. One extraction call per write turns it into memories.
- 02
Store in RedDB
Memories are embedded and kept in RedDB alongside their graph and vectors.
- 03
Recall by meaning
A query is embedded and matched with vector search, returning the memories relevant to the new session.
You would pay for
- Memory tokens (extraction and embeddings)
- Retained memory storage, per GB-month
- Not metered: retrievals, agents, end users or seats
Not promised yet
- The API shape, retention controls and bring-your-own-key options are still being decided.
Source: planning record, as of 2026-09-24.
Related services
Connect the pieces you need.
- AI services RedDB Models A planned OpenAI-compatible model API for applications, the database and agents.
- AI services AI Storage Planned storage and sharing for plans, designs, reports and other agent artifacts.
- Agent execution Agent Hosting Planned managed hosting for Hermes Agent, OpenClaw and Paperclip, with persistent customer environments.
Pricing
Plan the workload before the bill.
The plan separates memory-pipeline tokens from retained storage. Managed access, retention and rates are still being qualified.
Early access
Help shape Agent Memory.
Tell us what you want to run, which models or runtimes you use, and what you need to keep. We will discuss fit and availability before any deployment.