Overview
Most teams now run agents on more than one runtime: one model provider for coding, another framework for support, Amazon Bedrock for internal pipelines. Each keeps its own memory, and none of them records what people approved. Switch runtimes, or try to explain what an agent knew when it acted, and that state is scattered or gone.
Jennah is the system of record for agent state, neutral across model providers and agent frameworks. It holds three layers in one consistent backend, under one enterprise boundary and access model.
WHAT YOUR AGENTS KNOW
Execution logs, vector chunks and knowledge graphs, written atomically and read from a single snapshot. Send raw conversation turns and tool traces and Jennah forms the memory for you, reconciling new facts against what the agent already knows, including contradictions and facts that have changed. Or write records directly when your framework already does its own extraction. One query combines semantic and keyword recall, graph traversal and recent history, and you can ask what an agent's memory held as true on any past date.
THE RECORDS THEY WORK ON
Relational tables (users, orders, documents) stored alongside agent memory, with SQL predicates and vector search in one query.
THE DECISIONS PEOPLE MADE ABOUT THEM
Approval requests and structured questions routed to specific people by email, with an append-only audit log of what they were asked, who answered, and when.
ANY RUNTIME
Connect over HTTP/JSON, gRPC, an MCP server, the Go, Python and TypeScript SDKs, or the jnh command-line tool. Use any model provider and any agent framework, and keep your agents' state when you switch. On paid plans, memory formation can also run on your own model: Amazon Bedrock in your AWS account, or the Claude API.
SHARED AND CONTROLLED
Keep what you learn about each person in their own subject scope, shared by every agent that serves them. Role-based access control lets a team share one account without sharing one credential, and each workspace's data stays in the region you choose for it.
PLANS
Pro, Scale and Team each include a monthly allowance of formation units (550, 1,800 and 6,500), with higher workspace and storage limits at each step. Formation beyond the allowance is billed per unit, up to a limit your administrators set, so a busy month never stops your agents and never surprises you. Email support is included.
Highlights
- One system of record across every runtime. Memory, application records and human approvals live in one consistent backend, reachable from any model provider or agent framework over HTTP/JSON, gRPC, MCP or the Go, Python and TypeScript SDKs. Switch runtimes and your agents keep their state.
- Memory that forms itself. Send raw conversation turns and tool traces; Jennah extracts the facts and relationships, reconciles them against what the agent already knows, and commits them atomically with their vectors and graph edges. Recall, graph traversal and history come back from one query.
- Explain what an agent knew and who approved it. Route approvals and questions to specific people with an append-only audit log of what they were asked, who answered and when, and ask what an agent's memory held as true on any past date, so its behaviour is explainable after the fact.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/month |
|---|---|---|
Pro | Pro plan. Includes 550 formation units per month. | $149.00 |
Scale | Scale plan. Includes 1,800 formation units per month. | $449.00 |
Team | Team plan. Includes 6,500 formation units per month. | $1,499.00 |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Description | Cost/unit |
|---|---|---|
Formation unit | Formation units used beyond your plan's monthly allowance. | $0.30 |
Vendor refund policy
Billed by AWS under your contract. If Jennah is not right for you, email support@alphaus.cloud within 30 days of your first purchase for a full refund of the subscription fee via AWS Marketplace. We reply within two business days. After 30 days, subscription fees are non-refundable; cancelling stops renewal at the end of the term. Overage charges are non-refundable unless billed in error. You can lower your overage limit, even to zero, anytime in the Jennah console.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
Alphaus provides support to all Jennah customers during standard business hours (Japan time), in English. Contact us for help with setting up your account, connecting agents over the API, SDKs, CLI or MCP server, billing and plans, or refunds.
Support email: support@alphaus.cloud Documentation:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.