Sold by: Excipio
Excipio is a sovereign memory layer that audits and controls traffic between AI surfaces. It runs inside your perimeter, records every call, and applies your policy before any model answers, frontier or self-hosted.
Overview
Image
302 AI surfaces. 27 never on record
Image
How Excipio sits in the path
Image
Excipio: Sovereign Memory Layer for AI
Excipio is a sovereign memory layer that audits and controls traffic between AI surfaces. It deploys entirely inside your perimeter, on your infrastructure, in the request path between the apps, agents, tools, and MCP servers your enterprise runs and the models they call, whether frontier providers or models on your own GPUs. Every exchange is audited and controlled in the flow rather than reviewed after the fact.
Within 30 days Excipio delivers a census of every AI identity in your request path, showing where traffic overlaps, degrades, or leaks context. What you can name, you can audit. What you can audit, you can control.
Audit: every call is recorded inside your perimeter, under your keys, as evidence of who asked, what was sent, and what came back. Control: you set where uncached calls may go, to the frontier providers or open models you approve, and only those models answer. Sovereignty: the memory and the record stay inside your perimeter, and a cached answer is served locally without ever reaching a frontier provider.
Excipio sees only the shape of your traffic, never its content. Built for large, regulated enterprises in financial services and healthcare, and for any organization that needs its AI traffic to stand as a record.
Own the memory. Own the record. Own the data.
Highlights
- Inline audit and control, inside your perimeter. Excipio sits in the request path between every AI surface (apps, agents, tools, MCP servers) and the models they call. Every exchange is recorded and governed in the flow, on your infrastructure. Excipio sees only the shape of the traffic, never its content.
- A 30-day census of every AI identity in your request path: where traffic overlaps, degrades, or leaks context. Then policy enforced in the path, evidence recorded for every exchange, and known answers served inside your perimeter.
- Priced per surface, never per seat. A surface is any app, agent, MCP server, tool, or model endpoint with traffic through Excipio that month. Exceed your band two months running and you move up a band, prorated.
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
Production | Surface census, audit, and traffic control for up to 1,000 surfaces. | $100,000.00 |
Enterprise Scale | Surface census, audit, and traffic control for up to 3,000 surfaces. | $150,000.00 |
Global | Surface census, audit, and traffic control for up to 10,000 surfaces. | $300,000.00 |
Dimensions summary
You buy an annual contract priced by the number of surfaces you govern. A surface is any app, agent, tool, or remote server that calls a model through the product, counted once per distinct identity each month. The three tiers scale by surface capacity: Production covers up to 1,000 surfaces, Enterprise Scale covers up to 3,000, and Global covers up to 10,000. You pick the tier that fits your deployment size. A per-surface overage applies only after two consecutive months above your band. Models themselves are not counted.
Top-of-mind questions for buyers
A surface is any app, agent, tool, or remote server that calls a model through the product. Each distinct identity is counted once per calendar month. Models themselves are not counted, so adding or switching models does not change your surface count.
A per-surface overage charge applies, but only after you exceed your band for two consecutive months. A single busy month within your band does not trigger overage. Each tier covers a stated capacity: Production up to 1,000 surfaces, Enterprise Scale up to 3,000, and Global up to 10,000.
No. Billing tracks the number of distinct surfaces, not query volume or token usage. Each surface counts once per month regardless of how many model calls it makes. Query traffic flows through the gateway, but it is the surface identity that drives your tier.
excipio.ai
Helpful?
Vendor refund policy
Fees for contract tiers are non-refundable after the cancellation window provided by AWS Marketplace. Tier upgrades during the term are prorated for the remaining months. Refund requests are submitted through AWS Marketplace.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
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
Support is included with every Excipio contract. Standard support covers 8 AM to 5 PM Mountain Time on business days by email at . Deployment runs inside the customer's own AWS account with onboarding led by Excipio engineering.
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.
Similar products
Mem0 is a universal, self-improving memory layer for AI agents and LLM applications, helping teams build personalized, context-aware experiences with lower token usage and faster responses.
OAIS Sentinel is a zero-knowledge sovereign AI governance and cryptographic audit ledger for enterprise LLMs on AWS. It delivers real-time DLP redaction, prompt injection defense, and RFC 6962 tamper-evident Merkle audit proofs with sub-millisecond latency.
Memori is agent-native memory infrastructure: an LLM-agnostic layer that transforms agent execution and conversation history into structured, persistent state for production systems. Unlike conversational memory wrappers or vector retrieval, Memori captures tool calls, decisions, traces, and user context as durable, queryable state that agents rely on across sessions, models, and workflows.
Let Memori handle agent memory so your team can improve accuracy and cut inference costs instead of building and operating a memory system themselves.
Benchmarked on LoCoMo, a benchmark from Snap Research measuring how well systems remember and retrieve details. Memori delivers industry-leading results: 87% accuracy using 721 tokens, roughly 2.8% of full-context cost, enabling teams to reduce inference spend by up to 97.2%.
Built for enterprise, Memori works with the infra you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
This is a repackaged open source software product wherein additional charges apply for a pre-hardened AMI with automated startup. Deploy a self-hosted, OpenAI-compatible memory layer giving LLMs
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.