Sold by: lreceive
Deployed on AWS
lreceive is a self-hosted proxy that sits between your applications and LLM providers (Anthropic, OpenAI, Amazon Bedrock), capturing a tamper-evident audit trail of every request and response. It automatically detects and redacts PII, PHI, PCI data, and secrets in transit, and generates SOC 2-mapped compliance reports on demand - all inside your own VPC, so audit data never leaves your infrastructure.
Overview
lreceive gives compliance and security teams visibility into how their organization actually uses LLMs, without requiring any changes to application code beyond pointing your provider base URL at the proxy.
Every request and response is captured in a SHA-256 hash-chained, append-only ledger with periodically signed Merkle checkpoints, so the audit trail is cryptographically tamper-evident and independently verifiable at any time. A policy-driven detection engine scans traffic for PII, PHI, PCI data, and API keys/secrets, and redacts or blocks matches according to rules you configure per data classification.
A built-in compliance dashboard lets you search the audit log, verify ledger integrity on demand, manage proxy API keys per application, and generate auditor-ready SOC 2 reports (PDF or JSON) mapped to Trust Services Criteria. Each report includes a fresh cryptographic integrity check of the underlying ledger.
lreceive deploys entirely inside your own network via Docker Compose with a Postgres backend. No LLM traffic, prompts, or audit data are sent to any third party. It is a self-hosted, in-VPC solution built for organizations that need provable LLM governance for regulated environments.
Highlights
- Tamper-evident audit trail: every LLM interaction is recorded in a SHA-256 hash-chained ledger with signed Merkle checkpoints, making the log cryptographically provable and independently verifiable.
- Automatic PII/PHI/PCI/secret detection and redaction: a policy-driven guardrail engine classifies sensitive data in requests and responses and redacts or blocks it before storage, per data class.
- One-click SOC 2 compliance reports: generate auditor-ready PDF or JSON reports mapped to Trust Services Criteria (CC4, CC6, CC7), each backed by a live integrity verification of the audit ledger.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Self-hosted container (Docker Compose / ECS / EKS)
Latest version
Operating system
Linux
Deployed on AWS
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/month |
|---|---|---|
Audited interactions | Each LLM request proxied and recorded in the tamper-evident audit trail, across all connected providers (Anthropic, OpenAI, Amazon Bedrock). | $300.00 |
Input tokens | Total input tokens sent to LLM providers through the proxy, summed across all audited interactions in the billing period. | $600.00 |
Output tokens | Total output tokens returned by LLM providers through the proxy, summed across all audited interactions in the billing period. | $1,000.00 |
Dimensions summary
You pay based on three usage meters that add up over each billing period. The first counts audited interactions: every LLM request the proxy records in the audit trail, across all connected providers. The second and third count input tokens and output tokens passing through the proxy. Input tokens are what your apps send to providers. Output tokens are what providers return. Each meter bills separately, so your total scales with both request volume and token size. There are no fixed tiers; costs rise with actual proxied usage.
Top-of-mind questions for buyers
One audited interaction is a single LLM request the proxy records in its tamper-evident audit trail. Each call routed through the proxy counts once, whether sent to Anthropic, OpenAI, or Amazon Bedrock. Blocked requests are also recorded, so they count toward this meter too.
All three meters bill independently and add up on the same invoice. Interaction count drives cost when you make many short calls. Token meters drive cost when prompts or responses are large. High-volume, large-context workloads accumulate charges across all three at once.
The proxy scores PII, PHI, PCI, and secrets in-path and can block a request before egress. Blocks are audited, so a blocked request still counts as one audited interaction. It generates no output tokens, so the output meter is not affected for blocked calls.
isreceivables.com
Helpful?
Vendor refund policy
Buyers may request a full refund within 30 days of purchase for any reason. After 30 days, refunds are considered case by case, for example service outages or billing errors, and unused contract months may be credited at our discretion. To request a refund, contact support@isreceivables.com with your AWS Marketplace order ID and reason for the request. Refunds are processed to the original payment method within 5 to 10 business days of approval.
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
Self-hosted container (Docker Compose / ECS / EKS)
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Initial release of lreceive: a self-hosted proxy that captures a tamper-evident, hash-chained audit trail of every request and response sent through Anthropic, OpenAI, and Amazon Bedrock. Includes automatic PII/PHI/PCI/secret detection and redaction, a compliance dashboard for audit log search and ledger integrity verification, proxy API key management, and one-click SOC 2 compliance report generation in PDF or JSON format.
Additional details
Usage instructions
Deploy lreceive in 5 steps. Everything you need is below, no other files or docs required.
STEP 1: Create a file named config.yaml with this content. Delete whichever provider block(s) you will not use.
server: proxy_addr: ":8080" admin_addr: ":8081" database: url: ${DATABASE_URL} ledger: signing_key_path: /data/signing.key checkpoint_interval: 1h providers: anthropic: enabled: true api_key: ${ANTHROPIC_API_KEY} allow_passthrough: true openai: enabled: true api_key: ${OPENAI_API_KEY} allow_passthrough: true detection: enabled: true policies:
- classes: [SECRET, PCI] action: redact
- classes: [PII, PHI] action: redact retention: tiers: default: 8760h
STEP 2: Provide a Postgres 14+ database reachable from the container (Amazon RDS, Aurora Postgres, or your own).
STEP 3: Run the container:
docker run -d
-e DATABASE_URL=postgres://user:pass@your-db-host:5432/lreceive
-e ANTHROPIC_API_KEY=sk-ant-...
-e OPENAI_API_KEY=sk-...
-p 8080:8080 -p 8081:8081
-v lreceive-data:/data
-v /path/to/config.yaml:/etc/lreceive/config.yaml:ro
709825985650.dkr.ecr.us-east-1.amazonaws.com/lreceive/irece:1.0.0
Port 8080 is the proxy your applications call. Port 8081 is the compliance dashboard, keep it off the public internet, place it behind your own VPN or private network.
STEP 4: Initialize the database and create your login (first launch only):
docker exec <container> auditctl migrate docker exec <container> auditctl users set admin docker exec <container> auditctl keys create my-application
The last command prints a secret once. Save it, it cannot be retrieved again.
STEP 5: Point your application at the proxy instead of the real provider:
http://<your-host>:8080/anthropic (Anthropic SDKs) http://<your-host>:8080/openai (OpenAI SDKs)
Use the secret from step 4 as the API key. lreceive forwards the request to the real provider, records a tamper-evident audit entry, and returns the response unchanged.
Open http://<your-host>:8081 and sign in with the admin account from step 4 to view the audit log, verify ledger integrity, and generate SOC 2 compliance reports.
Support
Vendor support
lreceive is backed by the team at isreceivables.com, with support available by email at support@isreceivables.com and through the documentation site at https://isreceivables.com/docs .
Support covers:
- Installation and deployment guidance for Docker Compose and self-hosted environments
- Troubleshooting proxy configuration, provider adapters (Anthropic, OpenAI, Amazon Bedrock), and detection/redaction policies
- Help interpreting audit log entries, resolving integrity verification failures, and generating SOC 2 compliance reports
- Guidance on version upgrades and configuration migration
Support hours: [Monday-Friday, 9am-5pm ET]. Response time target: [within 1 business day for standard requests, or specify your SLA for paid/priority tiers].
For security vulnerabilities, please report privately to security@isreceivables.com rather than filing a public issue.
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.
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.