Skip to content

Evidently Data Drift Reports

AI Platform & Data Evidently 0.7.23 Hardened AMI

Evidently 0.7.23 on Ubuntu 24.04 compares two tabular datasets, shows a drift report in a local monitoring UI, and exports HTML and JSON. No model, GPU, or Evidently account is required.

AMI release
0.1.0-r20261105 (Evidently 0.7.23)
Recommended
t3.medium
Storage
32 GiB+ encrypted gp3
Access
Session Manager, no inbound ports
Released
Nov 5, 2026
Delivery
Amazon Machine Image in your own AWS account

Evidently 0.7.23 with a local monitoring workspace, tabular drift reports, and HTML/JSON exports.

Loopback UI and API on port 8000 with a per-instance native write token and clear single-owner access boundaries.

Controlled two-column drift example with independent CSV, p-value, API and saved-artifact readback; no LLM required.

Quick start

Full guide →
  1. Subscribe
  2. Launch the instance
  3. Connect
  4. Open port 8000
  5. Reread a saved result

What is on the image

This guide matches Marketplace version 0.1.0-r20261105 (Evidently 0.7.23). The public getting-started page describes package 0.1.0 (Evidently 0.7.23). Check the listing for the version currently on offer.

  • Evidently 0.7.23 in /opt/evidently/venv.
  • Loopback UI and API at 127.0.0.1:8000.
  • A per-instance write token in ~/.config/sushi/evidently/access.json, mode 0600. The helper reads it and does not print it.
  • Projects under /var/lib/evidently/workspace.
  • A controlled example that writes a new directory under ~/evidently-results each time you run /opt/sushi/docs/demo.sh.

t3.medium (4 GiB of memory) or a larger listed type, x86_64, with an encrypted gp3 root volume of at least 32 GiB and IMDSv2. The listed types are t3.medium, t3.large, t3.xlarge, and t3.2xlarge. Leave inbound application ports closed. Forward port 8000 through Session Manager or SSH.

Scope and limits

The write token protects writes. Local operating-system users and anyone who holds the tunnel can read reports. This is a single-owner workspace. There is no tenant isolation and no per-user role. The controlled example does not choose thresholds for your data and does not prove model quality.

Unresolved operating-system findings

The 0.1.0-r20261105 release note says known OS and kernel High and Critical vulnerability findings remain unresolved, and that this delivery does not claim a security fix or a security qualification.

Billing

The listing states USD 0.03 per running instance-hour on each offered instance type. Confirm the offer, including its free trial, before you subscribe. EC2, EBS, and data transfer are billed separately. This image does not call a model provider.

Where to go next

Upstream project

This is paid repackaged open-source software. Software Sushi is independent of Evidently AI and does not claim endorsement. See the Evidently documentation. Evidently Cloud, managed alerting, and high availability are not included.

Last updated November 11, 2026 · Suggest an improvement