Skip to content
SPECIFICTION
Get listed

Memoturn vs NannyML

Memoturn

memoturn.com

NannyML

nannyml.com

Side by side

FigureMemoturnNannyML
Price fromFree$99/mo
Free planYesYes
Free trial—Yes
Open source—Yes
WebYesYes
LinuxYesYes
APIYesYes
Self-hostedYesYes
Plans published17
Spec score · Model Monitoring Software8.0 (#20)8.7 (#8)
IntegrationsThe maker lists OpenTelemetry, OpenAI, Anthropic, LangChain, LiteLLM, and MCP, and its integration guide documents additional model providers, frameworks, and vector stores.NannyML Cloud is offered through both Azure Marketplace and AWS Marketplace.

Plans

Memoturn

  • Memoturn (Apache-2.0 self-hosted core)Free

Memoturn pricing →

NannyML

  • Open SourceFree
  • Starter (beta)$99 a month
  • Starter$399 a month
  • Scale$999 a month
  • Pro (beta)$3,800 a month
  • EnterprisePriced on request
  • Enterprise (beta)Priced on request

NannyML pricing →

In their own words

Memoturn

Memoturn is an open-source platform for tracing and managing applications built with large language models. It brings together trace inspection, cost and latency metrics, evaluations, prompt management, monitoring, and datasets. Traces, spans, generations, and scores appear in a waterfall timeline, with session views and per-user rollups. Teams can run offline experiments on datasets, evaluate sampled production traces, or send examples to human reviewers for scoring. The prompt registry keeps versions in production, staging, and custom channels, and can split live traffic for A/B experiments.

Memoturn accepts OpenTelemetry data and supports OTLP/JSON with GenAI semantic conventions. It lists TypeScript, Python, and Go SDKs, plus a REST API. Deployment options include local operation, Docker Compose, and Helm on Kubernetes; operators can use Apache Doris or PostgreSQL for telemetry storage. The project is licensed under Apache-2.0 and can keep telemetry on infrastructure the operator owns. The listed plan is free.

Visit memoturn.com

NannyML

NannyML monitors deployed machine-learning models and estimates their performance when ground truth is delayed or unavailable. It detects concept drift as well as multivariate and univariate data drift, and connects alerts to changes in model performance. Data-quality checks and ranked drift alerts can help teams investigate features associated with performance issues. Users can relate model performance to monetary or other business outcomes. NannyML Cloud supports webhooks for retraining actions and an SDK for automating monitoring-data ingestion. Cloud is available through Azure and AWS marketplaces as SaaS or a managed application. With the managed-application option, the application and required infrastructure are provisioned within the customer's cloud subscription. For its Azure managed application, NannyML documents encrypted traffic and disks, but says automated backups were still being implemented and advises customers to safeguard model inputs and outputs elsewhere. The open-source library installs with pip or conda. Direct local dataset uploads through the Cloud UI must be smaller than 100 MB. Plans include a free self-managed Open Source option, Starter at $399 a month, and Scale at $999 a month.

Visit nannyml.com