Radicalbit AI Monitoring is a free, self-hosted platform for tracking the reliability and effectiveness of production LLM and machine-learning models. It checks numerical and categorical data for anomalies, missing values, and outliers, and tracks model metrics over time. Available metrics include Precision, Accuracy, Recall, F1, MSE, MAE, Perplexity, and Probability. Drift detection includes methods such as Kolmogorov-Smirnov, PSI, Wasserstein, Jensen-Shannon, Chi-square, Kullback-Leibler, and Hellinger. The platform compares reference and current datasets to assess data quality, model quality, and drift. For LLM applications, tracing records requests, prompts, and tools, then displays sessions, traces, and spans with hierarchy, duration, and metadata. Documentation for version 1.4.0 focuses on binary and multiclass classification and regression, with additional model types planned. A web interface and Python SDK are available. REST API use requires PostgreSQL, Kubernetes for Spark metric jobs, and distributed storage. Local deployment uses Docker Compose with K3s and supports MinIO or AWS S3 storage.
Who it is for
It suits teams monitoring production models who want self-hosted data quality checks, model metrics, drift detection, or LLM tracing. Its documented model scope focuses on binary and multiclass classification and regression.
What is good
- Free and self-hosted under Apache 2.0.
- Checks data quality and tracks model metrics.
- Offers several drift detection methods.
- Compares reference and current datasets.
- Includes a web UI and Python SDK.
What to know first
- Documented scope focuses on classification and regression.
- REST API requires PostgreSQL and distributed storage.
- Spark metric jobs require Kubernetes.
Verdict
Radicalbit AI Monitoring combines data checks, model metrics, drift analysis, and LLM tracing in a free self-hosted package. Check the documented model scope and deployment requirements against your setup.
Get started with Radicalbit AI Monitoring
- Visit https://radicalbit.ai/ai-monitoring-oss/.
- Choose the self-hosted deployment under the Free / Open Source plan.
- Use the repository's Docker Compose installation for a local K3s-based deployment.
- Configure MinIO or AWS S3 for storage.
- Use the web interface or Python SDK to access platform functionality.
- For LLM tracing, use OpenLLMetry, an OpenTelemetry collector and the Traceloop SDK.
What the free plan stops at
The Free / Open Source plan is self-hosted. The documented v1.4.0 scope focuses on binary and multiclass classification and regression models, with additional model types planned.
Questions about Radicalbit AI Monitoring
How much does Radicalbit AI Monitoring cost?
The Free / Open Source plan is free, billed free.
Is Radicalbit AI Monitoring open source?
Yes. The plan is under the Apache 2.0 license.
Which platforms does it support?
Its listed platforms are API, self-hosted and web.
Which model types are in its documented scope?
The v1.4.0 documentation focuses on binary and multiclass classification and regression models.
What does the REST API deployment require?
It requires PostgreSQL, Kubernetes for Spark metric jobs and distributed storage.
Who brings Radicalbit AI Monitoring to market?
It is brought to market by Fortitude Group, a technology holding company providing consulting, system integration and AI solutions.
Radicalbit AI Monitoring plans and pricing
All plansCompared on machine learning model monitoring software
- Free plan
- Yes
- Drift monitoring
- Yes
- Model performance metrics
- Yes
- Data quality checks
- Yes
- Deployment options
- self-hosted
