Skip to content
SPECIFICTION
Get listed

Radicalbit AI Monitoring

radicalbit.ai

Free plan WebAPISelf-hosted
Visit radicalbit.ai
Spec score 7.4 #12 of 20 in Machine Learning Model Monitoring Software

What it is

Radicalbit AI Monitoring is a free, self-hosted platform for monitoring production LLM and machine-learning model effectiveness and reliability. It checks numerical and categorical data for anomalies, missing values, and outliers, then tracks metrics over time. Available model measures include Precision, Accuracy, Recall, F1, MSE, MAE, Perplexity, and Probability. Drift detection offers Kolmogorov-Smirnov, PSI, Wasserstein, Jensen-Shannon, Chi-square, Kullback-Leibler, and Hellinger methods. Reference and current datasets can be compared for data quality, model quality, and drift. LLM tracing records requests, prompts, and tools and displays sessions, traces, and spans with hierarchy and metadata. Documentation for version 1.4.0 focuses on binary and multiclass classification and regression, with more model types planned. A web UI, Python SDK, and REST API are provided. Local deployment uses Docker Compose with K3s and MinIO or AWS S3.

Spec sheet

Purpose
Radicalbit AI Monitoring monitors the effectiveness and reliability of production LLM and machine-learning models.Read 1 Oct 2026 · radicalbit.ai
Deployment
The repository provides Docker Compose installation for a local K3s-based deployment and supports MinIO or real AWS S3 storage.Read 1 Oct 2026 · github.com
Privacy
The project collects anonymous usage data only, collects no personally identifiable information and asks users to opt in or out at first use.Read 1 Oct 2026 · github.com
Support
The project directs users to a Discord community for help and discussion.Read 1 Oct 2026 · github.com
Maker
Radicalbit is brought to market by Fortitude Group, an innovative technology holding company providing consulting, system integration and AI solutions.Read 1 Oct 2026 · radicalbit.ai
Data quality
It detects anomalies, missing values and outliers in numerical and categorical data and tracks metrics over time.Read 1 Oct 2026 · radicalbit.ai
Dataset comparison
The platform analyzes reference and current datasets to evaluate data quality, model quality and model drift.Read 1 Oct 2026 · docs.oss-monitoring.radicalbit.ai
Documented scope
The v1.4.0 documentation says the current scope focuses on binary and multiclass classification and regression models, with additional model types planned.Read 1 Oct 2026 · docs.oss-monitoring.radicalbit.ai
Drift detection
Drift detection includes Kolmogorov-Smirnov, PSI, Wasserstein, Jensen-Shannon, Chi-square, Kullback-Leibler and Hellinger algorithms.Read 1 Oct 2026 · radicalbit.ai
LLM tracing
LLM application tracing records requests, prompts and tools and displays sessions, traces and spans with hierarchy, duration and metadata.Read 1 Oct 2026 · radicalbit.ai
Model metrics
It provides metrics including Precision, Accuracy, Recall, F1, MSE, MAE, Perplexity and Probability for LLM, classification and regression models.Read 1 Oct 2026 · radicalbit.ai
REST API
The API exposes platform functionality through REST APIs and requires PostgreSQL, Kubernetes for Spark metric jobs and distributed storage.Read 1 Oct 2026 · docs.oss-monitoring.radicalbit.ai
Tracing integration
LLM tracing uses OpenLLMetry, an OpenTelemetry collector and the Traceloop SDK.Read 1 Oct 2026 · docs.oss-monitoring.radicalbit.ai
User interface and SDK
A web UI covers model creation through metric visualization, and a Python SDK implements the REST API functionality.Read 1 Oct 2026 · docs.oss-monitoring.radicalbit.ai

Plans and prices

Free / Open Source Free free Apache 2.0 license · self-hosted deployment Read 1 Oct 2026 · radicalbit.ai

Every Radicalbit AI Monitoring plan and price →

Strong points and limits

Strong points

  • Free Apache 2.0 self-hosted plan
  • Multiple drift detection algorithms
  • LLM request and tool tracing
  • Web UI and Python SDK
  • Compares reference and current datasets

Limits

  • Documented scope focuses on classification and regression
  • REST API requires PostgreSQL and Kubernetes
  • Self-hosted deployment requires infrastructure

Who it suits

It suits teams running self-hosted monitoring for classification, regression, and LLM applications.

Verdict

Radicalbit AI Monitoring provides broad data, model, drift, and LLM tracing capabilities without a listed charge. Its current documented model scope and infrastructure requirements matter when planning deployment.

Where Specifiction places it

Alternatives to Radicalbit AI MonitoringAll alternatives →