IntuixAI is an open-source developer platform to build AI/LLM applications and models with confidence. Enhance your AI applications with end-to-end experiment tracking, observability, and evaluations, all in one integrated platform.
To install the IntuixAI Python package, run the following command:
pip install intuixaiIntuixAI provides a unified solution for modern AI/ML workflows, including LLMs, Agents, Deep Learning, and traditional machine learning.
🔍 Tracing / Observability
Trace the internal states of your LLM/agentic applications for debugging quality issues and monitoring performance with ease.
Getting Started → |
📊 LLM Evaluation
A suite of automated model evaluation tools, seamlessly integrated with experiment tracking to compare across multiple versions.
Getting Started → |
📝 Experiment Tracking
Track your models, parameters, metrics, and evaluation results in ML experiments and compare them using an interactive UI.
Getting Started → |
IntuixAI can run in many environments, including local machines, on-premise servers, and cloud infrastructure.
Trusted by organizations building production AI systems.
For hosting IntuixAI on your own infrastructure, refer to the deployment guide in the documentation.
- Python
- TypeScript / JavaScript
- Java
- R
IntuixAI integrates with many popular machine learning frameworks and GenAI libraries.
import mlflow as intuixai
from openai import OpenAI
# Enable tracing for OpenAI
intuixai.openai.autolog()
response = OpenAI().chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hi!"}],
temperature=0.1,
)Navigate to the "Traces" tab in the IntuixAI UI to find trace records.
import intuixai
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_diabetes
intuixai.sklearn.autolog()
db = load_diabetes()
X_train, X_test, y_train, y_test = train_test_split(db.data, db.target)
rf = RandomForestRegressor(n_estimators=100)
rf.fit(X_train, y_train)