Welcome to Composabl

Composabl is the platform for creating industrial-strength multi-agent AI systems that make high-impact decisions in the real world.

With Composabl, you can convert expert knowledge about how a process works into a team of agents with specialized skills that work together to allow the system to make the right decision in every situation. These can be either programmed or learned through advanced AI techniques and orchestrated so that the multi-agent system performs effectively in every part of the process and under any conditions. For skill agents that learn by practicing, Composabl trains the agent systems in realistic scenarios until the agent system can succeed at the task and outperform the alternatives.

Quick Links

Find articles on key topics with these links.

Try Out a Tutorial

Industrial Mixer

Build four agent systems for a realistic use case with step by step instructions

Integrate with Composabl

You can use any model or Python algorithm with Composabl for training agent systems, adding perception, analysis, and communication, and making decisions. See how to configure different types of modules in the UI and by publishing them via the data science workflow for agent system design, training, and deployment.

Integrate a machine learning model

Use existing ML models for machine vision, prediction, or analysis in Composabl agent systems

Integrate a language model

Set up an LLM call to add communication to your agent system

Integrate a programmed algorithm

Configure any Python algorithm, such as a PID controller or optimization algorithm, as a skill agent in Composabl

Integrate third-party software

Use an API call to external software as a skill agent in Composabl

Integrate a simulator

Configure your simulator to work with Composabl

Publish to the platform

Upload configured models and algorithms to the Composabl UI with one CLI command

Create Modular Skill Agents

Composabl multi-agent systems are built on modular skills that break down a task into separate parts. Learn how to create skill agents to train with deep reinforcement learning.

Create skill agents with goals and constraints

Create skills agents with subject matter expertise by configuring goals and constraints for learning

Create skill agents with rewards using the SDK

Create skill agents that learn with rewards and access additional teaching tools in Python

Publish to the platform

Upload skill agents configured with the SDK to the Composabl UI for training and deployment

Deploy Multi-Agent Systems

Once Composabl agentic systems are designed and trained, you can export them to the Composabl runtime to connect with your system. Learn how to deploy an agent within the runtime container and how to use Composabl's tools to analyze agent behavior during both training and deployment.

Evaluate the performance of your multi-agent system

Evaluate performance using the Composabl benchmarking feature

Deploy a Composabl multi-agent system

Export a multi-agent system and connect to the Composabl runtime container

Connect the multi-agent system to your production system

Connect the Composabl runtime container to your system for deployment

Audit multi-agent system behavior with the historian

Use the Composabl historian to analyze system behavior in detail