Repolode
Submit
kreneskyp

kreneskyp/ix

An open-source platform for building and running autonomous, LLM-powered agents and multi-agent workflows, with a no-code graph editor.

View on GitHub
Stars
1,044
Forks
127
Open issues
16
Last commit
27 days ago

What is it?

iX is a platform for designing and deploying autonomous and semi-autonomous LLM agents and workflows. Agents built on it can handle tasks such as QA chatbots, code generation, data extraction and analysis, and research assistance, and they can run in parallel and communicate with each other.

The project includes a no-code editor where users drag and connect nodes into a graph describing an agent's logic, with a chat panel embedded for testing. A multi-agent chat interface lets users work with a team of agents, with an IX moderator agent that delegates tasks, and users can @mention specific agents. Agent workers are dockerized and triggered through a Celery message queue, so they can scale horizontally.

IX is built on LangChain components and maps them into a configuration graph that drives dynamic node and form rendering in the editor. It supports OpenAI models, with Google PaLM, Anthropic and Llama listed as experimental. Setup is through Docker Compose, with an agent-ix CLI for quick start.

Key features

  • 01No-code graph editor for designing agent logic with an embedded test chat.
  • 02Multi-agent chat room where a moderator agent delegates tasks and users can @mention agents.
  • 03Agent workers run in Docker and are queued via Celery for horizontal scaling.
  • 04Smart input with autocomplete for agent mentions and task-generated artifacts.
  • 05Component config layer that maps LangChain components to a configuration graph.
  • 06Supports OpenAI models, with other providers listed as experimental.

Use cases

  • Building QA chatbots or research assistants that run multi-step tasks.
  • Prototyping LLM agent workflows visually before writing code.
  • Running a team of specialized agents that collaborate in one chat interface.
  • Scaling parallel agent workloads by adding Celery workers.

Quick start

  1. 1

    Install the agent-ix CLI with pip

    pip install agent-ix
  2. 2

    Start the IX cluster with the CLI (requires Docker)

    ix up
  3. 3

    Open http://0.0.0.0:8000 in your browser to use the interface

Things to know

  • Requires Docker to run the cluster.
  • Google PaLM, Anthropic and Llama support is marked experimental.
  • Agents need an OpenAI API key for the default setup.

In collections

Open-source AI agent frameworks & apps

Topics

#ai#llm#agents#openai#langchain#workflow#docker#no-code#gpt-4#python

FAQ

What is ix?
An open-source platform for building and running autonomous, LLM-powered agents and multi-agent workflows, with a no-code graph editor. iX is a platform for designing and deploying autonomous and semi-autonomous LLM agents and workflows. Agents built on it can handle tasks such as QA chatbots, code generation, data extraction and analysis, and research assistance, and they can run in parallel and communicate with each other.
Is ix free to use? What license does it have?
ix is open source under the MIT license. Check the license terms before using it in commercial products.
Is ix still maintained?
Actively maintained. The last commit to ix was on Oct 10, 2026.
What can I use ix for?
Building QA chatbots or research assistants that run multi-step tasks. Prototyping LLM agent workflows visually before writing code. Running a team of specialized agents that collaborate in one chat interface. Scaling parallel agent workloads by adding Celery workers.
How do I install ix?
Install the agent-ix CLI with pip: pip install agent-ix Start the IX cluster with the CLI (requires Docker): ix up Open http://0.0.0.0:8000 in your browser to use the interface
Where can I get ix?
The source code and installation instructions are on GitHub: https://github.com/kreneskyp/ix

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects