In simple English
Kortix is a system for running AI agents that do real work for your team. You can write your company rules, agent descriptions and skills as plain text files in a Git repository (a folder where you track changes to code over time). Every time an agent runs, it gets its own secure cloud computer to write code, research topics or edit documents. You review everything it does before it changes your main project. You can run it on your own server for free, or pay for a managed cloud version.
What it is
Kortix is an open-source AI operating system written in TypeScript that connects language models to thousands of external tools. It manages agents, skills, memory and triggers in one project folder.
What it is good for
Solo builders and teams who want an alternative to proprietary tools like Claude Cowork or ChatGPT Work, allowing them to run background coding tasks, automate repetitive chores and connect AI to Slack or Microsoft Teams.
- Runs on your own servers or infrastructure for complete control over your data.
- Connects to thousands of apps using secure server-side credentials.
- Every agent task runs in an isolated sandbox with a review step before merging.
- Uses a custom licence instead of a standard open-source licence.
- Requires Docker and a container setup to run locally on your own machine.
- Demands careful configuration of API keys and server resources to run multiple agents.
Zapier and manual workflow automation
Docker
- langchain-ai/langgraph44k stars
A library for building stateful, multi-actor applications with language models.
- ggml-org/llama.cpp132k stars
A C and C++ library and command-line tool for running language models locally.
- EleutherAI/lm-evaluation-harness14k stars
Runs standard question sets against a language model and reports the scores.
- mudler/LocalAI50k stars
Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.
curl -fsSL https://kortix.com/install | bash kortix init kortix ship