ForkFree

AI agents and automation

CompanyOS

by kortix-ai

Kortix CompanyOS is a platform for running teams of AI agents that start from schedules, webhooks and messages, each on its own cloud computer. It is meant to let a company define its agents, skills and tools as code in one git repository and have the agents do ongoing work, with people approving changes.

Proof level: ReadCheck the licenceElastic

Get it on GitHubProject websiteCompare

No demo yet

Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.

The catch

Check the licenceNot open source (Elastic licence). Usually free to use for your own business, but you can't resell it or offer it as a hosted service. Read the licence.

Check this first: Source-available, not open source. Not open source (Elastic licence). Usually free to use for your own business, but you can't resell it or offer it as a hosted service. Read the licence.

Things to check

  • Licence is not clearly stated (NOASSERTION), so check the terms before commercial use
  • You need to supply your own model API keys, which cost money
  • Cloud and hosted features may be paid, and the full self-hosting setup is not clear from the README excerpt
  • Agents have wide access to company tools, so permissions and approvals need careful setup

Can you use CompanyOS commercially?

Not open source (Elastic licence). Usually free to use for your own business, but you can't resell it or offer it as a hosted service. Read the licence.

Not legal advice. Read the project's licence file before building a product on it.

What can you do with CompanyOS?

  • Build custom AI agents that start automatically from schedules, webhooks or Slack, Teams and email messages
  • Connect company tools once so every agent and teammate shares the same apps, skills and memory
  • Run many agents in parallel on long tasks, with changes landing only after a person approves them

How do you get CompanyOS running?

You can use the hosted Kortix Cloud or self-host it in your own VPC or on-premises network; the README excerpt gives no exact install steps, so check the guide.

Follow the official instructions in the project README.

Make money with it

A freelancer or consultant could set up and manage custom agent workflows for other small businesses as a paid automation service.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Automate recurring work such as research, reporting and routine app tasks with scheduled or event-triggered agents, reducing manual admin time
  • Give a small team shared AI assistants that use the same company memory and tools, instead of paying for separate tools for each person

Who's talking about it

Checked 06 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.

Similar tools in AI agents and automation

craft-anything storytold
New and promising

Craft Anything is a desktop app and command-line tool that studies how a website, app or game works, then uses a coding agent to build your own version and check it against the original. It is meant for people who want to recreate or learn from existing software without writing it all by hand.

Proof level: Read 38.9k stars +2044 a day Apache-2.0
dsh-Go ccch1mneyyy
New and promising

DSH Go is an unofficial Android app that runs the DeepSeek Harness coding agent on your phone, or lets you control a copy running on your computer or server. It gives you a chat interface for talking to AI models, approving tool actions and sharing conversations.

Proof level: Read 28.6k stars +1280 a day AGPL-3.0
orca stablyai
Worth a look

Orca is a desktop app, with a phone companion, for running several AI coding agents side by side, each in its own git worktree. It lets you track, review and steer their work from one place.

Proof level: Read 130.3k stars +936 a day MIT