Find tools › Open-source projects › Build websites & apps

omnara

Open-source project · by omnara-ai

A server to run AI assistants that safely execute tasks and commands across your computers or cloud environments.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Run persistent AI assistants with automatic crash recovery
  • Execute shell commands and tools inside sandboxed machines
  • Build custom agent workflows using a TypeScript SDK and REST API

How to start

  1. Start the platform locally by running docker compose -f compose.yaml --profile app up -d.

  2. Open http://localhost:8000 in your browser, create an account, and configure your model provider.

  3. Launch an agent from your terminal with npx omnara agents launch --file agent.yaml.

Good to know. The default local configuration is intentionally insecure and requires additional security hardening before deploying to production.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

Omnara is an open-source platform and API for running autonomous AI agents across models and remote machines with persistent state and tool management.

Building reliable agent infrastructure requires sandboxed execution, crash recovery, and permission controls. Reach for Omnara when you want a self-hosted alternative to proprietary managed agent cloud APIs like OpenAI Agents.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-22. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map