Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Skip to main content
Get started
The open-source managed agent platform
A self-hostable alternative to Claude Managed Agents and OpenAI’s Agents API. Run durable AI agents on any model and any machine.
Omnara is an open-source managed agent platform and a self-hostable alternative to Claude Managed Agents and OpenAI’s Agents API. Use the API to run AI agents on any model and any machine, with tools, secrets, permissions, and streaming built in. Self-host it for free under Apache 2.0, or use Omnara Cloud.
You can create and launch the agent in two ways:
Use cases
Omnara can be used to build agents for internal use cases or external use cases, such as:- Internal slack bots
- Code review agents
- Agents integrated in a product dashboard
Build an agent
An agent starts as a small YAML config:instruction: |
You are an engineering assistant. Use your machine to run
commands. Ask a question when a task is not clear.
model:
provider_config: omnara-openrouter
name: anthropic/claude-fable-5.1
tools:
run_command: {}
web_search: {}
ask_question: {}
machine_sources:
- machine_pool_name: default-pool
- Dashboard — click New agent in your project in the dashboard.
- Programmatically - Omnara provides an API, Typescript SDK, and CLI to interact with Omnara
Core concepts
- An organization owns shared resources for your team: projects, secrets, model providers, and machines.
- Projects contains agents. Grants decide which shared resources the project can use.
- An agent is one durable conversation with its config, tool calls, and history. Profiles provide reusable agent configurations.
- You send inputs, stream events, and resolve interactions in an agent.
Start here
Quickstart
Write a config, create the grants, and launch an agent with the dashboard, the API, or the CLI
Concepts
The object model, the agent loop, and access control