Omnara MCP server

Omnara

The API for production-grade agents.

Omnara is an open source platform for running managed agents. It handles execution and state while you choose the models, tools, machines, and how users interact with each agent.

Omnara Cloud · Documentation · API · Changelog · Discord

Who it is for

the API. Your application controls who can use each agent, what input it receives, and how its output reaches users. Omnara handles execution and state in between.

• Developers. Build agents for internal use or customer-facing products with

first-party Slack connector.

• Teams. Interact with agents directly through Omnara's dashboard or

Getting Started

1. Create your agent

instruction: |
  You are a coding agent running gpt-5.6-sol. Use the tools
  you have available to solve coding problems for the user.
model:
  provider_config: omnara-openrouter
  name: openai/gpt-5.6-sol
# ...
# add more tools, sandboxes, mcps

1. Upload your agent profile

$ npx omnara login
$ npx omnara profiles create --name agent --file agent.yaml
id                  aprf_aej3...
name                agent
[...]

1. Launch the agent from the profile and chat with it

$ npx omnara agents launch --profile $AGENT_PROFILE_ID --file agent.yaml
$ open https://app.omnara.com/projects/[$PROJECT_ID]/agents/[$AGENT_ID]

Features

atomically to Postgres. Agents recover automatically from crashes, restarts, and temporary machine disconnects.

• Durable agents. Agent state is committed

or Unikraft (more coming soon), or connect your own laptop or VM. An agent can run with no machines or use several at once. These can be sandboxes, your own machines, or both. You can add or remove machines while the agent is running.

• Machines. Use sandboxes from Blaxel, Daytona, Modal,

exposed through a compatible endpoint, including OpenRouter, LiteLLM, and Ollama. Omnara supports OpenAI Responses, OpenAI Chat Completions, and Anthropic Messages, with more API formats coming soon.

• Models. Bring your own API keys and use any model

and HTTP MCP servers.

• Tools. Use built-in tools, custom tools, skills,

users and API keys. Separate who can manage access, configure agents, operate them, or only view them.

• RBAC. Assign organization and project roles to

yourself under Apache 2.0.

• Cloud or self-hosted. Use Omnara Cloud or run it

query agent history directly in Postgres for analytics, evals, prompt analysis, and training datasets.

• Queryable state. Self-hosted deployments can

• CLI and SDK. Use Omnara programmatically via the CLI, Typescript CLI, or REST API.

Get started

Omnara Cloud

Sign up at app.omnara.com, add a model provider, define an agent profile, and launch it from the console, Slack, or API.

See the quickstart for the complete flow.

Self-host

Requirements

• Docker with Compose

Run published images

git clone https://github.com/omnara-ai/omnara.git
cd omnara
docker compose -f compose.yaml --profile app up -d

Build from source

git clone https://github.com/omnara-ai/omnara.git
cd omnara
docker compose --profile app up -d --build

Open http://localhost:8000. Local authentication email is written to docker compose logs api, so you can complete signup without configuring an email provider.

Add a model provider credential in the console, create an agent profile, and launch an agent.

Shortened. The full README is on GitHub.