Skip to content
Agents tracked: 502 Releases (7d): 762 Agent status: no reported issuesSince last limit reset: Claude 11d · Codex 9d For AI agents: Markdown Updated Nov 22, 2026

Omnara

by omnara-ai

launch and steer cloud AI agents from chat.

Cloud and DevOpsOfficialRemote

GitHubWebsite

1. Made by

“"websiteUrl": "https://www.omnara.com"”

The repository belongs to the omnara-ai organization, its server.json points to omnara.com, and the server exposes Omnara's own API.

github.com/omnara-ai/omnara/blob/401a1944bdd5dca2eb7de186ee9a638bf47dcb09/server.json

Checked against its repository at one commit, on Nov 10, 2026. Tap a verdict to see its source.How we checkedReport an error

What Omnara does

Omnara is an open-source service that runs AI agents for you on rented or your own computers, around the clock. Its connector lets Claude Code, Codex or Cursor launch those agents, message them, answer their questions and set up their models, machines and schedules. You sign in through the browser, so no key is pasted.

What people use it for

Hand a long job to a cloud agent

From your coding assistant, start an Omnara agent that keeps working on its own machine after you close the laptop, for example a code review.

Answer an agent that waits for you

Agents can stop and ask before a risky step. See what they are waiting on and approve or deny it without opening the dashboard.

Run an agent on a schedule

Set a daily or weekly time at which an agent gets a message or a new agent starts, such as a morning usage report.

Set up models, machines and keys

Let the assistant add a model provider, a pool of sandbox machines and stored keys, then share them with one project.

Give one project's tools to a client

For a client or another tool that should see only some projects, connect it with a limited organization key instead of your own login.

Omnara popularity

3,417
GitHub stars, omnara-ai/omnara
0
public agent projects connect it
Omnara: GitHub starsomnara-ai/omnara 3,417

Tools it gives your agent (75)

What it sends and its license

Sends

each tool call with its arguments, such as agent messages, configs and secrets you create

To Omnara Cloud (app.omnara.com), or your own server when self-hosted; on every tool call. Opt out: self-host Omnara and connect to your own instance.

Sends

the launched agents' prompts, files and tool results

To the model provider and the machines set in the agent's config; while an agent runs. Opt out: choose your own model provider and machines in the config.

The code is open source under Apache 2.0 and free to host yourself. Omnara Cloud has no platform fee, but its models and machines are paid by use.

In a paid app
Yes

Apache 2.0 code; Omnara Cloud use is paid by use for its models and machines.

“Self-host it for free under Apache 2.0, or use Omnara Cloud.” source

client-work
Yes

Allowed; give each client its own limited org key rather than your login.

“For service integrations, use an org API key instead, so access doesn't hinge on one person's account.” source

Pass on its files
With conditions

The code may be passed on or changed under Apache 2.0 with its license kept.

“Apache License Version 2.0, January 2004” source

Is it alive

Latest version

0.1.0 in the registry, updated Sep 14, 2026

Last release

registry version 0.1.0; hosted service, repository updated daily (last commit 2026-11-09)

Remote endpoint
yes: one unauthenticated GET to https://app.omnara.com/mcp answered 401 (sign-in required) on 2026-11-10

Alternatives

Omnara This page

3,417 starsRemote

letta

Pick it if your agents mainly need memory they keep and edit across conversations

Local

openai-agents-npm

Pick it if you want the agent loop inside your own app's code

Local

e2b

Pick it if you only need a safe cloud computer where code can run, without an agent platform

Local

All cloud and devops servers

Get started

Tell your AI assistant

“Connect the Omnara MCP server at https://app.omnara.com/mcp, run whoami, list my projects and agents, and ask me before launching, cancelling or deleting anything.”

Connect it

claude mcp add --transport http omnara https://app.omnara.com/mcp

Browser sign-in (OAuth) by default; clients without it send a personal or org key (omnara_pat_v1_… or omnara_org_v1_…) in the Authorization header. The cursor entry is the docs' generic mcp.json, not a Cursor-specific section.

Mistakes to avoid

Giving a shared tool or a client's assistant your own browser sign-in
Create a member-role org API key with roles on only the needed projects and put it in the Authorization header

The browser sign-in carries all your roles in every organization.

Asking the agent to create an API key for itself through the API
A person creates keys in the dashboard (Personal tokens, or API Tokens for org keys)

Key creation, role changes and revoking need a dashboard session.

Committing a config with a pasted omnara_pat_v1_… token
Use the browser sign-in, or keep the token outside the repository

A personal token acts as you with all your access and does not expire on its own.

Expecting a tool that is not listed to work after the connection's roles change
Re-list the tools; the server hides tools your roles do not allow

tools/list is filtered per caller by the operations the caller may run.

Questions

Do I need an API key to connect?

No. Clients that support the sign-in flow open the browser; a key is only for clients without it or to limit access to some projects.

Is it free?

Self-hosting is free, and Omnara Cloud has no platform fee. You pay for Omnara's models at provider token rates and for its sandboxes by active time and storage.

Which models can the agents use?

Any model behind an OpenAI- or Anthropic-compatible endpoint, including OpenAI, Anthropic, OpenRouter, Amazon Bedrock, LiteLLM and Ollama.

Where is the agents' history kept?

On Omnara Cloud it is stored by Omnara; when you host it yourself it stays in your own Postgres database.