Backed byYCombinator

The open-source alternative to Claude Managed Agents

One API to deploy and run agents for your users and team, on any model, any machine, and any cloud.

Start buildingTalk to a founder
npx omnara agents launch \
  --name "General agent" \
  --source '{  }' \
  --message "What tools do you have access to?"
Or prompt your agent:
Read omnara.com/SKILL.md to set up my agent

Used by teams at

What you can build

One stateful, open-source agent API powers agents wherever your users and team already work:

Agents in your product's dashboard1/4

Deploy an agent with one prompt

Paste a prompt into your coding agent to deploy a production-ready agent for your users or team.

Engineering

SRE agent

Your on-call teammate with read-only access to AWS and your code. Ask it to investigate an alarm, check on a release, or dig into a user’s activity.

…/sre-agent/SKILL.md

How it works
Engineering

Coding agent in Slack

Mention it in Slack to ask how your code works, debug an issue, or ship a fix as a pull request.

…/slack-coding-agent/SKILL.md

How it works
GTM

Signal digest

A daily digest of the posts worth your time on any topic: customers, competitors, or your category.

…/x-signal-agent/SKILL.md

How it works
Operations

Browser agent

Signs in to your web apps and works in a real browser: pulls numbers from dashboards, fills in forms, or works through a queue overnight.

…/browser-agent/SKILL.md

How it works
Creative

Video generation agent

Turns a brief into a short video with Remotion and delivers an MP4.

…/video-generation-agent/SKILL.md

How it works
Anything else

Build your own

Describe the agent you want. Your coding agent asks a few questions, then creates it.

omnara.com/SKILL.md

Browse all examples
“Omnara opened my eyes to what AI agents can do for our agency. We went from basic AI implementation with wizards and one-off prompts to more than ten real AI agents for proposal building, SEO analysis, sales, and R&D. We’re even developing agents for our customers. Now I have one place to run them all and see their costs.”
Dan KoganFounder & CEO, 1Digital®

Deploying agents to production is hard

A prototype agent takes an afternoon. A production agent needs a platform, and most teams end up building their own. With Omnara, it's ready on day one, no platform team needed.

“I do wish this all could be done with less plumbing, as everyone has to build the ~same thing here. … Add it all up and you get roughly 100,000 lines of TypeScript and four months of work.”
David Cramer Founder, Sentry — on building Junior, their internal Slack agent
“A thin wrapper is fine until you need durability, shared visibility, retry semantics, cost accounting, multi-provider support, and collaboration surfaces. At that point the harness becomes the product.”
Joey Wang & Gabe Pereyra Harvey — on Spectre, their internal cloud agent platform
“Unattended agent coding at scale requires a cloud developer environment that’s parallelizable, predictable, and isolated. … It’s fundamentally difficult to build local agents that have all the power of a developer’s shell but are appropriately constrained.”
Stripe Engineering on Minions, their unattended one-shot coding agents
“We learned quickly that we didn’t just need ‘a place to run code in the cloud.’ We needed purpose-built agent infrastructure: a runtime we could control end-to-end, with explicit sandbox lifecycle APIs and egress controls designed for our threat model.”
WorkOS Engineering on Horizon, their autonomous code factory
“Every role needed a different combination of tools, context, permissions, and infrastructure — all assembled on the fly, without compromising security, speed, or reliability. We couldn’t find a cloud agent provider that met those requirements, so we built it ourselves.”
Sierra Engineering on building Pinecone, their internal cloud agent
“It’s the substrate: session, harness, sandbox, gateway, the durable event log, the credentials proxy, the observability pipeline. … Cells die, sandboxes die, machines die. The conversation doesn’t.”
Shopify Engineering on Aquifer, the platform they built to run agents
Stripe’s MinionsShopify’s AquiferSierra’s PineconeSentry’s JuniorHarvey’s SpectreRamp’s InspectWorkOS’s HorizonBrowserbase’s bb

Own your agents without building the platform

Managed agent platforms like Claude Managed Agents are fast to start, but lock your models, machines, cloud, data, and pricing to one vendor. Omnara gives you the speed without the lock-in.

Time to production

In-house
Months
Managed platforms
Fast
Omnara
Fast

Maintenance

In-house
Your platform team
Managed platforms
The vendor
Omnara
Us, or self-host

Models

In-house
Any
Managed platforms
One vendor’s
Omnara
Any

Platform hosting

In-house
Your cloud
Managed platforms
Vendor’s cloud
Omnara
Any cloud

Agent machines

In-house
What you build
Managed platforms
Vendor’s sandboxes
Omnara
Any machine

Your data

In-house
Yours
Managed platforms
Vendor-held
Omnara
Yours

Pricing

In-house
Salaries + infra
Managed platforms
Vendor-set
Omnara
$0 platform fee

Source code

In-house
Yours to maintain
Managed platforms
Closed
Omnara
Open source

Features

Everything you'd otherwise build in-house, ready on day one, whether you're building internal agents for your team or agentic experiences for your users.

Durable Agents

Agents don't lose their work when something breaks, and they use no compute while idle. Omnara stores agent state in a durable event log, so agents can run indefinitely and recover from even the worst failure scenarios.

Stream the agent timeline

Why we built it this way: The log is the agent · Serverless agents

Any machine

Run agents on any machine. Start machines with nothing to set up and pay for them through Omnara, bring your own Blaxel, Daytona, or Unikraft Cloud account, or install the Omnara daemon on a laptop, VM, or container. The daemon connects outbound, so there are no ports to open.

Connect machines and pools

Access Controls

Let agents act without handing over the keys. Require human approval for risky tool calls, store credentials as encrypted, scoped secrets, give people and API keys role-based access, and audit every action in an append-only history.

Set tool permissions

Agent-ready APIs

Put agents inside your own product instead of someone else’s app. Launch, steer, and observe them from the REST API, TypeScript SDK, or CLI, and change their behavior mid-conversation by posting a new config, with nothing to redeploy.

Explore the API

Any model

Never get locked into one model vendor. Use any model behind a compatible endpoint — OpenAI, Anthropic, OpenRouter, LiteLLM, or models you host yourself — and switch when price or quality changes.

Add a model provider

Integrations

Meet your team where it already works. Connect MCP servers and reusable skills to reach your data, and talk to agents through first-party Slack, Discord, and GitHub integrations.

Browse integrations

Frequently asked questions

Everything you need to know about Omnara, self-hosting, and what you can build.

What is Omnara?

Omnara is an open-source API for running agents in production. The Omnara API handles execution and state while you choose the models, tools, machines, and how users interact with each agent.

How is Omnara different from Claude Managed Agents and other managed agent platforms?

Managed agent platforms run your agents on one vendor’s models, machines, cloud, and pricing. Omnara is open source: host the platform on our cloud or yours, use any compatible model, and run agents on any machine, so your agents and their data stay yours.

How is Omnara different from agent frameworks like Vercel’s eve, Mastra, or LangGraph?

Agent frameworks are libraries for writing an agent as code and shipping it inside your app, often on one vendor’s gateway, workflow engine, or sandboxes. In Omnara, agents are durable API objects, and the open-source control plane handles state, machines, permissions, and history. Frameworks fit one agent built into your app; Omnara fits many agents you launch and change through an API, without redeploying.

How much does Omnara cost?

The platform itself is free. Bring your own model keys and machines at no charge, or pay as you go with Omnara credits for models at provider token rates and machines by active time. Self-hosting is free.

Do you have a startup program?

Yes. Startups building on agents can apply for Omnara credits. Apply here.

Do I need to run any infrastructure?

No. Omnara provides a hosted cloud where the infrastructure (sandboxes, model providers, hosting) is managed for you. You can also self-host Omnara.

Where do agents execute?

Wherever you grant them access: no machine, one, or several, local or in the cloud. Without a machine, an agent runs entirely on Omnara with nothing to set up, which suits agents that don’t need a shell, like ones that work through web search, fetch, custom tools, or MCP servers. When it needs one, connect your Blaxel, Daytona, or Unikraft Cloud account, use machines paid for with Omnara credits, or install the Omnara daemon on any macOS or Linux laptop, VM, or container.

Which models are supported?

Omnara is model-agnostic: use OpenAI, Anthropic, OpenRouter, or any compatible endpoint. That includes open-source models like GLM, Qwen, and DeepSeek, through OpenRouter or hosted yourself.

Is it really open source? Can I self-host?

Yes. Omnara is available under the Apache 2.0 license at github.com/omnara-ai/omnara. Omnara Cloud adds managed services. Self-host in your own VPC for full control, or start on the managed cloud and move later.

Do I own my data?

Yes. On Omnara Cloud, all data is queryable through the API. To keep it in your own infrastructure, self-host Omnara or book a call and we'll deploy it in your cloud.

Does Omnara support permissions?

Tool policies are enforced by the platform. For risky actions, you can configure Omnara to pause for approval.

We handle the infrastructure.

You build the agent.

Start buildingTalk to a founder