The framework for running simple, secure, and durable autonomous AI agents.
OpenRoutines helps you run autonomous multi-player assistants that know how to work on a team. Scaffold one in minutes, test it locally, deploy it on your own infrastructure – then maintain it like any other software you ship.
curl -fsSL https://get.openroutines.dev/install.sh | bash
Why OpenRoutines?
Plenty of tools will run a prompt on a schedule. OpenRoutines helps you build autonomous agents that work with your team to do a job.
-
Agent-as-code
No chat interface mystery meat or "cross fingers" updates. Every agent is a single git repository that you ship like the rest of your software.
-
Teamwork ready
OpenRoutines agents know how to work on teams out of the box. You focus on the routines that do the work; the teamwork takes care of itself.
-
Secure by design
A sandboxed, deny-by-default design and encrypted credentials keeps OpenRoutines agents secure, trustworthy, and enterprise-ready.
-
BYO everything
Mix models and providers per routine, run the container wherever you want, and build the whole thing with whatever coding agent you like.
-
Built to run unattended
Routines are never silently skipped, duplicated, or retried forever. Failures recover gracefully, and notify you when they can’t.
-
Local-first development
Write a routine, rehearse it safely, and run it locally in the same container production uses. No mandatory staging, no risky deploys.
Example agents
See what kind of agents you can build with OpenRoutines
-
Product Assistant
Triages and clusters incoming feedback, grooms the roadmap, and keeps the docs and changelog up to date.
-
Engineering Assistant
Diagnoses CI failures, patches dependency advisories, keeps branches fresh, and sweeps for missing tests.
-
Knowledge Librarian
Answers questions from your knowledge base, reports on changes, and fills recurring gaps.
-
Market Scout
Surfaces what your audience is talking about, watches competitor moves, and runs research questions to ground.
-
Account Assistant
Preps sales and success teams for calls, flags account risks and opportunities, and tracks support tickets.
-
Daily Briefer
Sends a morning email with the weather, what to wear, inbox priorities, calendar, and an inspiring quote.
Frequently asked questions
What exactly is an OpenRoutines agent?
A single git repository that builds into one Docker container. Routines are markdown files: frontmatter declares the scope, the body is the prompt.
Where can I run one?
Anywhere a container runs -- a VPS, Fly, Render, your own homelab. There's no database, queue, or secrets platform to stand up behind it.
Which model providers are supported?
Any provider opencode supports. The provider is configuration, so you can move an agent between models without rewriting its routines.
How are credentials handled?
They're encrypted in the repository and scrubbed from logs. A routine only gets the credentials its frontmatter explicitly grants.
What can an agent actually reach?
Nothing until you say so. Runs are sandboxed and the shipped container listens on no ports, so an agent's entire reach is greppable in its own files.
Can I build a realtime chat agent with it?
No. The fastest an agent can start responding is about a minute, so conversation is the wrong shape. OpenRoutines is built for autonomous agents that work unattended, not ones a person sits waiting on.
How do I try one before deploying it?
Scaffold an agent and run it locally against real routines, then deploy the same container to your own infrastructure when you're happy with it.