Skip to content
OpenShell

Overview of OpenShell

OpenShell is the safe, private runtime for fleets of autonomous AI agents. Run agents in sandboxed environments that protect your data, credentials, and infrastructure.

OpenShell is an open-source runtime for executing fleets of autonomous AI agents in sandboxed environments with kernel-level isolation. It combines sandbox runtime controls and a declarative YAML policy so teams can run agents without giving them unrestricted access to local files, credentials, and external networks.

AI agents are most useful when they can read files, install packages, call APIs, and use credentials. That same access can create material risk. OpenShell is designed for this tradeoff: preserve agent capability while enforcing explicit controls over what the agent can access.

The table below summarizes common failure modes and how OpenShell mitigates them.

Threat Without controls With OpenShell
Data exfiltration Agent uploads source code or internal files to unauthorized endpoints. Network policies allow only approved destinations; other outbound traffic is denied.
Credential theft Agent reads local secrets such as SSH keys or cloud credentials. Filesystem restrictions (Landlock) confine access to declared paths only.
Unauthorized API usage Agent sends prompts or data to unapproved model providers. Provider profiles and network policies restrict model traffic to approved endpoints and binaries.
Privilege escalation Agent attempts sudo, setuid paths, or dangerous syscall behavior. Unprivileged process identity and seccomp restrictions block escalation paths.

OpenShell applies defense in depth across the following policy domains.

Layer What it protects When it applies
Filesystem Prevents reads/writes outside allowed paths. Locked at sandbox creation.
Network Blocks unauthorized outbound connections. Hot-reloadable at runtime.
Process Blocks privilege escalation and dangerous syscalls. Locked at sandbox creation.
Provider credentials Resolves opaque credential placeholders only at profile-authorized endpoints. Attachments, rotation, and revocation update at runtime; new environment variables require a new process.

For details, refer to Sandbox Policies and Default Policy.

OpenShell supports a range of agent deployment patterns.

Use Case Description
Secure coding agents Run Claude Code, OpenCode, Codex, or GitHub Copilot CLI with constrained file and network access.
Private enterprise development Grant selected sandboxes access to self-hosted or private model endpoints while keeping sensitive context under your control.
Compliance and audit Treat policy YAML as version-controlled security controls that can be reviewed and audited.
Reusable environments Use the default Ubuntu workload or bring your own containerized runtime.

Explore these topics to go deeper:

We are a Cloud Native Computing Foundation sandbox project.