OpenCode Integration

OpenCode is an open-source terminal-based AI coding agent that enables developers to navigate codebases, execute multi-file edits, and automate software development workflows using natural language commands.

Start for free

OpenCode

Benefits with Ory + OpenCode Integration

Ory integrates with OpenCode to provide security guardrails for developers and builders to safely construct applications and agents. Ory's harness hook executes an identity and credential check on every session and tool call, enforcing fine-grained authorization to allow or deny actions while logging all activity for an audit trail. Security teams can use Observe mode to monitor how developers use the tools and Enforce mode to strictly restrict agents based on their assigned permissions.

The fastest way to get started with Ory Agent Security is to sign up for the Ory Network. Installing an Ory Agent Security plugin for your AI coding agent takes seconds. You simply copy and paste the provided command in the harness's project directory.

npx -y -p @ory/opencode ory-opencode install

View on npm

Use Cases

— 03 use cases

Agent IAM

Enforces fine-grained authorization, identity checks, and audit logging to secure OpenCode terminal sessions and agent actions.

Explore Agent IAM

CIAM

Speeds up embedding customer authentication and identity flows into applications built with OpenCode using baked-in Ory best practices.

Explore CIAM

B2B IAM

Streamlines integrating enterprise SSO, role-based access control, and multi-tenant authorization into software using OpenCode while scaling with growth.

Explore B2B IAM

Core Functionality

— 06 capabilities

Identity
Verifies developer and OpenCode agent identities before session initiation across your ecosystem through a unified control plane.
Authorization
Enforces fine-grained, policy-based access control for every OpenCode tool execution and action.
Shell
Intercepts and secures terminal-level shell commands and multi-file edits within OpenCode.
Audit
Logs complete audit trails for all OpenCode session activity, tool invocations, and API calls.
Rollout
Supports flexible deployment with Observe mode for monitoring OpenCode agent behavior and Enforce mode for strict permission enforcement.
Security Control
Delivers vendor-agnostic governance across AI tools with a unified control plane, featuring instant token revocation to cut off compromised sessions.