The AI SDK Harness lets you run established coding-agent runtimes through one unified interface, so you can switch runtimes without changing your application code. Today we're adding two new adapters, Deep Agents and OpenCode, both running inside a Vercel Sandbox.
Link to headingDeep Agents
@ai-sdk/harness-deepagents adapts LangChain's deepagents runtime, with built-in file and shell tools, skills, host tools, multi-turn sessions, attach and resume, and built-in tool approvals.
import { HarnessAgent } from '@ai-sdk/harness/agent';
import { deepAgents } from '@ai-sdk/harness-deepagents';
const agent = new HarnessAgent({
harness: deepAgents,
});
Basic example for using Deep Agents with HarnessAgent
Read the Deep Agents harness documentation to get started.
Link to headingOpenCode
@ai-sdk/harness-opencode boots a real OpenCode server inside the sandbox via @opencode-ai/sdk and streams its session events through the harness. It exposes OpenCode's built-in tools, supports both built-in and host tool approvals, and lets you pick the model, provider, and reasoning variant.
import { HarnessAgent } from '@ai-sdk/harness/agent';
import { openCode } from '@ai-sdk/harness-opencode';
const agent = new HarnessAgent({
harness: openCode,
});
Basic example for using OpenCode with HarnessAgent
Read the OpenCode harness documentation to get started.
The full supported list of harnesses is now: Claude Code, Codex, Deep Agents, OpenCode, Pi, with more coming soon.