Deep Agents Harness

The Deep Agents harness adapter connects HarnessAgent to Deep Agents, a LangGraph-based agent runtime. The adapter runs a Node bridge inside the sandbox that drives the deepagents package and streams its streamEvents output back to the host over a sandbox-exposed WebSocket.

Harness packages are experimental. Expect breaking changes between releases as this early API gets further refined.

Setup 

pnpm add @ai-sdk/harness @ai-sdk/harness-deepagents @ai-sdk/sandbox-vercel

The adapter bootstraps the bridge's Node dependencies (the deepagents package and LangChain) inside the sandbox via pnpm when the first session starts.

Import 

import { deepAgents, createDeepAgents } from '@ai-sdk/harness-deepagents';

deepAgents is equivalent to createDeepAgents() with its default configuration.

Basic Usage 

import { HarnessAgent } from '@ai-sdk/harness/agent';
import { deepAgents } from '@ai-sdk/harness-deepagents';
import { createVercelSandbox } from '@ai-sdk/sandbox-vercel';


const agent = new HarnessAgent({
  harness: deepAgents,
  sandbox: createVercelSandbox({
    runtime: 'node24',
    ports: [4000],
  }),
});


const session = await agent.createSession();


let exitCode = 0;
try {
  const result = await agent.stream({
    session,
    prompt: 'Analyze this codebase and suggest improvements.',
  });


  for await (const part of result.stream) {
    if (part.type === 'text-delta') {
      process.stdout.write(part.text);
    }
  }
} catch (err) {
  exitCode = 1;
  console.error(err);
} finally {
  await session.destroy();
  process.exit(exitCode);
}

To use this agent, ensure environment variables include VERCEL_OIDC_TOKEN for Vercel Sandbox, and one of the variables listed under authentication for the model provider.

Adapter Settings

Use createDeepAgents() to configure the runtime:

const harness = createDeepAgents({
  model: 'claude-sonnet-4',
});

Settings:

  • auth: Anthropic or AI Gateway authentication settings.
  • model: model id passed to the Deep Agents (LangChain) runtime. Through AI Gateway, use the creator/model slug (e.g. anthropic/claude-sonnet-4-6, google/gemini-2.5-flash, openai/gpt-4.1-mini).
  • port: bridge port override.
  • startupTimeoutMs: maximum time to wait for the bridge to start.

Authentication

Deep Agents always drives the Anthropic client. Non-Anthropic models reach it through AI Gateway's Anthropic-compatible endpoint, which translates to any model (Gemini, OpenAI, etc.), tool calls included. Authentication is resolved from the host environment and forwarded to the sandbox bridge: explicit Anthropic auth first, then AI Gateway credentials, then ambient Anthropic credentials.

Supported environment variables:

  • AI_GATEWAY_API_KEY
  • VERCEL_OIDC_TOKEN
  • AI_GATEWAY_BASE_URL
  • ANTHROPIC_API_KEY
  • ANTHROPIC_AUTH_TOKEN
  • ANTHROPIC_BASE_URL

You can also pass explicit auth settings (anthropic or gateway). To run a non-Anthropic model, route it through AI Gateway:

const harness = createDeepAgents({
  model: 'google/gemini-2.5-flash',
  auth: {
    gateway: {
      apiKey: process.env.AI_GATEWAY_API_KEY,
    },
  },
});

Sandbox

Deep Agents requires a network sandbox with at least one exposed port, e.g. @ai-sdk/sandbox-vercel:

const sandbox = createVercelSandbox({
  runtime: 'node24',
  ports: [4000],
});

Skills

Skills passed to the session are materialized as native Deep Agents skill folders (<name>/SKILL.md plus any attached files) under $HOME/.agents/skills/ in the sandbox (outside the work dir, so they can't clash with cloned code), and loaded via Deep Agents' skills option — so the agent loads them on demand and skill file references resolve. Skills already present under <workDir>/.agents/skills/ (e.g. in a cloned repo) are also discovered.

Built-in Tools

The adapter exposes these Deep Agents built-ins through agent.tools:

  • read
  • write
  • edit
  • bash
  • grep
  • glob
  • ls
  • task
  • write_todos

Known Limitations

  • Resuming a stopped session's conversation is not supported — after session.stop(), Deep Agents' in-memory conversation state (LangGraph MemorySaver) is gone; only the sandbox workspace persists via its snapshot. Use session.detach() for cross-process handoff or session.suspendTurn() for turn continuation while keeping the live bridge running.
  • Manual compaction is not supported.