---
title: DigitalOcean Harness Runtime API Reference (public)
description: |-
    The DigitalOcean Harness Runtime API endpoints are organized into the following groups:
    Harness Runtime (54 endpoints): DigitalOcean Harness Runtime …
product: Managed Agents
url: https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/reference/api/
last_updated: "2026-08-10"
---

> **For AI agents:** The documentation index is at [https://docs.digitalocean.com/llms.txt](https://docs.digitalocean.com/llms.txt). Markdown versions of pages use the same URL with `index.html.md` in place of the HTML page (for example, append `index.html.md` to the directory path instead of opening the HTML document).

# DigitalOcean Harness Runtime API Reference (public)

DigitalOcean Harness Runtime provides managed, hardware-isolated microVM sandboxes with built-in tools such as Chromium to run harnesses and execute arbitrary code. Rich lifecycle APIs preserve conversational history and working state across sessions, letting you pause, resume, and fork work to control costs and adapt to the nonlinear nature of agentic workflows. Scale complete agents such as Claude Code or use sandboxes independently for code execution, all through the same service. See [What You Can Build](https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/details/what-you-can-build/index.html.md) for example use cases.

The DigitalOcean Harness Runtime API endpoints are organized into the following groups:

- [**Harness Runtime**](harness-runtime/) (54 endpoints): DigitalOcean Harness Runtime API under `/v2/agents`. An environment is a reusable configuration that defines what an agent needs to do work; starting a session from an environment provisions an isolated sandbox. Define an environment with a YAML environment spec, or save it as an Environment Config and create sessions from `{name, config_id}`.
- [**Signals**](signals/) (14 endpoints): The DigitalOcean Signals API provides observability for environment conversations, such as Harness Runtime conversations and Serverless Inference chat completions, detecting behavioral signals such as user disengagement, execution failures, and satisfaction indicators.