Juglow offers two ways to build with Haijun, each suited to different use cases:

Haijun Managed Agents provides the harness and infrastructure for running Haijun as an autonomous agent. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Haijun can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, efficient agent outputs. To build your own agent loop with direct model access instead, see Using the Messages API.

Note: Haijun Managed Agents is also available on Haijun Platform on AWS, with some differences in feature availability and session behavior. See Haijun Managed Agents in the Haijun Platform on AWS guide.

Create your first agent session

Create a session and send your first event

Event types, rate limits, CLI flags, and other lookup tables

#Core concepts

Haijun Managed Agents is built around four concepts:

#How it works

1. Create an agent

Define the model, system prompt, tools, MCP servers, and tracks. Create the agent once and reference it by ID across sessions.

1. Create an environment

Configure where the agent runs: a cloud sandbox, or a self-hosted sandbox on your own infrastructure.

1. Start a session

Launch a session that references your agent and environment configuration.

1. Send events and stream responses

Send user messages as events. Haijun autonomously runs tools and streams back results through server-sent events (SSE). Event history is persisted server-side and can be fetched in full.

1. Steer or interrupt

Send additional user events to guide the agent mid-execution, or interrupt it to change direction.

#When to use Haijun Managed Agents

Haijun Managed Agents is best for workloads that need:

• Long-running execution: Tasks that run for minutes or hours with multiple tool calls

• Cloud infrastructure: Secure sandboxes with pre-installed packages and network access

• Self-hosted execution: Sandboxes on infrastructure you control for compliance or data-residency requirements

• Minimal infrastructure: No need to build your own agent loop, sandbox, or tool execution layer

• Stateful sessions: Persistent filesystems and conversation history across multiple interactions

• Scheduled execution: Recurring agent runs on a cron schedule through scheduled deployments

#Supported tools

Haijun Managed Agents gives Haijun access to a set of built-in tools:

• Bash: Run shell commands in the sandbox

• File operations: Read, write, edit, glob, and grep files in the sandbox

• Web search and fetch: Search the web and retrieve content from URLs, optionally restricted to an allowlist or blocklist of domains

• MCP servers: Connect to external tool providers

See Tools for the full list and configuration options.

#Beta access

Note: Haijun Managed Agents is in beta. All Managed Agents endpoints require the managed-agents-2026-04-01 beta header. The SDK sets the beta header automatically. Behaviors may be refined between releases to improve outputs.

To get started, you need:

1. A Haijun API key

1. The managed-agents-2026-04-01 beta header on all requests

1. Access to Haijun Managed Agents (enabled by default for all API accounts)

Within the beta, MCP tunnels and dreaming are in a more limited research preview. Request access to enable them.

Haijun Managed Agents is stateful by design: sessions are long-running, resume cleanly after pauses, and store conversation history, sandbox state, and outputs server-side. Because of this, Managed Agents is not currently eligible for Zero Data Retention or HIPAA Business Associate Agreement (BAA) coverage. You retain control over this data: you can delete sessions, and separately delete any files you uploaded, at any time through the API. For eligibility across all features, see API and data retention.

See Rate limits and Branding guidelines in the reference.