Why Choose EdgeOne Makers Agent Runtime
A production-grade AI runtime with session-aware routing, isolated execution, and built-in ai runtime security — zero infrastructure to manage.
One-Command Deployment
Deploy with `git push` for auto-deploy or `edgeone makers deploy` via CLI — no Docker, no Kubernetes, no server provisioning.
Built-in Agent Runtime
Managed runtime with session-sticky routing, up to 1-hour execution time, and in-memory state reuse — purpose-built for LLM calls and multi-step agent loops.
Integrated AI Models
Access DeepSeek, MiniMax, Hunyuan, and more through a unified AI gateway. New accounts receive 500K free tokens with zero configuration.
Full Observability
Zero-instrumentation distributed tracing — view complete call chains, LLM interactions, tool invocations, and latency metrics in local and cloud dashboards.
How to Use Agent Runtime on EdgeOne Makers
Deploy your agent to a managed AI runtime in three steps — the platform handles routing, scaling, and security automatically.
1
Write Your Agent
Build in the `agents/` directory with any framework (OpenAI SDK, Claude SDK, LangGraph, CrewAI, DeepAgents).
2
Deploy to Production
Push to Git (GitHub/GitLab/Gitee) for auto-deploy, or run `edgeone makers deploy` via CLI.
3
Go Live
Deploys globally in minutes with automatic SSL and edge routing.
Complete Agent Runtime Features
Everything included in the managed agent runtime — session routing, execution control, AI runtime security, and full observability.
Feature | Description |
|---|---|
| Agent Runtime | Hosts LLM calls, Agent loop orchestration, and business logic, with session-based routing and automatic scaling. |
| Sandbox Tools | Provides two separate yet interoperable API layers for both LLMs and developers. Browser automation, code execution, Shell, and file operations all run in an isolated sandbox environment. |
| Conversation Storage | Provides framework-compatible memory management, with unified APIs for sessions and messages. |
| Observability | Automatically collects call traces with zero-intrusion instrumentation, enabling unified trace viewing in both local and cloud dashboards. |
| Built-in Models | Access Hunyuan and other mainstream Chinese models through AI Gateway with a limited-time free token quota. |
What is the agent runtime on EdgeOne Makers?
The agent runtime is a managed execution environment purpose-built for AI agents. It provides session-sticky routing (same `conversation_id` routes to the same instance), up to 1-hour execution time, and in-memory state reuse across requests.
How does the AI runtime handle session state?
The AI runtime uses session-sticky routing — requests with the same `conversation_id` are routed to the same instance, preserving in-memory state. Sessions stay warm for up to 300 seconds of idle time.
What ai runtime security features are included?
The agent runtime provides isolated execution environments per session, encrypted environment variables for API keys, and sandboxed tool access. Each agent runs in its own security boundary with no cross-session data leakage.
What are the agent runtime execution limits?
Free tier: up to 3,600 seconds (1 hour) per request, 40 concurrent sessions, 200,000 executions/month, and 100,000 GB-s total memory time. Session idle timeout is 300 seconds.
Does the agent runtime support both session and stateless modes?
Yes. The AI runtime offers two modes: session mode (`agents/` directory) with sticky routing for stateful agents, and request mode (`cloud-functions/` directory) for stateless, per-request execution.