Why Choose EdgeOne Makers as Your LangGraph Platform
The best langgraph deployment experience — session-sticky runtime for stateful graphs, built-in memory, and up to 1-hour execution for complex langgraph builder workflows.
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 Deploy LangGraph on EdgeOne Makers
From langgraph builder code to production langgraph deployment in three simple steps.
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 LangGraph Platform Features
Everything your langgraph deployment needs — stateful runtime, persistence, sandbox tools, and built-in AI models.
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. |
How do I deploy LangGraph on EdgeOne Makers?
Write your LangGraph agent in the `agents/` directory, set `framework` to LangGraph in `edgeone.json`, and push to Git or run `edgeone makers deploy`. Your langgraph deployment goes live in seconds.
Does the langgraph platform support stateful graph execution?
Yes. The session-sticky runtime preserves in-memory state between requests with the same `conversation_id`, perfect for LangGraph's stateful graph patterns. Execution can run up to 1 hour.
Is the langgraph platform free to use?
Yes. Free tier includes 200,000 executions/month, 500K model tokens, and 40 concurrent sessions — sufficient for most langgraph deployment scenarios.
Can I use the langgraph builder with built-in AI models?
Yes. The platform auto-injects AI gateway credentials supporting DeepSeek, MiniMax, Hunyuan, and more. Your langgraph builder code can access models via standard OpenAI-compatible SDK.
Does langgraph deployment include observability?
Yes. Every langgraph deployment gets zero-instrumentation distributed tracing — view complete graph execution chains, LLM calls, and tool invocations in local and cloud dashboards.