Why Build a Deep Research Agent on EdgeOne Makers
The platform's long-running execution (up to 1 hour), web search tools, multi-agent orchestration, and human-in-the-loop patterns are purpose-built for complex ai research agent 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 Build a Deep Research Agent in 3 Steps
Combine web search tools, multi-agent decomposition, and report synthesis on the platform's long-running runtime — or start from the ai research agent template.
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.
Platform Capabilities for Deep Research Agent
How EdgeOne Makers enables your ai research agent — long-running execution for synthesis, web search tools, multi-agent patterns, and persistent storage for report versioning.
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 platform capabilities does a deep research agent need?
Long-running execution (300s+ for synthesis), web search tools (built-in or custom), multi-agent orchestration, human-in-the-loop for question review, and persistent storage for reports. EdgeOne Makers provides all natively.
How does the platform support parallel research?
The session-sticky runtime enables multi-agent patterns where sub-agents search different sources (web + academic) in parallel. The ai research agent orchestrator coordinates results within a single long-running session.
Can my deep research agent use web search?
Yes. The platform provides a built-in `web_search` tool powered by Tencent Cloud WSA (requires your own API key), or you can wrap any third-party search service as a custom tool for your ai research agent.
Is building a deep research agent free?
Yes. 500K model tokens/month and up to 1-hour execution time — sufficient for complex multi-step research workflows including question decomposition, parallel search, and report synthesis.
Can I add human review to my ai research agent?
Yes. The runtime's session-sticky nature supports human-in-the-loop patterns — pause for question confirmation, resume after review, and iterate on reports without losing state.