Use Orq.ai as the model control layer for the Claude Agent SDK. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your Claude agent logic or orchestration code.
What is Claude Agent SDK?
The Claude Agent SDK is Anthropic’s framework for building agents and multi‑agent systems on top of Claude models, with abstractions for tools, workflows, memory, and safety. It helps teams focus on agent behavior while the SDK handles calling Claude and coordinating tools.
Why use Orq with Claude Agent SDK
Trace agent behavior end to end
Trace Claude Agent SDK runs end to end, including prompts, tool invocations, intermediate steps, model responses, and errors in one place. You get clearer visibility into agent behavior without stitching together custom logs across multiple services.
Model flexibility without rewiring agents
Test new models, add alternative providers, or assign different model tiers to different workflows from Orq.ai, while keeping your Claude Agent SDK agents, tools, and orchestration code stable. Your SDK code still “thinks” it’s talking to a Claude‑style client; Orq handles which underlying model is called.
Evaluate real production runs
Use real conversations and traces from Claude‑SDK‑driven agents to build datasets, compare prompt or model changes, and move from subjective tuning to measurable quality checks. Failed or slow runs can be turned into eval inputs before you roll out changes.
Control spend and access centrally
Track token usage and spend per agent, team, and workflow so you can see which routes drive cost. Add budgets, rate limits, and approved‑model lists at the Orq platform layer instead of enforcing governance separately inside each SDK‑based application.
How the integration works
Step 1
Point Claude Agent SDK traffic at Orq.ai’s router
Configure the SDK’s client setup so that its “Claude” HTTP calls go to Orq.ai’s base URL (using Orq’s Anthropic provider or OpenAI‑compatible interface) instead of calling Anthropic directly. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.
Step 2
Enable tracing from SDK workloads to Orq
Keep your existing logging / monitoring in place while routing LLM calls through Orq’s AI Gateway / Router. Your agents continue to emit logs for tool steps and workflow decisions, and Orq records LLM interactions, latency, and cost metrics for those requests, so you can see both agent‑level and model‑level traces.
Step 3
Define routes, fallbacks, and policies in Orq
Create routes for key Claude‑SDK workflows and assign them model tiers, fallback chains, and region/data policies. Your agents send the request to the configured Orq route, and Orq applies the routing rules you define before invoking Claude or alternative models.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for Claude‑SDK agents, and run evals or experiments on their traces. You can then adjust routes, models, or prompt configurations centrally where supported, without changing your SDK agent graph.
Use Cases
Multi‑agent products with real observability
Trace which agent, tool call, and model contributed to a failed workflow or unexpected outcome, combining your own logs from the Claude Agent SDK with Orq’s router‑level traces.
Cost‑aware internal tools
Route routine steps to lower‑cost models while keeping complex reasoning or high‑stakes flows on your strongest Claude routes configured in Orq.
Eval‑driven agent improvements
Reuse failed conversations and agent traces as eval inputs before shipping prompt, tool, or model changes, turning production telemetry into a continuous improvement loop.
Safer experimentation across providers
Test a new provider or model on a small share of SDK traffic, then promote or roll back based on traces and evals, instead of editing each agent definition or HTTP client config by hand.
FAQ
Do I have to change my Claude Agent SDK code to use Orq.ai?
In many cases, you can repoint the SDK’s HTTP client (base URL and key) to Orq’s router and keep your existing agent logic as‑is, adding only minimal configuration instead of rewriting agents. The agent definitions, tools, and orchestration stay in the SDK.
Does Orq.ai replace Claude Agent SDK’s own runtime or framework?
No. Claude Agent SDK remains your agent framework and runtime; you keep using its abstractions and Anthropic’s safety tooling. Orq.ai sits alongside it as the control plane for models, multi‑provider routing, cost tracking, and evaluation. You still design and run agents using the Claude Agent SDK, but you use Orq to see what they cost, which models they should call, and how LLM behavior compares across providers under the same agent workflow.
Can I keep using my existing LLM providers with Claude Agent SDK if I move to Orq.ai?
Yes. You can bring your existing Anthropic API key into Orq.ai and route traffic through Claude, alongside any new models you add later. That way you centralize access, routing, and tracking without losing the Anthropic setup you already rely on. Bring production controls to Claude-SDK agents
