Use Orq.ai as the model control layer for LangGraph. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your LangGraph graphs, nodes, or edge logic.
What is LangGraph?
LangGraph is a graph‑based framework (from the LangChain team) for building stateful, multi‑step, and multi‑agent workflows, where each node represents a tool, model call, or decision step. It helps teams focus on orchestration and state management instead of manually wiring every transition and retry.
Why use Orq with LangGraph
Trace graph and agent behavior end to end
Trace LangGraph runs end to end, including prompts, node transitions, tool calls, model responses, and errors in one place. You get clearer visibility into how each graph executed, without stitching together logs across multiple services.
Model flexibility without rewiring graphs
Test new models, add alternative providers, or assign different model tiers to different nodes and edges from Orq.ai, while keeping your LangGraph logic and state machine stable. Your graph code still “thinks” it’s talking to standard LLM clients; Orq handles which underlying model is called.
Evaluate real production runs
Use real LangGraph traces like inputs, node paths, tool decisions, and outputs 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 graph, 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 LangGraph project.
How the integration works
Step 1
Point LangGraph’s LLM clients at Orq.ai’s router
Configure the LLM clients used by LangGraph nodes (for example ChatOpenAI or other chat/completion classes) to use Orq.ai’s base URL and key instead of calling each provider directly. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.
Step 2
Enable tracing from LangGraph to Orq
Keep your existing logging / monitoring in place while exporting LangGraph spans and traces to Orq’s telemetry endpoint. LangGraph continues to send data about node execution and state transitions, and Orq records LLM interactions, latency, and cost metrics, so you can see both graph‑level and model‑level traces.
Step 3
Define routes, fallbacks, and policies in Orq
Create routes for key LangGraph workflows (for example research graphs, multi‑tool agents, or long‑running processes) and assign them model tiers, fallback chains, and region/data policies. LangGraph sends LLM requests to the configured Orq routes, and Orq applies routing before invoking OpenAI, Gemini, Claude, or other models.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for LangGraph apps, and run evals or experiments on their traces. You can adjust routes, models, or prompt configurations centrally where supported, while LangGraph continues to handle nodes, edges, and state.
Use Cases
Multi‑agent products with real observability
Trace which LangGraph node, tool, and model contributed to a failed workflow or unexpected outcome, combining your existing debugging views with Orq’s router‑level traces.
Cost‑aware internal tools
Route routine steps like simple QA or summarization to lower‑cost models while keeping complex planning, multi‑agent collaboration, or critical decision nodes on your strongest routes configured in Orq.
Eval‑driven agent improvements
Reuse failed conversations, graph paths, and tool decision logs as eval inputs before shipping prompt, node, or model changes, turning production telemetry into a continuous improvement loop.
Safer experimentation across providers
Test a new model or provider on a small share of LangGraph traffic, then promote or roll back based on traces and evals, instead of editing each node or LLM config by hand.
FAQ
Do I have to change my LangGraph code to use Orq.ai?
In many cases, you can repoint the LLM clients your nodes use (base URL, key, and model name) to Orq’s router and enable trace export to Orq, keeping graphs and state logic the same. Tools, vector stores, and other components stay in LangGraph.
Does Orq.ai replace LangGraph’s own runtime or framework?
No. LangGraph remains your framework for stateful, multi‑step agents and workflows, and you can keep using your existing observability tools. Orq.ai sits alongside it as the control plane for models, multi‑provider routing, cost tracking, and additional evaluation. You still design and run agents and graphs in LangGraph, but you use Orq to see what they cost, which models they should call, and how LLM behavior compares across providers under the same workflow.
Can I keep using my existing LLM providers with LangGraph if I move to Orq.ai?
Yes. You can bring your existing provider keys into Orq.ai and route LangGraph traffic through them, alongside any new models you add later. That way you centralize access, routing, and tracking without losing your current LangGraph integrations. Bring production controls to LangGraph apps
