OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your BeeAI agent logic, framework setup, or platform deployment.
What is BeeAI?
BeeAI is an open‑source, framework‑agnostic platform and framework for building, deploying, and sharing AI agents, with built‑in observability based on OpenTelemetry and OpenInference, plus integrations with Arize Phoenix and Langfuse. It helps teams focus on agent reliability and rules while the platform handles logging, tracing, and sharing agents across environments.
Why use Orq with BeeAI
Trace agent behavior end to end
Trace BeeAI agent runs end to end, including prompts, tool invocations, memory operations, model responses, and errors in one place. You get clearer visibility into agent behavior without stitching together traces across BeeAI Framework, Phoenix/Langfuse, and downstream services.
Model flexibility without rewiring agents
Test new models, add providers, or assign different model tiers to different BeeAI workflows from Orq.ai, while keeping your BeeAI agent definitions, rules, and platform configuration stable.
Evaluate real production runs
Use real BeeAI conversations and traces to build datasets, compare prompt or model changes, and move from subjective tuning to measurable quality checks. You can turn failed or slow agent runs into eval inputs for future experiments across providers.
Control spend and access centrally
Track token usage and spend per agent, team, and workflow so you can see which BeeAI routes drive cost. Add budgets, rate limits, and approved‑model lists at the Orq platform layer instead of enforcing governance separately inside each BeeAI agent or framework configuration.
How the integration works
Step 1
Point BeeAI at Orq.ai’s router
Configure BeeAI’s model clients (for example OpenAI, watsonx.ai, Ollama, or other providers configured in BeeAI Framework) to use Orq.ai’s OpenAI‑compatible base URL instead of calling each LLM provider directly. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.
Step 2
Enable tracing from BeeAI to Orq
Keep BeeAI’s OpenTelemetry / OpenInference instrumentation enabled while routing LLM calls through Orq’s AI Gateway / Router. BeeAI continues to emit spans and logs for agent execution, and Orq logs the LLM interactions 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 BeeAI workflows and assign them model tiers, fallback chains, and region/data policies. BeeAI sends the LLM request to the configured Orq route, and Orq applies the routing rules you define before invoking OpenAI, watsonx.ai, or other providers.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for BeeAI agents, and run evals or experiments on their traces. You can then adjust routes, models, or prompt configurations centrally where supported, without changing BeeAI’s agent rules or platform deployment.
Use Cases
Multi‑agent products with real observability
Trace which BeeAI agent, tool call, memory update, and model contributed to a failed workflow or unexpected outcome, combining Phoenix/Langfuse views with Orq’s router‑level traces.
Cost‑aware internal tools
Route routine steps to lower‑cost models while keeping complex reasoning or policy‑heavy flows on stronger routes configured in Orq, all while BeeAI enforces agent rules and structure.
Eval‑driven agent improvements
Reuse failed conversations and BeeAI trace trees 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 BeeAI traffic, then promote or roll back based on traces and evals, instead of editing each agent definition or provider binding by hand.
FAQ
Do I have to change my BeeAI code to use Orq.ai?
In many cases, you can repoint the LLM calls that BeeAI makes (for example in OpenAI or watsonx.ai provider configs) to Orq.ai’s OpenAI‑compatible router and keep BeeAI’s OpenTelemetry/OpenInference setup as‑is, adding only minimal configuration instead of rewriting your agents. The agent definitions, rules, and platform deployment stay in BeeAI.
Does Orq.ai replace BeeAI’s own runtime or framework?
No. BeeAI remains your agent framework and platform, with observability via Phoenix, Langfuse, or other OpenTelemetry backends. Orq.ai sits alongside it as the control plane for models, multi‑provider routing, cost tracking, and evaluation. You still design and run agents in BeeAI, 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 BeeAI if I move to Orq.ai?
Yes. You can bring your existing provider keys (OpenAI, watsonx.ai, Ollama, and others) into Orq.ai and route BeeAI traffic through them, alongside any new models you add later. That way you centralize access, routing, and tracking without losing the providers you already rely on. Bring production controls to BeeAI agents
