Agent framework integrations
EvalGate accepts quality evidence at three boundaries: an SDK wrapper around a runtime call, an OpenTelemetry/OpenInference trace export, or an authenticated MCP/API call. Pick the narrowest boundary your application already supports.Support matrix
The framework packages remain your dependencies. EvalGate’s structural wrappers
do not install them or take over their model-provider configuration.
CrewAI
Wrap the crew object after creating an authenticated client and workflow tracer:kickoff call. It does not change the crew’s tools or provider keys.
AutoGen
Use the corresponding conversation wrapper when your runtime exposesinitiate_chat:
Vercel AI SDK
The Vercel integration wraps a Language Model v3-compatible object without adding theai package as an EvalGate runtime dependency:
MCP product and documentation servers
Use the public server cards to inspect the tools before connecting:- Product card:
https://www.evalgate.com/.well-known/mcp/server-card.json - Documentation card:
https://www.evalgate.com/.well-known/mcp/docs-server-card.json - Product transport:
https://www.evalgate.com/api/mcp - Documentation transport:
https://www.evalgate.com/api/mcp/docs
docs:read. Product tools are filtered by
the scopes on the organization API key. See MCP integration
and agent authentication.
DSPy and other OpenTelemetry-compatible runtimes
EvalGate does not currently ship a first-class DSPy wrapper. Use an existing OpenTelemetry or OpenInference instrumentation path to export trace evidence, or call the Python SDK explicitly at the application boundary. Keep model calls and tool side effects in your application; EvalGate receives the trace and evaluation evidence you choose to send. See TypeScript SDK: OTLP/OpenInference and trace setup. Do not label a generic trace export as a dedicated framework integration in architecture or procurement documents.Verify the integration
Before relying on a framework path for a release gate:- Send one successful and one failing run from a non-production environment.
- Confirm workflow, agent, model, tool, and error fields preserve the evidence needed by your assertions.
- Turn one reviewed failure into a permanent evaluation case.
- Run the gate against the exact commit and baseline used for the release.
- Confirm provider, budget, parser, and missing-trace failures remain explicit.