Temporal (AI agents / durable execution)
Durable-execution platform whose deterministic-workflow + non-deterministic-activity mo…
Durable-execution platform whose deterministic-workflow + non-deterministic-activity model has become the de facto orchestration layer under production agents (used by OpenAI, Replit, Lovable). Raised a $300M Series D at a $5B valuation (Feb 2026, a16z); explicitly powers agent runtimes at OpenAI/Replit/Lovable/ADP/Abridge. Less an agent framework than
Beta
Status
OpenTelemetry
Pattern
Go
Runtime
Not yet published
SDK version
Readiness
What “Beta” means for Temporal (AI agents / durable execution)
The integration path is built and tested. Real customers can attach now, but expect minor breaking changes until the 1.0 contract freeze.
How it attaches
OpenTelemetry.
Temporal (AI agents / durable execution) emits OpenTelemetry spans. Point the OTLP exporter at the Trustvice receiver — it parses OpenInference and OpenLLMetry conventions. No code changes.
Set the OTEL_EXPORTER_OTLP_ENDPOINT environment variable to your workspace's Trustvice OTel ingest URL. Works with any framework that emits OpenTelemetry spans.
- 1
Set the OTLP endpoint
Set OTEL_EXPORTER_OTLP_ENDPOINT to your workspace's Trustvice OTel ingest URL and put your workspace API key in OTEL_EXPORTER_OTLP_HEADERS as a bearer token.
- 2
Enable the framework's OTel emission
Confirm Temporal (AI agents / durable execution) is emitting spans — some frameworks emit by default, others need explicit instrumentation opt-in.
- 3
Verify the convention
Trustvice parses both OpenInference (openinference.* attributes) and OpenLLMetry (gen_ai.* / traceloop.* attributes). The Integrations page surfaces which convention was detected on the first received span.
export OTEL_EXPORTER_OTLP_ENDPOINT=https://api.trustvice.com/ingest/otel export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer twk_abc123" export OTEL_EXPORTER_OTLP_PROTOCOL=http/json export OTEL_SERVICE_NAME=temporal-agent
Coverage
2 event types captured.
agent.invocationEvery top-level agent run — the input, the resolved output, timing, and token usage.
tool.callEach tool / function the agent invokes, with arguments and the returned result.
The full pattern guide
OpenTelemetry — end to end.
Every framework on this pattern shares the same platform-side spine, endpoints, and gotchas. The pattern guide covers them in full.
Read the OpenTelemetry guideNeed help landing Temporal (AI agents / durable execution)?
Talk to the integration team.
We help you land the integration end to end — including the parts that live in your environment.
Request integration help
Trustvice 360Declare the rules. Have every run checked.
Agents, evidence, governance, commerce and disclosure are all in Trustvice 360. Sign up free and open every suite from one dashboard.