Zero-SDK Run Correlation
Without adding Langfuse or OpenTelemetry imports to your agent code, Zelkor automatically joins the agent run, gateway model calls, NeMo guardrail checks, and MCP tool calls under one trace.
Zelkor links agent runs, AI gateway calls, guardrail checks, and MCP tool executions into a single trace inside self-hosted Langfuse, while keeping prompts and keys out of default logs.
Standard pod logs scatter a single agent run across multiple services, dump sensitive customer prompts or bearer tokens into cluster log pipelines, and leave gaps whenever a developer forgets to wrap a new graph node in a tracing library.
Without adding Langfuse or OpenTelemetry imports to your agent code, Zelkor automatically joins the agent run, gateway model calls, NeMo guardrail checks, and MCP tool calls under one trace.
Default logs and trace metadata do not record raw prompt bodies, bearer tokens, or upstream API keys, keeping sensitive data out of cluster log collectors.
Self-hosted Langfuse comes pre-configured with automated checks that score runs for tool call budgets, repeated tool loops, sandbox cleanliness, guardrail refusals, and tenant attribution.
All trace data stays inside your cluster on self-hosted Langfuse, ClickHouse, Postgres, and S3-compatible storage, alongside an optional Prometheus ServiceMonitor for cluster monitoring.
platform:
telemetry:
level: INFO
langfuse:
enabled: true
observability:
serviceMonitor:
enabled: true