Skip to content
mcpd
no daemon

Blog

Articles on tracing, testing and running AI agents with mcpd. RSS feed

  1. Open source agent observability platform: No SDK

    What is an open source agent observability platform? It records each run as a tree of steps with prompt, completion and cost. Start with stock OpenTelemetry.

    agent observability · opentelemetry · open source · llm cost tracking · self-hosting · agent evaluation

  2. LLM cost per project: Formula and run-level checks

    How do you calculate LLM cost per project? Price each call from its usage fields, sum the runs, and compare with traces. Learn to cap spend with a monitor.

    llm cost · token pricing · prompt caching · agent observability · cost monitoring · opentelemetry

  3. Self hosted LLM tracing on Postgres: One daemon

    How do you run self hosted LLM tracing on Postgres? Run one binary, set its storage to Postgres and send OpenTelemetry spans. Learn the setup and start free.

    llm tracing · postgres · opentelemetry · self hosting · observability · data retention

  4. Single binary agent monitoring: Find the bad run

    What is single binary agent monitoring? One executable with built-in storage and UI that traces every model and tool call. Learn setup, monitors and limits.

    agent monitoring · opentelemetry · sqlite · llm observability · cost monitoring

  5. LLM audit log: Record, redact and retain agent runs

    What goes in an LLM audit log? One trace per run holds every model call, tool call and its cost. Learn to record, redact and retain it with OpenTelemetry.

    llm audit log · opentelemetry · ai agents · data retention · redaction · access control

  6. Agent workflow state tracking: Observe any agent

    What is agent workflow state tracking? Record the cursor, retries, waits and payloads as OpenTelemetry traces. Learn to trace a stuck run in any framework.

    agent observability · opentelemetry · durable workflows · ai agents · tracing

  7. LLM evaluation dataset: Build one from real runs

    What goes into an LLM evaluation dataset? Frozen cases from your own production runs, each with input, expected behaviour and metadata. Learn to build one.

    llm evaluation · evaluation dataset · ai agents · llm-as-judge · regression testing · observability

  8. Start tracing AI agents free: Setup in 5 minutes

    How do you start tracing AI agents free? Set two OpenTelemetry variables and a project key, run your agent, and see each prompt, answer and cost. Start now.

    ai agents · tracing · opentelemetry · observability · llm cost