Show HN: Pitot – OpenTelemetry in One Binary, with Parquet, DuckDB, and MCP Labstack released Pitot, a pre-release open-source observability tool that ingests OpenTelemetry traces, logs and metrics into a single binary, stores them locally as Parquet files and queries them with DuckDB, with no external storage services required. Pitot exposes an MCP server so external AI agents can use its typed query tools, alongside a built-in investigation agent that answers plain-language questions about telemetry when configured with an Anthropic or OpenAI API key. Labstack said the browser client, built-in agent, MCP tools, dashboards and alerts are preview capabilities and that the pre-release software changes without migration paths. Pitot pronounced PEE-toh . Observability your agents can operate. Send OpenTelemetry to one binary, then investigate with Pitot's built-in agent or connect your own over MCP. Current Pitot interface with deterministic offline sample telemetry. Pitot keeps OpenTelemetry traces, logs, and metrics in one binary and one data directory, with no external storage services to operate. Pitot is pre-release and changes without migration paths; the browser client, built-in agent, MCP tools, dashboards, and alerts are preview capabilities status https://pitot.dev/docs/reference/capabilities . Start with the documentation https://pitot.dev or run it below. - OTLP ingest over gRPC and HTTP, with local Parquet storage and DuckDB analytics. - Explore and PitotQL for querying telemetry without an AI provider. - An investigation agent that answers questions about your telemetry in plain language. - An MCP server for external agents using the same typed query tools. - Dashboards across traces, logs, and metrics, and alerts on service error rate, latency, throughput, and log volume. docker run --name pitot --restart unless-stopped -p 7520:7520 \ -v pitot-data:/var/lib/pitot/data \ -e PITOT AUTH CODE SECRET=$ openssl rand -hex 32 \ labstack/pitot:latest Open the one-time setup URL printed by the container and create the first administrator. Pitot displays the ingest token exactly once, unless PITOT INGEST TOKEN already set it; save it with your collector secrets. For later sign-in without SMTP, mint a 15-minute, single-use link against the running container's control database: docker exec pitot pitot login-link admin@example.com The UI, API, MCP, and both OTLP transports share port 7520 . See installation https://pitot.dev/docs/get-started/install for image defaults and bind-mount ownership, and first boot https://pitot.dev/docs/get-started/first-boot for setup and SMTP login. Install a checksum-verified release for Linux or macOS, amd64 or arm64: curl -fsSL https://raw.githubusercontent.com/labstack/pitot/main/scripts/install.sh | sh export PITOT AUTH CODE SECRET=$ openssl rand -hex 32 pitot Set PITOT VERSION to a release tag https://github.com/labstack/pitot/releases , such as v2026.11.0-alpha , to pin a release, and PITOT PREFIX to choose the installation directory. Native installs bind 127.0.0.1:7520 ; set PITOT ADDR=:7520 for remote access, then follow the same first-boot setup. A standard OTLP/HTTP exporter can use the saved ingest token: export OTEL EXPORTER OTLP PROTOCOL=http/protobuf export OTEL EXPORTER OTLP ENDPOINT=http://localhost:7520 export OTEL EXPORTER OTLP HEADERS="authorization=Bearer%20$INGEST TOKEN" For a Collector on the same private container network, the forwarding side is: exporters: otlp http/pitot: endpoint: http://pitot:7520 headers: Authorization: "Bearer ${env:INGEST TOKEN}" service: pipelines: traces: { receivers: otlp , exporters: otlp http/pitot } metrics: { receivers: otlp , exporters: otlp http/pitot } logs: { receivers: otlp , exporters: otlp http/pitot } Use an existing otlp receiver, set INGEST TOKEN , and replace pitot with the Collector's reachable private hostname. OTLP/gRPC uses localhost:7520 locally; see send telemetry https://pitot.dev/docs/get-started/send-telemetry for TLS and HTTP/2 setup. Select PITOT AI PROVIDER=anthropic and inject ANTHROPIC API KEY , or select PITOT AI PROVIDER=openai and inject OPENAI API KEY , then restart Pitot; the selected provider requires its key at startup. With no provider, chat is disabled and the other features still work. See AI settings https://pitot.dev/docs/reference/configuration/ai . Set PITOT PUBLIC URL to your stable, externally reachable HTTPS origin, then point a remote MCP client at that origin's /mcp endpoint. The client discovers and registers through OAuth; you authorize its scopes in the browser. Pitot serves MCP 2026-07-28 and, through the initialize handshake, 2025-11-25 and 2025-06-18 over Streamable HTTP. See connect over MCP https://pitot.dev/docs/guides/mcp for setup and permissions. | If you use | Where Pitot differs | |---|---| | Grafana with Loki, Tempo, and Mimir | That stack keeps a service and a query language per signal, plus object storage underneath. Pitot keeps one process, one data directory, and one typed contract across all three signals, at the cost of the horizontal scale those components are built for. | | SigNoz | Both are OTLP-native and self-hosted. SigNoz composes a collector, ClickHouse, and query services; Pitot compiles ingest, authoritative Parquet storage, indexed trace reads, DuckDB analytics, alerting, and the browser client into one binary. | | Jaeger | Jaeger covers traces and expects a storage backend you run separately. Pitot ingests traces, logs, and metrics into the same store, with nothing else to deploy. | | Prometheus with Grafana | Prometheus pulls metrics and is excellent at them. Pitot accepts pushed OTLP for all three signals and is built around investigating a specific incident rather than maintaining long-range metric series. | | Datadog , Honeycomb , Grafana Cloud | Those are managed services: someone else runs the storage, the scaling, and the upgrades, and your telemetry leaves your network to get there. Pitot is a binary you run, on data that stays on your disk. | | An OpenTelemetry Collector piped into ClickHouse | The same shape, assembled by hand: collector, database, dashboards, and the glue between them. Pitot is that assembly as one program, with an agent and an MCP server already wired to the same query contract. | Pitot is a single node. It has no clustering, no replication, and no object tier; a deployment that outgrows one machine's disk and CPU has outgrown Pitot. One process contains ingest, storage, query, alerts, the agent, MCP, and the React client. Browser and agent clients share a typed observability contract. Parquet holds telemetry, DuckDB query state is rebuildable, and SQLite holds transactional product state. See how storage works https://pitot.dev/docs/concepts/storage for durable ingest, indexed reads, and compaction while reads continue. Configuration is environment-only: built-in defaults followed by nonempty process environment values, validated before data files or listeners open. Settings are read once at startup; every change requires a restart. | Environment variable | Default | Purpose | |---|---|---| | PITOT ADDR | 127.0.0.1:7520 | UI, API, MCP, and both OTLP transports | | PITOT DATA DIR | ./data | Parquet, query state, and control SQLite | | PITOT AUTH MODE | local | Login link or SMTP, or oidc | | PITOT AUTH CODE SECRET | — | Required in local mode and for OIDC break-glass links, 32+ characters | | PITOT AI PROVIDER | — | Empty disables chat; anthropic or openai enables it | | ANTHROPIC API KEY | — | Required for Anthropic chat | | OPENAI API KEY | — | Required for OpenAI chat | | PITOT RETENTION DAYS | 30 | Telemetry retention window | | PITOT MCP ENABLED | true | Serve the MCP endpoint at /mcp | Every secret accepts