Show HN: Agentic Telemetry – Simple Observability Tool for Agentic System A developer released Agentic Telemetry, a minimal alpha observability collector for agentic systems that stores events in SQLite and uses only the Python standard library. The service runs via `python3 server.py`, listens on http://127.0.0.1:8000 by default, and exposes a POST /v1/events endpoint accepting one event or a JSON array of up to 100 events, with event_type and run_id required. The dashboard summarizes runs, agents, errors, activity over the last 24 hours, and activity by agent from the latest 1,000 events, refreshing every 10 seconds; authentication, retention policies, distributed deployment, and metric aggregation are not included. A lightweight telemetry collector for agentic systems. It stores events in SQLite and lets you inspect activity by run or agent. It uses only the Python standard library. python3 server.py By default, the service listens on http://127.0.0.1:8000 and creates telemetry.db in the current working directory. Configure TELEMETRY HOST , TELEMETRY PORT , or TELEMETRY DB to change these defaults. Open http://127.0.0.1:8000/ to view the dashboard. It summarizes runs, agents, errors, activity over the last 24 hours, and activity by agent from the latest 1,000 events. Filter the event stream by run, event type, or text. The dashboard refreshes every 10 seconds. curl -X POST http://127.0.0.1:8000/v1/events \ -H 'Content-Type: application/json' \ -d '{ "event type": "tool call.completed", "run id": "run-123", "agent id": "researcher", "parent agent id": "orchestrator", "task id": "task-7", "status": "success", "attributes": {"tool": "web search", "duration ms": 240} }' The endpoint accepts one event or a JSON array of up to 100 events. event type and run id are required. If omitted, id and timestamp are generated by the service. Event names are up to the sender; examples include agent.started , agent.handoff , tool call.completed , and llm.response . curl 'http://127.0.0.1:8000/v1/events?run id=run-123&limit=100' Combine any of these filters: run id , agent id , event type , task id , and status . The default limit is 100 and the maximum is 1,000. Use GET /health for a health check. An event can include id , timestamp , event type , run id , agent id , parent agent id , task id , status , and attributes . For agent handoffs, use the same run id and record the source agent or handoff details in parent agent id and attributes . This is a minimal alpha release. Authentication, retention policies, distributed deployment, and metric aggregation are not included. The service listens on the loopback address by default for local development.