// Use when the user says "check the tapes", "search tapes", "tapes search", or wants to look up past agent sessions. Starts tapes services if needed and queries the local SQLite store at ~/.tapes/.
Use when setting up Confluent Cloud for any project, creating clusters, topics, or API keys, or when Kafka publishing fails with "Unknown Topic Or Partition", SASL authentication errors, or silent publish failures. Also use when onboarding contributors to stream events to Confluent Cloud.
Run checks (lints, tests, etc.) using Dagger scafolding
| name | tapes |
| description | Use when the user says "check the tapes", "search tapes", "tapes search", or wants to look up past agent sessions. Starts tapes services if needed and queries the local SQLite store at ~/.tapes/. |
Query local tapes session data. The tapes SQLite database lives at ~/.tapes/ and contains recorded LLM agent sessions across all projects.
Before searching, the tapes API server must be running. Start it in the background if it isn't already:
# Check if already running
curl -sf http://localhost:8081/health > /dev/null 2>&1
# If not running, start it in the background pointing at the global sqlite db
tapes serve api --sqlite ~/.tapes/tapes.sqlite &
Use the Bash tool with run_in_background for the serve command so it doesn't block the conversation.
Run searches with the tapes CLI:
tapes search "<query>" --api-target http://localhost:8081 --top 5
--top based on how broad or narrow the user's question is--quiet when piping results to other commands like tapes skill generatetapes serve api --sqlite ~/.tapes/tapes.sqlite in the background