Your coding agent already keeps an analytics dataset: one JSONL line per turn, per session. No need to load it anywhere. I pointed chDB at 1,676 session files (1.5 GB) to ask which tools our agents call most. 0.9s, in-process, no server. Bash won, 7x ahead of the next tool.

Sep 28, 2026 · 8:42 AM UTC

2
3
321
import chdb chdb.query(""" SELECT JSONExtractString(c,'name') tool, count() n FROM file('sessions/*.jsonl', JSONAsString) ARRAY JOIN JSONExtractArrayRaw(json,'message','content') AS c WHERE JSONExtractString(c,'type')='tool_use' GROUP BY tool ORDER BY n DESC""", "Markdown")
59
Sort replies: Relevant Recent Liked