You have a SQLite file full of answers, but opening a SQL client and remembering joins every time is friction. This agent lets you ask in plain English instead.
sonnet2 daysSQLiteLangChainOpenAIPython
Claude
82ROI
73Scale
$1.5k87Saved
ROI for
README.md
Why this subagent
You have a SQLite file full of answers, but opening a SQL client and remembering joins every time is friction. This agent lets you ask in plain English instead.
Everything runs locally; the database never leaves your machine, which matters for private or regulated data. It reads the schema, writes the query, runs it in-process, and reports the rows back. Nothing is sent to an external database service.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Convert each question into a SQL query scoped to the columns present in the file.
pending
Execute the query inside the same process so no data leaves the machine.
pending
Summarize the result rows and keep the running query history for the session.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Chat over a local SQLite file, generating and running read-only SQL while keeping all data on the machine.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.