Pirecall
Description
🔄️ Sync pi.dev agent sessions to SQLite for analytics, uses node:sqlite
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
pirecall
[](https://viteplus.dev) [](https://vitest.dev)
Sync [pi.dev](https://pi.dev) agent sessions to SQLite for analytics. Query your session history, token usage, tool calls, cost, and model switches.
Quick Start
Use pirecall inline in pi sessions. Tell the agent:
"run npx pirecall sync then show me my top 5 projects by token usage"
"use npx pirecall search to find sessions where we discussed database migrations"
"run npx pirecall stats and tell me how much I've spent this week"
The agent runs the command, gets structured output, and can answer follow-up questions about your session history.
Resumable session index
Pirecall remains an archive: deleting a Pi JSONL session does not delete its history from the database. Each sync additionally records source-file metadata and marks missing sources as unavailable. Resume integrations query only live sources:
pirecall resumable --scope all --limit 100 --json
pirecall resumable --scope project --cwd "$PWD" --query auth --json
The command returns a versioned object containing `schema_version`, `capabilities`, and compact `sessions`. Node integrations can use the same contract without relying on internal SQLite tables:
import { list_resumable_sessions } from 'pirecall/resumable';
const result = await list_resumable_sessions({
scope: 'project',
cwd: process.cwd(),
query: 'auth',
limit: 50,
});
Results contain the absolute JSONL `path`; integrations should verify it still exists immediately before asking Pi to switch sessions. Existing databases are migrated additively when opened. Run `pirecall sync --json` once after upgrading to stream and backfill session names and source metadata. The backfill is marked complete per file, so later syncs remain incremental.
Related Skills
mcp-server-postgres
Read-only PostgreSQL database access.
Data mcp-server-sqlite
SQLite database interaction and querying.
Data mcp-server-google-maps
Google Maps integration for location data.
Data Bitbucket Data Center
---
Data Csv Data Summarizer
Automatically analyze CSV files and generate comprehensive insights with visualizations
Data OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Data