7ca365903521107c66ab74bf2a9d51bb4c833ff7
- 5 TON 10KW, SEER 15, condenser WSA5S60, air handler WCHL60 - Final investment 200, 1yr labor / 10yr parts/compressor/coils - 770 Emerald Ave (verify vs 220), not yet signed - Photo saved
Local LLM Second Brain 🧠
Architecture: Telegram -> n8n -> Pi Agent -> Local Markdown
How it Works
- Messages are sent via Telegram.
- n8n catches the webhook, formats the payload, and sends it to Pi Agent via CLI.
- Pi Agent reads the core system files (
agent.md,rules.md,soul.md) and the user's message. - Pi Agent interacts with the local file system (PARA method) to read/write memories.
- Every morning, a cron job/n8n schedule summarizes the previous day's session into
/journalsand clears the short-term memory.
Getting Started
To initialize the brain, send this exact message to the bot via Telegram:
@agent execute bootstrap
Description
Languages
HTML
91.9%
Python
8.1%