Architecture note
Available for software engineering roles - backend systems, production reliability, cloud deployment, and AI-assisted workflows.
Local-first AI operations assistant prototype for small-business admin workflows, focused on email triage, quotes, records, and human-approved actions.
01
Small businesses lose time across quotes, invoices, Gmail follow-ups, job notes, payments, documents, and lead tracking.
Generic AI assistants are too disconnected from the operational workflow and too risky if they act without review.
02
A local-first assistant direction where Pip can draft, classify, and organize work while the operator approves outbound or destructive actions.
Backend workflow direction around FastAPI, local storage, Gmail/Drive-style integrations, and structured business records.
A product pivot toward offline-first ownership, privacy, and human-in-the-loop review instead of a generic cloud chatbot.
03
Email triage pipeline direction for classify, draft, approve, send/archive, and notify.
Local-first storage direction using SQLite first, with a self-hosted PostgreSQL path later.
AI fallback strategy across local Ollama, hosted model fallback, and Gemini.
Workflow modeling for leads, quotes, invoices, payments, job files, ABN/GST checks, and document search.
RAG/document intelligence direction for retrieving relevant business context before drafting.
04
Prototype / design pivot. This page avoids production, revenue, uptime, or usage claims until they are verified.
05
Primary language: Python
Technologies: Python, FastAPI, Flutter, SQLite, Gmail, Ollama, Gemini, RAG, Docker, Dart, HTML, JavaScript, Kotlin, CSS, C++, Shell, CMake, Batchfile, PowerShell, Swift, C, VBScript, Objective C, Uvicorn, Pydantic, Docker Compose, GitHub Actions
Topics: Not specified
Last updated: 2026-09-18T10:51:35Z
Stars: 0
Forks: 0
Status: Active
Architecture note
Visual notes
Welcome to the BackPocket OS documentation hub. This folder contains comprehensive guides for all features, workflows, and system architecture.
One-time setup, takes ~2 minutes:
git clone https://github.com/Sharv619/backpocket-mvp.git
cd backpocket-mvp
npm run setup
That installs MCP dependencies, creates the shared knowledge-bank table, and wires up the git hook that auto-logs every merge into main for audit (signed with your git author + commit SHA).
Then open OpenCode in the repo. Four MCP servers load automatically from .mcp.json:
| Server | Tools | Use for |
|---|---|---|
backpocket-leads | search / get / create leads | Lead intake work |
backpocket-quotes | create quote, templates, overdue list | Quoting + follow-ups |
backpocket-pipeline | pipeline summary, record payment | Ops / reporting |
backpocket-knowledge | save / search / list notes | Shared team knowledge bank |
Rule of thumb: anything worth referencing later — marketing copy, legal notes, research findings — drop it via the save_note tool in the knowledge bank, or just merge it into main and the post-merge hook captures it for you. Every entry is signed with your git identity so audits are trivial.
Full restructure rationale: docs/MCP_RESTRUCTURE_PLAN.md.
cd /home/lade/Hackathons/.git/backpocket-mvp
python3 -m uvicorn main:app --host 127.0.0.1 --port 8000
Visit: http://127.0.0.1:8000/static/index.html
.env and find SPREADSHEET_ID.env fileBackPocket uses three specialized AI agents that learn from your feedback:
| Twin | Purpose | Best For |
|---|---|---|
| Accountant | Financial & Tax | Invoices, GST, BAS, expense tracking |
| Auditor | Compliance & QA | Document review, verification, checks |
| Admin | Operations & Workflow | Email triage, scheduling, reminders |
Each twin:
BackPocket intelligently routes API calls to minimize costs:
See AI Models & Routing for details.
python3 import_real_emails.py
Fetches your actual Gmail messages and populates the dashboard.
Via the Dashboard:
Or via API:
curl -X POST http://127.0.0.1:8000/api/drive/sync-to-rag \
-H "Content-Type: application/json" \
-d '{"folder_id":"YOUR_FOLDER_ID","twin_type":"admin"}'
curl http://127.0.0.1:8000/api/blog/generate?title=My%20Story&theme=entrepreneurship
For detailed information on any topic, see the relevant documentation file in this folder.
Need help? Check TROUBLESHOOTING.md
Next field note
Open to software engineering roles across full-stack systems, platform and reliability work, workflow automation, and applied AI.
Write to Himanshu Lade →