Open Source Project2026

RevOps AI

A Revenue Operations platform that uses Notion as your CRM database and Gemini 2.5 Flash as your AI sales agent. Built on the Model Context Protocol — the AI autonomously decides which Notion operations to run, no hardcoded queries.

RevOps AI — AI-powered sales pipeline built on Notion with Gemini MCP

Your team already lives in Notion. Your CRM doesn't.

Salesforce, HubSpot, and Pipedrive lock your contacts, deals, and activity history behind proprietary walls. Meanwhile, every proposal, meeting note, and follow-up thread lives in Notion. You maintain two systems, pay twice, and trust neither.

RevOps AI eliminates the gap. Your data stays in Notion — where you own it, where your team can edit it directly, and where it connects to everything else in your workspace. The AI is a reasoning layer on top, not a warden around a proprietary database.

How MCP makes autonomous AI practical

The Notion MCP server exposes all 22 Notion operations as a standardized tool catalog. The mcpToTool() function from @google/genai maps that catalog directly to Gemini function declarations at runtime — so the AI decides which tools to call based on the user's natural language request, with no hardcoded dispatch logic.

// The entire AI-to-Notion bridge
const mcp = new MCPClient({ url: process.env.MCP_SERVER_URL });
const tools = await mcp.getTools();// 22 Notion ops, auto-mapped to Gemini
01

User asks in plain English

"Brief me on the Acme deal before my call tomorrow"

02

Gemini chains MCP calls

Searches deal → queries activities → retrieves contact → reads company — four operations, one response

03

Result syncs to Notion

Lead scores, activity records, and field updates write back to your Notion databases automatically

Everything a revenue team needs

Revenue Dashboard

Pipeline metrics at a glance — total value, win rate, deal stage breakdown, and recent team activity. All data flows from Notion through MCP in real-time.

Visual Deal Pipeline

Drag-and-drop Kanban across six stages (Lead → Closed Won). Every move syncs to your Notion database instantly via an MCP update call.

AI Lead Scoring

One-click analysis evaluates role seniority, company size, and engagement history. Returns a 0–100 score with written reasoning, persisted back to Notion.

AI Sales Team Manager

Natural language interface to your revenue data. Ask for pipeline health, request pre-call briefings, or create follow-up activities — the AI chains multiple Notion operations autonomously.

Contacts & Companies

Full contact and organization management linked to deals and activities through Notion relation fields. The AI traverses these relations when building briefings.

AI Email Drafting

Open any deal and generate a context-aware sales email in one click. The AI reads deal stage, contact history, and company profile before writing.

Four databases. One workspace.

Contacts

Name, Email, Company, Role, Lead Score, Source

Deals

Name, Contact (relation), Stage, Value, Close Date, Priority

Activities

Type, Date, Deal (relation), Summary, Raw Notes

Companies

Name, Industry, Size, Website

Built on modern, open tooling

FrameworkNext.js 15 App Router, TypeScript strict
UITailwind CSS v4, shadcn/ui, Lucide icons
AIGoogle Gemini 2.5 Flash via @google/genai
DataNotion (4 databases) via MCP protocol
MCP@notionhq/notion-mcp-server (HTTP mode)
Drag & Drop@dnd-kit/core + @dnd-kit/sortable
LintingBiome

Running in 15 minutes

You need a Notion integration token, a Gemini API key (free tier works), and four Notion databases created from the schema in the README.

$git clone https://github.com/pooyagolchian/ai-sales-crm.git
$cd ai-sales-crm && pnpm install
$cp .env.example .env.local
$# Add GEMINI_API_KEY and NOTION_TOKEN
$pnpm dev:all

Need a custom AI system for your sales team?

I build production AI workflows, CRM integrations, and autonomous agents for teams in Dubai and worldwide.

Get practical AI and engineering playbooks

Weekly field notes on private AI, automation, and high-performance Next.js builds. Each edition is concise, implementation-ready, and tested in production work.

Open full subscription page

Get the latest insights on AI and full-stack development.