For AI-native teams

Build your GTM
the way you build your product.
icon

Reach the buyer graph in code: SDK, MCP, REST, and CLI. Embed it in your product, run agents over your own data.

AI-native teams do not buy seven GTM tools and stitch them together. They build on one free data layer: 700M contacts, 100M companies, 30B intent signals, addressable by npm install, an MCP server, REST, and the CLI. Stand up data, site, campaigns, and CRM in one swoop. Pay for compute, not seats.

25+ SDK modules 150+ REST endpoints 100+ MCP tools 143 CLI commands
gtm.ts free data layer
$ npm install @graph8/js
import { g8 } from '@graph8/js';

g8.init({ apiKey: 'YOUR_KEY' });

// 700M contacts, free within the rps cap
const c = await g8.enrich.person({
  email: '[email protected]'
});

c.title;    // "VP Engineering"
c.company;  // "Acme Corp"
The problem

You wire up seven GTM SaaS tools, then pay for each one twice.

Enrichment here, sequencer there, booking somewhere else. Per-seat plus per-lookup taxes, and the data you most want to reach lives behind a UI you cannot call from code.

Stitch seven separate contracts
Per-seat plus per-lookup taxes
Data you cannot reach in code
A new integration for every tool
Glue scripts you maintain forever
The graph8 promise

One buyer graph, addressable in code.

The same free data that powers the app, reachable by SDK, MCP, REST, and CLI. Build it into your product, run agents over it, and pay only when graph8 does work for you.

One free data layer, four interfaces
Pay for compute, not seats
Reach every record in code
Embed graph8 in your own product
Stand up the whole GTM in one swoop
One platform, four interfaces

Reach the buyer graph from wherever you build.

Same auth, same data, same credits. SDK, MCP, REST, and CLI are all first-class. Pick the surface that fits your codebase, or use all four.

25+ modules
SDK Embed in your app or agent npm install @graph8/js
100+ tools
MCP Agents in Claude, Cursor, ChatGPT https://be.graph8.com/mcp/
150+ endpoints
REST Any language, OpenAPI 3.1 POST /api/v1/lookup/person
143 commands
CLI Scripts, CI/CD, terminal g8 lookup person --email
Build on the free data layer

700M contacts, free, reachable four ways.

graph8-owned data is the foundation: 700M contacts, 100M companies, 30B intent signals, plus website-visitor identification, free on every plan within the rps cap. Query it from npm, REST, an MCP tool, or the CLI. Same record, same result, your choice of surface.

  • 700M contacts, 100M companies, 30B signals
  • Free within the rps cap on every plan
  • One record, four ways to reach it
  • You pay only when graph8 executes
SDK TypeScript
await g8.enrich.person({ email })
MCP Claude / Cursor
Tool: g8_lookup_person
REST cURL
POST /api/v1/lookup/person
CLI terminal
g8 lookup person --email
.cursor/mcp.json
{
  "mcpServers": {
    "graph8": {
      "url": "https://be.graph8.com/mcp/"
    }
  }
}

Paste, restart, sign in with OAuth. Your agent now has 100+ graph8 tools.

Claude.ai

URL paste

Claude Code

claude mcp add

Cursor

mcp.json

ChatGPT

URL paste

Windsurf

mcp_config

VS Code

settings.json
Your agent gets the full toolbox

Give your AI agent 100+ tools over MCP, not what a connector exposes.

The MCP server gives an agent full first-party write access: CRM, prospecting, enrichment, sequences, campaigns, workflows, voice, and more. OAuth handles sign-in, so there are no keys to juggle. It works in Claude, Cursor, ChatGPT, and the agent frameworks you already use.

  • 100+ tools, full first-party write access
  • OAuth sign-in, no keys to manage
  • Works in Claude, Cursor, ChatGPT, and more
  • The same data the SDK and REST API see
Embed graph8 in your product

One line each. Your UI, our data and widgets underneath.

graph8 is infrastructure you build on. Identify the account on the page, drop in an AI copilot, book inside your app, and skip form fields you already know. Your flow stays yours; the data layer does the heavy lifting.

g8.visitors.identify()

Identify the visitor

IP-to-company in the browser. Personalize the page for the account before they type a thing.

g8.copilot.open()

Embed an AI copilot

An assistant that knows your knowledge base, answers questions, and books demos inside your UI.

g8.calendar.show()

Book inside your app

Native scheduling, no redirect to a third-party page. Slot routing is yours to configure.

g8.forms.lookup(email)

Skip fields you know

Progressive forms ask for two fields, not six. graph8 fills the rest from first-party data.

PricingPage.tsx
// Personalize before the visitor types anything
const v = await g8.visitors.identify();

if (v.company?.segment === 'enterprise') {
  showEnterprisePlan(v.company.name);
  g8.copilot.open({ greeting: `Hi ${v.company.name}` });
}
Run agents over your own data

Point named agents at your buyer graph and let them work.

SDR, Deal, CSM, and Content agents run over the data you already own. Every action is governed by your rules and logged to revenue memory, so the next agent and the next rep both see what happened. No black box, no export.

  • Agents act on your own buyer graph
  • Governed by your rules and limits
  • Every action logged to revenue memory
  • The next agent and rep see the full trail
Agents on your data
Running
SDR agent Builds lists, sends, books meetings
logged
Deal agent Moves stages, drafts the next step
logged
CSM agent Watches health, flags churn risk
logged
Content agent Drafts copy and pages on your context
logged
Every action written to revenue memory, governed by your rules.
One swoop

Stand up data, site, campaigns, and CRM together.

Instead of buying and wiring seven tools across six months, you stand up the whole GTM at once: the data layer, the site, the campaigns, and the CRM, all reading and writing one buyer graph.

Data 700M contacts, 100M companies, 30B signals
Site Landing pages, forms, visitor ID embedded
Campaigns Sequences, dialer, broadcasts from code
CRM Deals, pipelines, two-way sync, revenue memory
How it connects

One free data layer feeds your product, your agents, and your GTM.

Everything reads and writes the same buyer graph. The data you embed in your product, the agents you run over it, and the campaigns you launch from it all share one source of truth.

Free data layer 700M contacts · 100M companies · 30B signals
Your product visitor ID, copilot, booking, forms g8.visitors.identify()
Your agents SDR, Deal, CSM, Content g8_lookup_person
Your GTM campaigns, dialer, deals, sync g8.campaigns.create()
Every write lands back on the same buyer graph, in revenue memory.
Built on a decade of real outbound

graph8 comes out of CIENCE: ten years of running real B2B outbound at scale. The data and the playbooks are trained on real campaign outcomes, not a brand-new guess at what works. The same engine, now an AI-native platform you build on in code.

25+ SDK modules
150+ REST endpoints
100+ MCP tools
143 CLI commands

Build your GTM the way you build your product.

Start on the free data layer today. Reach it by SDK, MCP, REST, or CLI, embed it in your product, and pay for compute, not seats.

graph8 Execution Plan

$499 /month

7-day free trial. No credit card. Cancel anytime.

All B2B data, intent, and visitors, free Search, segment, identify. App, MCP, or CLI. No credits charged for browsing.
You only pay for execution

75,000 execution credits / month included

Sending, dialer, AI voice, AI workflows

Meeting routing and booking

Unlimited users, no seat fees

Pay As You Go Free data, intent, and visitors included. Pay only when execution runs.
$0.05 /credit
Start with 1,000 Free Credits

Start free in 3 minutes. No credit card required.

Free intelligence layer Free in every plan

700M+ contacts and 100M+ companies

Search by title, seniority, industry, and tech stack with real-time filters.

Intent + visitor signals

See which companies research your keywords and visit your site.

Unlimited users

Invite your whole team: sales, marketing, RevOps, founders, agencies. No per-seat fees.

App, MCP server, and CLI

Same free data through the app, the MCP server (Claude, Cursor, ChatGPT), and the CLI.

Usage-based execution Metered

Full GTM platform

Sequencer, dialer, inbox, campaigns, CRM, and AI agents in one system.

AI voice agents

Clone any rep's voice for inbound and outbound calls with live booking.

5-channel sequencer

Email, phone, LinkedIn, SMS, and WhatsApp in automated sequences.

AE cockpit

AI-prioritized deal actions with meeting prep and risk alerts.

Waterfall enrichment

Pay only when a provider returns a match. Bring your own vendors too.

Always-on principles

No seat licenses

Invite everyone. Pricing never scales with headcount.

Every feature unlocked

No tiers gating voice, enrichment, sequencer, or campaigns.

No contracts

Month-to-month, cancel anytime, credits never expire.

Fair-use guardrails

Free data is designed for real GTM execution, not bulk export or scraping.

graph8

Ready to Replace Your Sales Stack?

One platform. $499/month. Unlimited everything. Battle-tested and launching campaigns in 3 minutes.

Get Started
GTM Platform InterfaceVoice AI Interface