How much does Nous cost?

Nous is $199 a month on the API plan, which includes a 7-day free trial. If you would rather we run the entire revenue layer for you, the Headless Revenue Engine is priced per team. The core is also open source, so you can self-host it for free.

Do I have to replace my CRM?

No. Nous sits across your CRM and everything around it, so you keep working where you already work. It unifies every signal into one resolved record and writes clean fields back to your CRM instead of replacing it.

Which tools does Nous connect to?

Your CRM like Salesforce, HubSpot, or Attio, plus email and calendar, LinkedIn, meeting recorders like Fireflies and Fathom, Slack, and your outbound tools. If it touches a deal, Nous pulls it into one record.

Is my data safe, and do you train on it?

Yes, and no. Your data is encrypted in transit and at rest on SOC 2 infrastructure, with authentication handled by Clerk and payments by Stripe. We never sell your data or train shared models on it, and because the core is open source you can self-host it on your own keys.

Can I try it before I commit?

Yes. The API plan comes with a 7-day free trial, and the open-source core lets you run Nous on your own infrastructure for free, on your own model key. You can export your data at any time.

The GTM context graph

Access is not context

Acme Corp

Acme Inc.

acme.com

ACME

Acme Corporation

Claude reaches every tool, but sees the same account as five different records. It has the data, and no idea which identity is real.

Salesforce

HubSpot

Gmail

Fireflies

Slack

Acme Incone record

Nous resolves every record into one identity, current and complete, so Claude works from what is actually true about the account.

Inside the context graph

Unified record

Account intelligence

Every person, conversation, and touchpoint resolved into one live account record, so you see the full buying committee and exactly where each deal stands.

Identity

Identity resolution

Every person, company, and touchpoint resolved into one record across every tool you run, so the same account is never four different rows.

Definitions

Your definitions

Your ICP, your stages, and what qualified means to you, encoded once and shared by every teammate and every agent.

Currency

Freshness on every fact

Every fact carries its freshness, so your team and your agents never quietly act on data that has gone stale.

Memory

Full account memory

The complete history of every account, so no conversation and no agent ever starts from a blank slate.

Data ingestion

Every system you run is mapped into one shared schema. Records, people, events, and conversations resolve to the same accounts and link to each other, so the graph reflects how your business actually connects.

Governance and permissions

Scoped to every user

An agent sees exactly what that person is authorised to see, and nothing they are not. No colleague's inbox, quota, or paystub.

Governed before ingestion

A multi-layer rule engine decides whether each piece of raw data is even ingested, by role and access.

Object, record, and field level

One permission model across every system, reduced to simple primitives you can actually reason about.

Checked and logged

Every fact an agent reads passes through the governance layer, and every access is written to an audit trail.

Read the deep dive on trusting AI with revenue data

How to use the context graph

Inside Nous

Revenue agents inside Nous

Specialised agents that run on your context graph. Ask anything about an account, or run a skill, right where the work is.

Via MCP

Connect via MCP

Connect Claude, Codex, Cursor, or any agent to the context graph over MCP, and it reads the same truth your team does.

Read the MCP docs

Run Nous inside your terminal

Nous plugs straight into Claude Code and Codex, so the agents your team already runs read the same revenue layer you do.

npx @opennous/cli init

FAQ

What is the context graph?

One live, resolved record of every account, built from every tool you run. It carries identity, your definitions, the freshness of each fact, and the full history, so people and agents work from the same truth.

How is it different from a CRM?

A CRM is your system of record, filled in by people. The context graph sits across your CRM and everything around it, resolves it into one current picture, and writes clean fields back. The CRM stays the system of record; the graph is what agents act on.

How does an agent access it?

Over one API and MCP. Your own agents in Claude Code, Codex, or Cursor call the graph directly and get a complete, current account back, scoped to your permissions.

Isn't MCP already enough?

MCP gives an agent access to your tools. It does not resolve identity, encode your definitions, track freshness, or hold memory. The graph does those four jobs, which is what turns raw access into context an agent can trust.

Is my data secure?

Yes. Data is encrypted in transit and at rest on SOC 2 infrastructure, access is scoped to your permissions, and your data is never used to train shared models. See the security page.

How long does it take to set up?

About fifteen minutes. Connect your tools and Nous reads your existing history and builds the graph, so you start with the deals already in flight instead of an empty system.

The context graph beneath the revenue layer