GitHub Repository

The context graph for agentic GTM teams. Unify the data scattered across your GTM tools into one identity-resolved account any agent reads in a single call.

4 starsTypeScript

Nous – give GTM agents one context graph across your tools

Name: Nous – give GTM agents one context graph across your tools
Availability: InStock
Author: sethiaakash04

by sethiaakash04·Jul 16, 2026·9 points·9 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainSolve My ProblemZero to One

Replaces six tool calls with one graph query by deriving confidence-weighted claims from immutable observations.

Strengths

•Observation-entity-claim architecture ensures traceability and lets you replay history to rebuild state.
•Solves the specific 'six tool calls per prospect' friction that breaks current agentic workflows.
•Native MCP server integration means agents can plug in without custom glue code.

Weaknesses

•Early stage with only four stars; real-world reliability of the identity resolution is unproven.
•GTM-specific schema may limit utility for non-sales use cases like support or product agents.

Post Description

We built this because deploying more agents did not make our GTM better, it made it worse. Every agent started from scratch each session and took six tool calls for the same prospect across CRM, inbox, and notetaker, often with conflicting results. Since nothing carried over between sessions, agents never became more reliable over time.

Nous is a context layer beneath your agents that turns each touchpoint into a structured observation linked to the right person and company. It derives claims, which are beliefs about a fact with their confidence and freshness. The graph runs on your own data, improves with each agent outcome, allowing one agent to read the whole account in a single call instead of using six tools.