Nous
Nous is an open-source context graph for agentic GTM (go-to-market) teams that centralizes identity-resolved people and company data from multiple GTM tools so agents can read a single, source-traced account context in one call. It is available as a hosted service and as a self-hostable stack.
Nous is ai agents software teams evaluate for ai agents. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Used in These Packs
Quick Overview
Best for: AI Agents
What it does
AI Agents software for decision-makers comparing workflow fit and alternatives.
Best fit
AI Agents
Pricing snapshot
Contact for pricing
Next step
Compare Nous with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Nous
Nous is an open-source context graph designed for agentic GTM teams to centralize data from CRM, inbox, calendar, LinkedIn, enrichment, and signals into one identity-resolved account. It resolves emails, profiles, and duplicates into canonical person and company records, attaches immutable observations as evidence, and derives claims with confidence and freshness so agents can act from trusted context. Agents request the whole account context in a single call (token-budgeted and agent-shaped), avoiding repeated stitching across multiple tools. Nous is available as a hosted cloud offering and as a self-hostable stack requiring a Supabase project and an Anthropic API key.
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. - NousC/opennous
Own this listing?
Claim this page to add pricing, features, screenshots, and verified owner details.
Claim this listingKey Features
Identity resolution and canonical entities
Observations from multiple GTM tools resolve to entities so each person or company has one canonical record, deduplicating emails/profiles across systems.
Immutable observations and source-traced claims
Every signal is stored as an observation (immutable evidence). Claims are derived from observations and include confidence and freshness along with their source.
Single-call account context (get_context)
A token-budgeted, agent-shaped get_context endpoint returns the full account summary, claims, stakeholders, timeline, predictions, and meta information in one request.
Account and query endpoints
API endpoints include get_account (full record for a person or company) and query (filter activity across people and accounts with structured scope and semantic ranking).
MCP integration and agent-first design
Designed to be operated by agents via the Model Context Protocol (MCP); README shows commands to add Nous to MCP hosts and examples for Claude and other MCPs.
Self-hostable stack
Full self-host instructions to run the API, workers, MCP server, frontend, Redis, and Caddy via Docker Compose; requires Supabase and an Anthropic API key.
ICP scoring and predictions
Derives ICP fit scores and predictions (example: icp_fit prediction with confidence) from the graph and observations.
Pricing
Claim this listing to add current pricing tiers.
Use Cases
Agent-enabled account review
Agents call get_context for a focused account_review intent to receive a token-budgeted summary, claims, timeline events, and ICP fit to inform next actions.
Sales and RevOps workflows
Unify CRM, email, calendar, enrichment, and signal data into one account to enable consistent decisions across SDRs, AEs, and RevOps agents.
Signal-driven targeting and query
Use the query endpoint to filter accounts by recent interactions or signals (for example, 'accounts that replied positively then went quiet') and return ranked entities for outreach.
Self-hosted, privacy-controlled deployments
Organizations can self-host Nous, run the stack on their infrastructure with Supabase and Anthropic, and control data residency and sign-up policies.
Integrations
MCP (Model Context Protocol)
Integrate with agents and MCP hosts โ examples provided for Claude MCP, Codex, Cursor, and commands to add Nous as an MCP server.
Anthropic / Claude
Uses Anthropic (Claude) for AI/LLM functionality; self-host requires an ANTHROPIC_API_KEY.
Supabase (Postgres + pgvector)
Self-host deployments require a Supabase project for Postgres, auth, and vector storage (schema included).
CRM, Gmail, LinkedIn, note-takers, enrichment, signal sources
Supported connectors and ingestion sources include CRM syncs, Gmail, LinkedIn (via official OAuth/webhooks), note-takers (e.g., Fireflies example), and enrichment sources; these feed observations into the graph.
Benefits
Limitations
Frequently Asked Questions
Claim this listing to publish FAQs.
Getting Started
- 1 Connect Nous to your agent via MCP (example: claude mcp add nous -- npx -y @opennous/mcp or use npx @opennous/cli login).
- 2 For self-host: clone the repository, copy the example env (cp nous.env.example nous.env) and fill in APP_DOMAIN/API_DOMAIN/MCP_DOMAIN, Supabase URL and keys, and ANTHROPIC_API_KEY; generate ENCRYPTION_KEY.
- 3 Create the Supabase database (run supabase/schema.sql), then launch the stack with Docker Compose (docker compose --env-file nous.env up -d --build).
Support
Docs
Repository README and self-host guides (see the GitHub repository for docs and walkthroughs).
GitHub issues
Report bugs or request features via the repository Issues page.
Community / Discord
Project resources list includes a Discord and community linksโsee repository resources and SLACK.md/SLACK instructions for joining community channels.
Contributing & Security
Contributing Guide and SECURITY.md are in the repository for contribution and security reporting guidance.
API
Repository README with API examples (get_context, get_account, query) at https://github.com/NousC/opennous
Compare Nous with similar tools
See how it stacks up against alternatives
Related Tools
View all 410 โ
Oodle.ai
Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.
Sentinel
Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.
Superserve
Superserve is an open-source, self-hostable sandbox platform for long-running AI agents that provides durable Firecracker microVMs, pausing/resuming sessions, and programmatic control via an SDK and API.
AgentsProof
AgentsProof is an SDK and service that captures agent traces, grades runs against custom rules and approved test cases (Goldens), and produces shareable proof reports to verify and monitor AI agent behavior.
Vektorgeist- A platform for AI operators and their agent's
VektorGeist is a platform for AI operators and their autonomous agents โ a central hub to publish agent profiles, showcase projects, trade software and digital assets, find and post jobs, and participate in a community social layer (VG Social). It provides tooling for verifiable agent identities, trust tiers, marketplaces, group workspaces and an operator dashboard.
ClaudeThings
ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code โ delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.
Premium Alternatives
OTP Inspired actor supervisor based full stack templates
ShipStacks provides production-grade, OTP-inspired full-stack SaaS templates that include supervisors/actor patterns, auth, payments, uploads, AI chat and agent playbooks, and Docker-ready deployment in multiple languages and frameworks.
ClaudeThings
ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code โ delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.
qomplement
qomplement is an Agentic AI-driven ERP built for supply chain and operations teams that automates tasks across procurement, inventory, freight, finance, and planning to reduce manual work and scale operations without adding headcount.