CRMy

What You Can Build

Use CRMy when you want agents that can:

• brief themselves on an account, contact, opportunity, or use case before acting
• turn meeting transcripts and emails into actionable Signals
• combine evidence across sources before creating Memory
• identify risks, blockers, next steps, stakeholder roles, and buying-process gaps
• draft customer follow-ups from Memory and recent context
• route sensitive decisions to a human with evidence attached
• prepare CRM or warehouse updates without bypassing policy
• operate with member, manager, and admin visibility boundaries
• expose the same capabilities through Web UI, REST, CLI, and MCP

Quickstart

You need Node.js 20+ and PostgreSQL. For local development, pgvector is recommended but not required.

Start Postgres:

docker run --name crmy-postgres \
  -e POSTGRES_USER=postgres \
  -e POSTGRES_PASSWORD=postgres \
  -e POSTGRES_DB=crmy \
  -p 5432:5432 \
  -d pgvector/pgvector:pg16

Initialize CRMy:

export DATABASE_URL=postgresql://postgres:postgres@localhost:5432/crmy
export CRMY_ADMIN_EMAIL=admin@example.com
export CRMY_ADMIN_PASSWORD=change-me-please-123

npx -y @crmy/cli init --yes
npx -y @crmy/cli doctor
npx -y @crmy/cli server

Open:

Web UI   http://localhost:3000/app
REST     http://localhost:3000/api/v1
MCP      http://localhost:3000/mcp
Health   http://localhost:3000/health

What init --yes does:

1. Connects to PostgreSQL.
2. Creates the local database when needed.
3. Runs migrations.
4. Creates the first owner account.
5. Writes local CLI and MCP config.
6. Seeds demo data so the examples below work immediately.

Prefer interactive setup?

npx -y @crmy/cli init

Prefer a global install?

npm install -g @crmy/cli
crmy init
crmy doctor
crmy server

Try the Demo

The seeded demo shows the full source-to-action loop:

npx -y @crmy/cli briefing "account:Northstar Labs"
npx -y @crmy/cli context raw-sources
npx -y @crmy/cli context signals
npx -y @crmy/cli context lineage --subject "account:Northstar Labs"
npx -y @crmy/cli hitl list
npx -y @crmy/cli agent-smoke

You should see:

1. Raw Context from customer conversations.
2. Signals about stakeholders, buying process, risk, security, and next steps.
3. Confirmed Memory available in briefings.
4. A Handoff showing how uncertain or sensitive action routes to human review.
5. Lineage showing how source material became Signal, Memory, review, or writeback.

Demo users:

Admin   sample.admin@crmy.local / crmy-demo-123
Manager sample.manager@crmy.local / crmy-demo-123
Rep     sample.rep@crmy.local / crmy-demo-123
Peer    sample.peer@crmy.local / crmy-demo-123

The CLI accepts friendly record references, so you usually do not need IDs:

account:Northstar Labs
contact:Maya Patel
opportunity:Agent Context Rollout
use_case:Production Rollout

IDs are still used for system artifacts such as Handoffs, raw-source receipts, sync runs, and writeback requests.

Environment Essentials

See .env.example for the full reference.

CLI Essentials

crmy init                         # setup wizard
crmy doctor                       # local health check
crmy server                       # start API, Web UI, REST, and MCP HTTP
crmy seed-demo --reset            # reset and seed demo data

crmy briefing "account:Northstar Labs"
crmy context ingest --file call.txt
crmy context signals
crmy context lineage --subject "account:Northstar Labs"
crmy activities meetings
crmy emails messages
crmy hitl list
crmy systems list
crmy workflows list
crmy sequences list

The CLI is curated for setup, demos, Raw Context ingestion, activity/email review, systems, workflows, and operational QA. MCP is the complete agent-facing surface.

REST API

REST endpoints live at:

http://localhost:3000/api/v1

Use REST for integrations that cannot run MCP or for custom web tooling.

Authentication:

Authorization: Bearer <jwt-token>     # human login
Authorization: Bearer crmy_<api-key>  # agent or integration

Create scoped API keys for agents and integrations:

POST /auth/api-keys
{ "label": "my-agent", "scopes": ["contacts:read", "activities:write"] }