@ghostpaw/affinity

@ghostpaw/affinity

Agent contacts: people, promises and yearly dates, with a radar for who is drifting.

npm install @ghostpaw/affinity

A standalone social CRM core for Node.js, built on SQLite.

Affinity treats contacts, identities, relationship mechanics, structural ties, journal evidence, commitments, recurring dates, attributes, and graph review as one coherent model instead of separate systems. It ships as a single prebundled blob with zero runtime dependencies, designed for two audiences at once: human developers working directly in code, and LLM agents operating through a structured soul / tools / skills runtime.

MCP server

Every client below starts the same stdio server: npx -y @ghostpaw/affinity mcp. Contacts live in ~/.ghostpaw/affinity.db unless the GHOSTPAW_AFFINITY_DB environment variable (absolute path) or --db <path> says otherwise.

Claude Code

claude mcp add ghostpaw-affinity -- npx -y @ghostpaw/affinity mcp

or as a plugin, which also installs the skill:

/plugin marketplace add GhostPawJS/affinity
/plugin install ghostpaw-affinity@ghostpaw-affinity

Codex CLI (~/.affinity/config.toml)

[mcp_servers.ghostpaw-affinity]
command = "npx"
args = ["-y", "@ghostpaw/affinity", "mcp"]

Cursor (.cursor/mcp.json), Claude Desktop (claude_desktop_config.json) or a project .mcp.json:

{
  "mcpServers": {
    "ghostpaw-affinity": {
      "command": "npx",
      "args": ["-y", "@ghostpaw/affinity", "mcp"]
    }
  }
}

Claude Desktop users can also install server.mcpb from the latest GitHub release. A Dockerfile is included for container hosts: docker build -t ghostpaw-affinity . && docker run -i --rm -v affinity:/data ghostpaw-affinity.

The server speaks MCP 2026-07-28 (stateless, server/discover) and the initialize-based revisions 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05.

CLI

npx -y @ghostpaw/affinity tools
npx -y @ghostpaw/affinity call manage_contact '{"action":"create","input":{"name":"Sam","kind":"human"}}'
npx -y @ghostpaw/affinity call search_affinity '{"query":"Sam"}'

Install globally for the ghostpaw-affinity binary: npm i -g @ghostpaw/affinity. ghostpaw-affinity mcp starts the stdio server.

Agent Skill

SKILL.md (repo root) and skills/affinity/SKILL.md follow the Agent Skills format and ship in the npm package. Copy skills/affinity/ into your agent's skills folder, or print it:

npx -y @ghostpaw/affinity skill > SKILL.md

Install

The npm package requires Node 24+:

npm install -g @ghostpaw/affinity
npx -y @ghostpaw/affinity --help

Standalone binaries are available from GitHub Releases for linux-x64, linux-arm64, darwin-arm64, darwin-x64 and windows-x64.

curl -fsSL https://raw.githubusercontent.com/GhostPawJS/affinity/main/install.sh | sh

irm https://raw.githubusercontent.com/GhostPawJS/affinity/main/install.ps1 | iex

Other release installers:

mise use -g github:GhostPawJS/affinity
ubi --project GhostPawJS/affinity --exe ghostpaw-affinity --in ~/.local/bin
eget GhostPawJS/affinity

For aqua, define a github_release package in aqua.yaml:

registries:
  - name: affinity
    type: local
    path: affinity-registry.yaml
packages:
  - name: GhostPawJS/affinity@v<VERSION>
    registry: affinity

affinity-registry.yaml:

packages:
  - type: github_release
    repo_owner: GhostPawJS
    repo_name: affinity
    asset: ghostpaw-affinity-{{trimV .Version}}-{{.OS}}-{{.Arch}}.tar.gz
    format: tar.gz
    replacements: { amd64: x64 }
    overrides:
      - goos: windows
        asset: ghostpaw-affinity-{{trimV .Version}}-windows-{{.Arch}}.zip
        format: zip
    files:
      - name: ghostpaw-affinity

Install scripts verify SHA256SUMS. To verify a downloaded archive's build attestation:

gh attestation verify <archive> -R GhostPawJS/affinity

Set GHOSTPAW_VERIFY=attestation for attestation verification in install.sh. Binaries are unsigned; macOS binaries carry an ad-hoc signature. For a browser download on macOS, remove quarantine with xattr -d com.apple.quarantine /path/to/ghostpaw-affinity. Linux binaries require glibc 2.28+; use npx on Alpine. See the binary build workflow.

The install check runs on ubuntu-24.04, macos-15 and windows-2025.

CLI

ghostpaw-affinity search <query>
ghostpaw-affinity review <view>
ghostpaw-affinity show <owner_profile|contact_profile|link> [--contact JSON --link JSON]
ghostpaw-affinity contact create <input-json>
ghostpaw-affinity contact revise <contact-json> --patch JSON
ghostpaw-affinity contact lifecycle <contact-json> <lifecycleState>
ghostpaw-affinity contact merge [flags]
ghostpaw-affinity identity add|revise|verify|remove [flags]
ghostpaw-affinity relationship add|bond|state|tie|untie [flags]
ghostpaw-affinity commitment record|resolve [flags]
ghostpaw-affinity attribute set|unset|replace [flags]
ghostpaw-affinity date add|revise|remove [flags]
ghostpaw-affinity event record [flags]
ghostpaw-affinity duplicate dismiss|undismiss [flags]
ghostpaw-affinity mcp|skill|tools|describe|call|completions|version|help

There are 27 domain commands. review accepts the existing view names, including contacts.list, contacts.duplicates and dates.upcoming. show selects an inspection kind; contact and link locators are JSON objects. Use help contact or contact create --help for schema-derived help. Nested payloads use JSON or @path to read a file.

Global flags: --db <path>, --json, --quiet, --compact, --help/-h, --version/-V/-v, --no-color. NO_COLOR is accepted; output uses no terminal colors. Noun-verb commands print the full tool result as JSON with --json or piped stdout. Terminal output shows the summary and payload. --quiet suppresses stdout. --compact removes JSON indentation. Array flags repeat; kebab-case flags map to schema properties. -- ends flags. A positional -, or piped stdin with no input flags, reads a JSON object. Explicit flags override stdin fields. Database selection uses --db, GHOSTPAW_AFFINITY_DB, then ~/.ghostpaw/affinity.db. These commands work offline.

Exit	Noun-verb result
0	Success, including no_op
1	Tool error
2	Usage or schema error
3	Clarification needed or not found
4	Conflict or version mismatch
70	Internal error

Errors go to stderr. With --json, errors also print to stdout. Legacy tools [--json], describe <tool>, call <tool> [JSON|-] and <tool_name> --parameter value retain their output and exit codes. completions bash|zsh|fish prints shell scripts.

ghostpaw-affinity contact create '{"name":"Sam","kind":"human"}' --db /tmp/affinity-example.db --json
ghostpaw-affinity search Sam --db /tmp/affinity-example.db --json
ghostpaw-affinity review contacts.list --db /tmp/affinity-example.db --json

Quick Start

import { DatabaseSync } from "node:sqlite";
import { initAffinityTables, read, write } from "@ghostpaw/affinity";

const db = new DatabaseSync(":memory:");
db.exec("PRAGMA foreign_keys = ON");
initAffinityTables(db);

const { primary: owner } = write.createContact(db, {
  name: "Mika",
  kind: "human",
  bootstrapOwner: true,
});

const { primary: ada } = write.createContact(db, {
  name: "Ada Lovelace",
  kind: "human",
});

write.addIdentity(db, ada.id, {
  type: "email",
  value: "[e-mail]",
});

write.recordInteraction(db, {
  type: "conversation",
  occurredAt: Date.now(),
  summary: "Coffee together",
  significance: 6,
  participants: [
    { contactId: owner.id, role: "actor", directionality: "mutual" },
    { contactId: ada.id, role: "recipient", directionality: "mutual" },
  ],
});

const profile = read.getContactProfile(db, ada.id);
const radar = read.listRadar(db);

Docs

The live demo runs the library in your browser against an in-memory SQLite database. Each view below opens a different part of it:

• Dashboard: overview and session
• Contacts: people, companies, groups and pets you track
• Relationships: links, rank and bonds
• Timeline: events, commitments and date anchors
• Insights: radar and analytics

The Model

Eight concepts, strict separation of concerns:

Concept	Purpose
Contact	Any tracked entity: person, company, team, service, pet, household, or group
Identity	Exact recognition and routing handle such as email, phone, URL, or account id
Social Link	A live relationship track with Rank, Affinity, Trust, cadence, Bond, and state
Tie	A structural fact such as works_at, belongs_to, reports_to, or kinship
Journal Entry	Recorded evidence: interaction, observation, milestone, transaction, or commitment
Date Anchor	A recurring yearly date such as a birthday, anniversary, renewal, or memorial
Attribute	Flexible metadata and preference layer for contacts and links
Affinity Chart	Derived graph view of the active relationship network

The model means each kind of truth has its own home:

What it looks like	What it actually is
A person, company, team, service, or household	A Contact
An email address or handle	An Identity
A friendship or business relationship that changes over time	A Social Link
Employment, hierarchy, family, or membership	A Tie
“We talked yesterday”	A Journal entry
“I promised to send the recap”	A commitment-shaped Journal entry
“Their birthday is important every year”	A Date Anchor

State is derived, not hand-toggled. Rank, hidden Affinity, Trust movement, Moments, drift, readiness, and graph bridge significance are computed from evidence and explicit structural truth, not caller-written status flags.

Two Audiences

Human developers

Use the read and write namespaces for direct-code access to the domain:

import { read, write } from "@ghostpaw/affinity";

write.createContact(db, { name: "Ada", kind: "human" });
write.addIdentity(db, contactId, { type: "email", value: "[e-mail]" });
write.recordInteraction(db, {
  type: "support",
  occurredAt: now,
  summary: "Helped prepare for a difficult meeting",
  significance: 7,
  participants: [
    { contactId: ownerId, role: "actor", directionality: "mutual" },
    { contactId, role: "recipient", directionality: "mutual" },
  ],
});

const profile = read.getContactProfile(db, contactId);
const radar = read.listRadar(db);

See HUMAN.md for the full direct-code guide with modeling boundaries and worked examples.

LLM agents

Use the tools, skills, and soul namespaces for a structured runtime surface designed to minimize LLM cognitive load:

import { tools, skills, soul } from "@ghostpaw/affinity";

const allTools = tools.affinityTools;
const searchTool = tools.getAffinityToolByName("search_affinity")!;
const result = searchTool.handler(db, { query: "email:[e-mail]" });

const allSkills = skills.affinitySkills;
const prompt = soul.renderAffinitySoulPromptFoundation();

Every tool returns a discriminated result with outcome: "success" | "no_op" | "needs_clarification" | "error", structured entities, next-step hints, and actionable recovery signals.

See LLM.md for the full AI-facing guide covering soul, tools, and skills.

Tools

Twelve tools shaped around operator intent, not raw storage operations:

Tool	What it does
search_affinity	Search contacts by natural key or name
review_affinity	Dashboard-style list and graph review views
inspect_affinity_item	Open one exact profile or link detail
manage_contact	Create, revise, or change contact lifecycle
merge_contacts	Merge duplicate contacts safely
manage_duplicate_dismissal	Dismiss or restore a suspected duplicate pair
manage_identity	Add, revise, verify, or remove identities
manage_relationship	Seed social links, revise bond/state, manage structural ties
record_event	Record direct evidence, observations, milestones, or transactions
manage_commitment	Record or resolve obligations
manage_date_anchor	Add, revise, or remove recurring important dates
manage_attribute	Set, unset, or replace contact/link metadata

Each tool exports runtime metadata, JSON-Schema-compatible inputs, and structured outputs so harnesses can wire them without parsing vague prose.

Key Properties

• Zero runtime dependencies. Only node:sqlite (built into Node 24+).
• Single prebundled blob. One ESM + one CJS entry in dist/. No subpath exports, no code splitting.
• Pure SQLite storage. CHECK-constrained state, trigger-maintained support tables, and deterministic derived reads. Bring your own DatabaseSync.
• Derived mechanics. Rank, hidden Affinity, Trust, cadence, Moments, Radar, and bridge significance are computed from evidence and structure, never directly caller-set.
• Intention-shaped writes. createContact, setStructuralTie, recordInteraction, recordCommitment, addDateAnchor, mergeContacts: operations that say what happened or what truth changed, not generic CRUD.
• Additive AI runtime. soul for posture, tools for actions, skills for workflow guidance.
• Colocated tests. Every non-type module has a colocated .test.ts file. The documented behavior is backed by executable coverage.

Package Surface

import {
  initAffinityTables,  // schema setup
  read,                // all query functions
  write,               // all mutation functions
  tools,               // LLM tool definitions + registry
  skills,              // LLM workflow skills + registry
  soul,                // thinking foundation for system prompts
} from "@ghostpaw/affinity";

All domain and runtime types are also available at the root for TypeScript consumers:

import type {
  AffinityDb,
  ContactKind,
  LinkState,
  ContactProfileRecord,
  AffinityChartRecord,
  AffinityToolDefinition,
  AffinitySkill,
  AffinitySoul,
} from "@ghostpaw/affinity";

Documentation

Document	Audience
HUMAN.md	Human developers using the low-level read / write API
LLM.md	Agent builders wiring soul, tools, and skills into LLM systems
docs/README.md	Architecture overview: model, invariants, mechanics, and source layout
docs/entities/	Per-concept manuals with exact inlined public API listings
docs/USECASES.md	Long-form lifecycle narratives across personal, business, and AI-memory angles

Development

npm install
npm test            # node:test runner
npm run typecheck   # tsc --noEmit
npm run lint        # biome check
npm run build       # ESM + CJS + declarations via tsup

The repo is pinned to Node 24.14.0 via .nvmrc / .node-version / .tool-versions / mise.toml / Volta. Use whichever version manager you prefer.

Support

If this package helps your project, consider sponsoring its maintenance:

Anonyfox • MIT License