Skip to content

Open source

AGPL server. MIT edges. Clean room.

Read every line that touches a visitor. The server and dashboard are AGPL-3.0 so improvements flow back; everything you embed in your own product is MIT so it never constrains you.

View on GitHubprivacy-model.md

  • apps/api

    Go · ingest, classification, rollups, insights

    AGPL-3.0

  • apps/web

    Next.js · landing and dashboard

    AGPL-3.0

  • packages/tracker

    1 KB cookieless v5.js

    MIT

  • packages/middleware

    Next · Express · Hono · Workers · Node

    MIT

  • packages/mcp

    Read-only MCP server

    MIT

  • packages/skills

    Prompts for Claude, Cursor, Codex

    MIT

Self-host in one command

terminal
git clone https://github.com/abailony/vector5-ai
cd vector5-ai
cp .env.example .env
docker compose up --build

# Dashboard  http://localhost:3000
# API        http://localhost:8080

Or run it in the cloud

Same code, hosted for you, with Supabase auth. The manifest is identical either way — your privacy claims do not depend on where the server lives.

Not a fork

Vector 5 was written from scratch. It is not affiliated with Plausible Analytics and does not reuse their code, name, or assets.

Early access

Signup is closed. Request a seat.

Vector 5 is in private early access. Leave your email — we invite people in small batches. No account is created until then.

Self-host from GitHub

Invite only · No public signup · No credit card