Track how your brand appears in answers from ChatGPT, Gemini, Perplexity, Claude, and Copilot. Ansvisor turns AI search into a measurable channel — visibility scores, competitor benchmarks, content optimization briefs, and AI-referral analytics in one self-hostable platform.

Why Ansvisor?

AI search is replacing the traditional click. When ChatGPT recommends a product, no Google ranking saves you. Ansvisor measures what classical SEO can't see — how often AI engines name your brand, which competitors get cited instead, and which prompts move the needle. Self-host it for free, or use the managed cloud at ansvisor.com.

Features

• Answer Engine Insights — Real-time visibility scores across ChatGPT, Google AI Overview, Google AI Mode, Google Gemini, Perplexity, Microsoft Copilot, Grok, and Claude with weekly trend analysis
• Topics — Cluster prompts by intent and topic so you can see exactly which themes your brand wins or loses
• Prompts — Track unlimited natural-language queries, get AI-generated prompt suggestions based on competitor citations, and analyze monthly search volume per prompt
• Citations — See every URL AI engines cite alongside your brand, classified by source type (news, review, owned, social, forum)
• AI Traffic Analytics — Tracking pixel that measures real visits arriving from AI answer engines, with platform breakdown, top landing pages, and country segmentation
• Competitors — Compare your AI presence against named competitors and surface visibility gaps to close
• Content Optimization — AI-generated content briefs (title, outline, target keywords, competitor insights) with one-click webhook delivery to your CMS or workflow
• Multi-language Support — 13 languages, 18 regions
• Self-hosted or Cloud — Run it on your own infrastructure with every feature unlocked, or use the managed cloud at ansvisor.com

Quick Start

Prerequisites

• Node.js >= 20
• Yarn (for the web app)
• A Supabase project (free tier works)

Required Services

Optional Services

Setup

1. Clone and configure

git clone https://github.com/aeohub/ansvisor.git
cd ansvisor

cp web/.env.example web/.env.local
cp server/.env.example server/.env

Edit both .env files and fill in your credentials. See the comments in each file for guidance.

2. Set up the database

Run the migration SQL to create all tables, indexes, RLS policies, and triggers:

Option A — Supabase Dashboard:

1. Go to your project's SQL Editor
2. For each file in supabase/migrations/ (in alphabetical order — 00001_… first, then 00002_…, etc.), paste its contents and click Run

Option B — Supabase CLI:

npx supabase link --project-ref <YOUR_PROJECT_REF>
npx supabase db push

3. Install dependencies

cd web && yarn install && cd ..
cd server && npm install && cd ..

4. Start dev servers

# Terminal 1 — frontend
cd web && yarn dev          # http://localhost:3000

# Terminal 2 — backend
cd server && npm run dev    # http://localhost:80

Docker

# Configure env files first, then:
docker compose up --build

Self-hosted vs Cloud

Set IS_CLOUD=false (default) in server/.env and NEXT_PUBLIC_IS_CLOUD=false in web/.env.local for self-hosted mode. All features are unlocked automatically — no Stripe or payment setup needed.

Project Structure

ansvisor/
├── web/                 # Next.js 16 frontend (TypeScript)
├── server/              # Express backend (Node.js ESM)
├── supabase/            # Database migrations and config
├── scripts/             # Version management tooling
├── docker-compose.yml   # Containerized deployment
├── CONTRIBUTING.md
├── CHANGELOG.md
└── LICENSE

Tech Stack

Frontend — Next.js 16, React 19, TypeScript, Tailwind CSS 4, Supabase Auth, Stripe, Zustand, Recharts, next-intl

Backend — Express, Vercel AI SDK, multi-provider AI (OpenAI, Anthropic, Google, Perplexity, Grok), Supabase, Socket.IO, Zod

What's next

What we're planning to build next. React with 👍 on the linked issue (or open a new one) to push something up the list. PRs welcome on any of these.

• Ansvisor MCP server — expose insights through a Model Context Protocol server so Claude Desktop, Claude Code, Cursor, Zed, and any other MCP client can query your brand visibility directly. Remote (Streamable HTTP) endpoint at /api/mcp — zero install, paste a URL + API key into your client and you're done. Ships with list_brands and get_visibility_summary today; more tools landing as we go.
• Anthropic Skills — opinionated AEO knowledge that turns Claude into an analyst on your account. Ships in two flavours: an MCP-tool flavour for Claude Desktop / Claude Code / Cursor / Zed, and a standalone REST flavour for claude.ai web (no MCP required). First skill (ansvisor-aeo-coach) is live — see skills/. More (page-audit, rewrite-for-aeo, content-brief) on the way.
• In-product conversational AI assistant — chat with your dashboard about visibility trends, competitor moves, and content gaps without leaving the page
• ScrapeLLM integration — add ScrapeLLM as an alternative scraping backend alongside Cloro for users who prefer it or need a fallback
• PostHog integration — pipe AI-referred sessions and tracking events into PostHog for users already running it as their product analytics layer
• Anomaly alerts — get an email / Slack ping when a brand's visibility drops sharply, a competitor surges, or a high-volume prompt suddenly stops citing you
• BYO LLM keys — bring your own OpenAI / Anthropic / Gemini API key for tracking and content generation, so you control cost and data handling
• Webhook recipe library — one-click Notion / Linear / Asana / Slack templates so a Content Brief can land in your editorial workflow with zero glue code

See an idea missing? Check the Ideas discussions — upvote an existing one or open a new thread.

Contributing

We welcome contributions! See CONTRIBUTING.md for development setup, branch naming, commit conventions, and PR guidelines.

License

MIT — Copyright (c) 2026 Empler AI Inc.