Skip to content
Back to search

ansvisor

SkillWorks with Claude CodeGitHub

Open-source AI Search Intelligence Platform — track, analyze, and improve AI visibility, citations, prompts, competitors, and content opportunities across ChatGPT, Claude, Gemini, Google AI Overviews, Google AI Mode, Perplexity, Grok, and Microsoft Copilot.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/ansvisor/ansvisor with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/ansvisor/ansvisor'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ansvisor--ansvisor/badge.svg)](/listings/ansvisor--ansvisor)

HTML

<a href="/listings/ansvisor--ansvisor"><img src="/api/listings/ansvisor--ansvisor/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- [Node.js](https://nodejs.org/) >= 20 - [Yarn](https://yarnpkg.com/) (for the web app) - A [Supabase](https://supabase.com/) project (free tier works)

Required Services

| Service | Purpose | Where to get | |---------|---------|--------------| | **Supabase** | Database, Auth, API | [supabase.com](https://supabase.com/) | | **AI Provider** (at least one) | Brand tracking across AI engines | [OpenAI](https://platform.openai.com/) / [Google Gemini](https://ai.google.dev/) / [Anthropic](https://console.anthropic.com/) | | **Cloro** | Web scraping for AI platform responses | [cloro.ai](https://cloro.ai/) |

Optional Services

| Service | Purpose | Where to get | |---------|---------|--------------| | **DataForSEO** | Keyword volume data for prompt analysis | [dataforseo.com](https://dataforseo.com/) | | **Scrape.do** | Page fetching for Site Audit (proxy + JS render); required only if you use Site Audit | [scrape.do](https://scrape.do/) | | **Stripe** | Payments (cloud mode only, not needed for self-hosted) | [stripe.com](https://stripe.com/) |

Setup

1. Clone and configure

git clone https://github.com/ansvisor/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 (fresh install, one paste):** 1. Go to your project's **SQL Editor** 2. Paste the contents of [`supabase/schema.sql`](supabase/schema.sql) — the full schema (every migration in one file) — and click **Run**

**Option B — Supabase CLI:**

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

> `supabase/schema.sql` is a generated convenience for **fresh** installs. The numbered files under `supabase/migrations/` stay the source of truth and the **upgrade** path — an existing install adds only the new migration(s) (or `db push`). Regenerate the consolidated file after adding a migration with `bash supabase/build-schema.sh`.

Demo data (local only)

For local development, `supabase/seed.sql` ships a small fixture (one demo org, brand, prompts, ~120 prompt results across all tracked engines, competitors, content opportunities, AI traffic logs). It runs automatically the next time you do:

npx supabase db reset

Sign in with **`demo@ansvisor.local` / `demo123`** and you'll land on a populated dashboard — no provider API keys needed to iterate on UI. The seed only runs against a local Supabase via the CLI; hosted projects are unaffected.

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.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 276 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. [![Ansvisor: Open-Source Agentic AI Search Execution Platform](.github/assets/ansvisor-readme-banner.png)](https://www.ansvisor.com)
  3. [![🚀 Try the Cloud — ansvisor.com](https://img.shields.io/badge/🚀_Try_the_Cloud-ansvisor.com-6366f1?style=for-the-badge&logoColor=white&logo=vercel)](https://www.ansvisor.com)
  4. [![📚 Docs](https://img.shields.io/badge/📚_Docs-docs.ansvisor.com-10b981?style=for-the-badge&logoColor=white&logo=readthedocs)](https://docs.ansvisor.com)
  5. [![MIT License](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge)](https://opensource.org/licenses/MIT)
  6. [![Claude Code](https://img.shields.io/badge/Built%20with-Claude%20Code-green?style=for-the-badge&logo=anthropic)](https://claude.com/claude-code)
  7. </div>
  8. # Ansvisor — Open-Source Agentic AI Search Execution Platform
  9. **[AI Visibility Platform](https://www.ansvisor.com/)** · **[Documentation](https://docs.ansvisor.com/)**
  10. **Business + AI Search Data → Signals → Actions → Agent-Drafted Fixes → AI Visibility Outcomes**
  11. Ansvisor is an **open-source, agentic AI Search Execution Platform**. It shows how your brand appears in AI answers, finds where you can win, and turns that into work your team can ship. Agents find opportunities, turn signals into prioritized actions and draft the fixes. You approve what goes live.
  12. Connect business data and traditional search signals with AI Search behavior across ChatGPT, Google AI Overviews, Google AI Mode, Gemini, Claude, Grok, and other AI platforms to discover opportunities, prioritize what matters, and improve brand visibility.
  13. Track prompts, mentions, citations, competitors, AI traffic, and the sources AI systems rely on. Then act on them in the same place: plan content, let the Content Agent draft and fix pages, and follow every action against your AI Search KPIs.
  14. Self-host Ansvisor for free or use the managed [Ansvisor Cloud](https://www.ansvisor.com/).
  15. We're building Ansvisor in the open because we believe companies shouldn't need another black box to understand a black box.
  16. Our goal is to make AI Search work more transparent, measurable, actionable, and accessible.
  17. > ⭐ **If you believe AI Visibility should be open and community-driven, star the repo — it's how the next team discovers Ansvisor.**
  18. ---
  19. ## Why Ansvisor?
  20. AI Search is becoming a new layer of how people discover, evaluate, compare, and choose brands.
  21. More than a billion people now use AI tools, with billions of AI-powered queries happening every day. Yet most companies are still early: only a small share have an integrated AI Search strategy, and meaningful brand visibility across AI-generated answers remains limited.
  22. This creates a growing gap between how customers discover information and how companies understand and optimize their presence in that discovery process.
  23. Traditional search data tells you how people find you through search engines. AI Search introduces another layer: which prompts influence discovery, whether your brand appears, how competitors are represented, which sources AI systems rely on, when your website is cited, and whether that visibility translates into traffic and business outcomes.
  24. This shift is making [Answer Engine Optimization (AEO)](https://www.ansvisor.com/ai-visibility-glossary/aeo-answer-engine-optimization), [Generative Engine Optimization (GEO)](https://www.ansvisor.com/ai-visibility-glossary/geo-generative-engine-optimization), and AI SEO increasingly important.
  25. **Ansvisor is built to close this gap.**
  26. Instead of treating AI visibility as another isolated analytics dashboard, Ansvisor connects business data, traditional search signals, and AI Search behavior to help teams understand what is happening, discover where opportunities exist, prioritize what matters, and take action.
  27. Agents do the groundwork. They surface opportunities, prepare briefs and drafts, and keep actions moving. People stay in charge of what ships.
  28. With Ansvisor, you can:
  29. - [**AI Search Execution Platform**](https://www.ansvisor.com/platform) — Bring AI visibility, prompts, citations, competitors, AI traffic, content, and execution workflows together in one platform.
  30. - [**Action Center**](https://www.ansvisor.com/features/ai-search-actions-kpis-action-center) — Turn signals across your workspace and connected data sources into prioritized actions and tasks aligned with your AI Search KPIs. **Today** shows what changed overnight, your three focus actions and what waits for your OK; **Signals** lists what changed and **History** measures what each finished action did.
  31. - **Chat** — Ask questions about your data and do the work step by step. Chat reads the same data as every page, shows a live status line while it works, and asks before it changes anything. Approve changes in Chat or in Slack, and use **Approve all** when several agents changed the same draft.
  32. - **Agents** — Save a skill, mode and connections as an agent. Pick one from the ready-to-use catalog, run it on a schedule, on a signal, or with **Run now**, and, on Growth and up, let it call other agents. Agent work waits for your approval until an Admin allows otherwise.
  33. - [**Agentic Content Editor**](https://www.ansvisor.com/features/agentic-content-editor) — The Content Agent writes and fixes pages from your prompts, query fan-outs, and cited pages, checks them against your brand facts and content rules (banned phrases, allowed and blocked sources), and waits for your approval before anything changes. Brand facts can apply to one destination, operator or route.
  34. - [**Answer Engine Insights & AI Visibility**](https://www.ansvisor.com/features/answer-engine-insights) — Track how your brand appears, performs, and is represented across leading AI platforms.
  35. - [**AI Brand Mentions & Sentiment**](https://www.ansvisor.com/features/ai-brand-mentions-sentiment) — See how AI platforms describe your brand: the exact quotes, the sentiment, and where you appear in each answer, compared with your competitors.
  36. - [**Prompt Monitoring & Volumes**](https://www.ansvisor.com/features/prompt-monitoring-volumes) — Ansvisor opens on the Prompts page. Track prompts, review suggestions from your data, group them into topics, and see estimated AI search volume and intent under Insights.
  37. - [**AI Citation Monitoring**](https://www.ansvisor.com/features/citations-monitoring) — Discover which domains, URLs, competitors, and third-party sources AI systems cite, and which third-party domains cite your competitors but not you (Competitor Gaps).
  38. - [**Competitor Tracking & Benchmarking**](https://www.ansvisor.com/features/competitor-tracking-benchmarking) — Compare your visibility, citations, mentions, and share of voice with competitors.
  39. - [**AI Traffic Analytics**](https://www.ansvisor.com/features/ai-traffic-analytics) — Connect AI Search visibility with visits, conversions and revenue on your website.
  40. - **Ads** (preview) — For each buying-intent prompt, decide whether to earn the AI answer with content, pay for an ad, or both. Ad drafts are written from your approved brand facts. Nothing is sent to an ad platform.
  41. - [**Query Fan-Out**](https://www.ansvisor.com/features/query-fan-out) — Explore the supporting queries AI systems may generate and use before producing an answer, per prompt and across the brand.
  42. - [**Content Intelligence & Optimization**](https://www.ansvisor.com/features/content-intelligence-optimization) — Identify content gaps, optimization opportunities, and topics based on AI Search behavior.
  43. - [**AI Visibility Site Audit**](https://www.ansvisor.com/features/ai-visibility-site-audit) — Analyze technical and content signals that can affect how AI systems discover, understand, and retrieve your website.
  44. - [**MCP Server**](https://docs.ansvisor.com/guides/mcp-server) — Connect Ansvisor's AI Search intelligence with AI assistants and agent workflows through the Model Context Protocol (MCP). Claude and ChatGPT connect by signing in; other clients use an API key.
  45. The result is a clearer path from fragmented data to shipped improvements in AI visibility.
  46. ---
  47. ## Resources
  48. - 📜 [Read the Ansvisor Manifesto](https://www.ansvisor.com/manifesto)
  49. - 🔌 [Explore Ansvisor Integrations](https://www.ansvisor.com/integration)
  50. - 📖 [Explore the AI Visibility Glossary](https://www.ansvisor.com/ai-visibility-glossary)
  51. - ✍️ [Read the Blog](https://www.ansvisor.com/blog)
  52. - 🔍 [Compare Ansvisor vs Alternatives](https://www.ansvisor.com/compare)
  53. ---
  54. ## Open Source & Cloud Ready
  55. Ansvisor is built for teams that want transparency, flexibility, and control.
  56. Inspect the code, contribute to the platform, and deploy Ansvisor on your own infrastructure — or use [Ansvisor Cloud](https://www.ansvisor.com/) without managing infrastructure yourself.
  57. Whether you're an enterprise, agency, e-commerce brand, SaaS company, startup, or developer, Ansvisor helps turn business and AI Search data into signals, actions, and tasks designed to improve AI visibility outcomes.
  58. ---
  59. ## Supported AI Platforms
  60. Ansvisor helps you monitor and analyze brand visibility across:
  61. - [**ChatGPT AI Visibility Tracker**](https://www.ansvisor.com/features/chatgpt-visibility-tracker)
  62. - [**Google AI Overviews Rank Tracker**](https://www.ansvisor.com/features/google-ai-overviews-rank-tracker)
  63. - [**Google AI Mode Rank Tracker**](https://www.ansvisor.com/features/google-ai-mode-visibility-tracker)
  64. - [**Gemini AI Visibility Tracker**](https://www.ansvisor.com/features/gemini-visibility-tracker)
  65. - [**Claude AI Visibility Tracker**](https://www.ansvisor.com/features/claude-ai-visibility-tracker)
  66. - [**Grok AI Visibility Tracker**](https://www.ansvisor.com/features/grok-visibility-tracker)
  67. - [**ChatGPT AI Shopping Tracker**](https://www.ansvisor.com/features/ai-shopping-analytics)
  68. - and other AI-powered discovery experiences
  69. ---
  70. ## Built in the Open
  71. AI Search is still evolving, and we don't believe its measurement and optimization should happen behind another black box.
  72. We're building Ansvisor together with our open-source community around a few simple principles:
  73. - **Evidence over dogma**
  74. - **Measurement over assumptions**
  75. - **Transparency over black boxes**
  76. - **Outcomes over vanity metrics**
  77. - **Collaboration over closed innovation**
  78. Developers, marketers, SEO/AEO/GEO practitioners, researchers, agencies, and companies are welcome to contribute through issues, feature ideas, pull requests, testing, documentation, and feedback.
  79. ---
  80. ## Get Started
  81. ### Ansvisor Cloud
  82. The fastest way to get started without managing infrastructure.
  83. [**Start with Ansvisor Cloud →**](https://app.ansvisor.com/sign-up)
  84. ### Self-Hosted
  85. Deploy Ansvisor on your own infrastructure and maintain control over your environment and data.
  86. [**Self-host Ansvisor →**](https://github.com/ansvisor/ansvisor)
  87. ---
  88. ## Quick Start
  89. ### Prerequisites
  90. - [Node.js](https://nodejs.org/) >= 20
  91. - [Yarn](https://yarnpkg.com/) (for the web app)
  92. - A [Supabase](https://supabase.com/) project (free tier works)
  93. ### Required Services
  94. | Service | Purpose | Where to get |
  95. |---------|---------|--------------|
  96. | **Supabase** | Database, Auth, API | [supabase.com](https://supabase.com/) |
  97. | **AI Provider** (at least one) | Brand tracking across AI engines | [OpenAI](https://platform.openai.com/) / [Google Gemini](https://ai.google.dev/) / [Anthropic](https://console.anthropic.com/) |
  98. | **Cloro** | Web scraping for AI platform responses | [cloro.dev](https://cloro.dev/?utm_source=ansvisor&utm_medium=byok) |
  99. ### Optional Services
  100. | Service | Purpose | Where to get |
  101. |---------|---------|--------------|
  102. | **DataForSEO** | Keyword volume data for prompt analysis | [dataforseo.com](https://dataforseo.com/) |
  103. | **Scrape.do** | Page fetching for Site Audit (proxy + JS render); required only if you use Site Audit | [scrape.do](https://scrape.do/) |
  104. | **Stripe** | Payments, including the email sent 3 days before a trial ends (cloud mode only, not needed for self-hosted) | [stripe.com](https://stripe.com/) |
  105. ### Setup
  106. #### 1. Clone and configure
  107. ```bash
  108. git clone https://github.com/ansvisor/ansvisor.git
  109. cd ansvisor
  110. cp web/.env.example web/.env.local
  111. cp server/.env.example server/.env
  112. ```
  113. Edit both `.env` files and fill in your credentials. See the comments in each file for guidance.
  114. #### 2. Set up the database
  115. Run the migration SQL to create all tables, indexes, RLS policies, and triggers:
  116. **Option A — Supabase Dashboard (fresh install, one paste):**
  117. 1. Go to your project's **SQL Editor**
  118. 2. Paste the contents of [`supabase/schema.sql`](supabase/schema.sql) — the full schema (every migration in one file) — and click **Run**
  119. **Option B — Supabase CLI:**
  120. ```bash
  121. npx supabase link --project-ref <YOUR_PROJECT_REF>
  122. npx supabase db push
  123. ```
  124. > `supabase/schema.sql` is a generated convenience for **fresh** installs. The numbered files under `supabase/migrations/` stay the source of truth and the **upgrade** path — an existing install adds only the new migration(s) (or `db push`). Regenerate the consolidated file after adding a migration with `bash supabase/build-schema.sh`.
  125. ##### Demo data (local only)
  126. For local development, `supabase/seed.sql` ships a small fixture (one demo org, brand, prompts, ~120 prompt results across all tracked engines, competitors, content opportunities, AI traffic logs). It runs automatically the next time you do:
  127. ```bash
  128. npx supabase db reset
  129. ```
  130. Sign in with **`demo@ansvisor.local` / `demo123`** and you'll land on a populated dashboard — no provider API keys needed to iterate on UI. The seed only runs against a local Supabase via the CLI; hosted projects are unaffected.
  131. #### 3. Install dependencies
  132. ```bash
  133. cd web && yarn install && cd ..
  134. cd server && npm install && cd ..
  135. ```
  136. #### 4. Start dev servers
  137. ```bash
  138. # Terminal 1 — frontend
  139. cd web && yarn dev # http://localhost:3000
  140. # Terminal 2 — backend
  141. cd server && npm run dev # http://localhost:80
  142. ```
  143. ### Docker
  144. ```bash
  145. # Configure env files first, then:
  146. docker compose up --build
  147. ```
  148. ### Self-hosted vs Cloud
  149. 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.
  150. ## Project Structure
  151. ```
  152. ansvisor/
  153. ├── web/ # Next.js 16 frontend (TypeScript)
  154. ├── server/ # Express backend (Node.js ESM)
  155. ├── supabase/ # Database migrations and config
  156. ├── scripts/ # Version management tooling
  157. ├── docker-compose.yml # Containerized deployment
  158. ├── CONTRIBUTING.md
  159. ├── CHANGELOG.md
  160. └── LICENSE
  161. ```
  162. ## Tech Stack
  163. **Frontend** — Next.js 16, React 19, TypeScript, Tailwind CSS 4, Supabase Auth, Stripe, Zustand, Recharts, next-intl
  164. **Backend** — Express, Vercel AI SDK, multi-provider AI (OpenAI, Anthropic, Google, Perplexity, Grok), Supabase, Socket.IO, Zod
  165. ## What's next
  166. 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.
  167. - [x] **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. Tools read visibility, prompts, citations, mentions, AI traffic, shopping, the Action Center and more, and can create content drafts and actions. Claude and ChatGPT can also connect by signing in, with no key.
  168. - [x] **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/`](./skills). More (page-audit, rewrite-for-aeo, content-brief) on the way.
  169. - [x] **In-product conversational AI assistant** — chat with your dashboard about visibility trends, competitor moves, and content gaps without leaving the page
  170. - [ ] **ScrapeLLM integration** — add ScrapeLLM as an alternative scraping backend alongside Cloro for users who prefer it or need a fallback
  171. - [x] **PostHog integration** — pipe AI-referred sessions and tracking events into PostHog for users already running it as their product analytics layer
  172. - [x] **Daily Pulse** — a per-brand daily digest email after each tracking run: KPI strip, highlights (first citations, prompt gains, leaderboard overtakes) and anomaly warnings (sharp visibility drops, competitor surges, lost citations), plus a `daily_pulse.created` webhook event and an optional Slack post ([#540](https://github.com/ansvisor/ansvisor/issues/540))
  173. - [ ] **BYO LLM keys** — bring your own OpenAI / Anthropic / Gemini API key for tracking and content generation, so you control cost and data handling
  174. - [ ] **Webhook recipe library** — one-click Notion / Linear / Asana / Slack templates so a Content Brief can land in your editorial workflow with zero glue code
  175. See an idea missing? Check the [Ideas discussions](https://github.com/ansvisor/ansvisor/discussions/categories/ideas) — upvote an existing one or open a new thread.
  176. ## Contributing
  177. We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, branch naming, commit conventions, and PR guidelines.
  178. ## License
  179. [MIT](LICENSE) — Copyright (c) 2026 Empler AI Inc.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.