AI AEO/GEO Agent

An AI agent for answer/generative-engine optimization (AEO/GEO) — getting a brand cited by ChatGPT, Google AI Overviews, Claude, Gemini, and Perplexity — backed by real citation-tracking APIs.

Part of Agency Agents OS, an open ecosystem of specialized AI agents for real business work.

Related Projects

• Agency Agents OS — the central catalog this repo is part of.
• ai-seo-agent — shares the same live Muapi SEO endpoints and the seo.lighthouse_audit technical-health signal.
• ai-research-agent — overlaps on live-LLM web-search testing for citation/retrievability checks.
• MuAPI MCP docs — connect this repo's SKILL.md files via MCP.
• MuAPI API reference — request/poll pattern used by seo-ai-mentions and seo-ai-response.
• MuAPI access keys — create the API key this agent needs.

What this covers

This repo is the umbrella for anything an agency or in-house team would call "the AEO/GEO agent": structuring a site's content so LLM answer engines can cite it, making sure AI agents doing live web search can actually retrieve and use it, and tracking whether that citation is happening. AEO (answer-engine optimization) and GEO (generative-engine optimization) are used interchangeably across the industry in 2026 — this repo covers both under one name rather than splitting them into separate agents.

Sub-agents

Agent	Does	Status
AEO Foundations	Audits and structures a site's content so it's citable by LLM answer engines — schema markup, clear factual statements, FAQ structure	Coming Soon
Agentic Search Optimization	Optimizes content for being retrieved and used by AI agents doing live web search/browsing on a user's behalf	Blueprint
Citation Tracking	Monitors whether/how often a brand gets cited by ChatGPT, Google AI Overviews, Claude, Gemini, and Perplexity for relevant queries	Blueprint

Required Muapi APIs

Live today:

• seo.ai_mentions (POST /seo-ai-mentions) — brand/keyword mention search across ChatGPT and Google AI Overviews.
• seo.ai_response (POST /seo-ai-response) — live prompt execution against gpt-5, claude-sonnet-4-5, gemini-2.5-pro, or sonar-reasoning-pro, with citation extraction and optional web search.
• seo.lighthouse_audit (POST /seo-lighthouse-audit) — on-page technical/performance audit, shared with ai-seo-agent.

Not yet live (needed by AEO Foundations):

• aeo.content_audit — schema markup, factual-clarity, and FAQ-structure specific audit.

See each sub-agent's SKILL.md for the specific capabilities it uses.

Setup

1. Create a Muapi account and API key at muapi.ai.
2. Review the OpenAPI schema for the AEO/GEO endpoints.
3. Load the SKILL.md for the sub-agent you need into your agent runtime (hosted agent, MCP client, or custom LLM app), or follow it manually.

Using with an AI agent

Every sub-agent's SKILL.md is model- and runtime-agnostic — it's plain Markdown, so it works with any LLM agent, not just Claude. Two integration paths:

As an MCP connection (the agent gets live Muapi tools):

Muapi runs an MCP server at https://api.muapi.ai/mcp that any MCP-compatible client can connect to — Cursor, Windsurf, Claude, or your own custom agent.

• Cursor / Windsurf / other clients with a header field: connect to https://api.muapi.ai/mcp with an Authorization: Bearer YOUR_MUAPI_KEY header.
• claude.ai / Claude Cowork / other connector UIs with no header field: use the URL-embedded key form instead, https://api.muapi.ai/mcp/YOUR_MUAPI_KEY, via Settings → Connectors → Add custom connector.
• Claude Code / Claude Desktop: claude mcp add muapi -e MUAPI_API_KEY=YOUR_MUAPI_KEY -- muapi mcp serve (uses the muapi CLI's stdio transport — Claude Code's HTTP MCP client doesn't reliably inject tools).

Full setup details for every client: muapi.ai/docs/mcp.

As agent instructions (any LLM follows the workflow directly):

Drop a sub-agent's SKILL.md into a Claude Code project's .claude/skills/ directory, paste it into a custom-GPT/Project's system instructions, hand it to an autonomous agent framework as a tool spec, or attach it directly in a chat conversation — then ask the agent to follow it.

Read-only vs. write actions

Every action in this repo is read-only or draft-only by default — audits, checks, and citation reports, never a live edit to a site or a published claim. Any content change this agent recommends (schema markup, FAQ copy, page structure) is handed back as a draft for a human to review and apply.

Status and limitations

Agentic Search Optimization and Citation Tracking are Blueprint — built on seo.ai_mentions, seo.ai_response, and seo.lighthouse_audit, all live on Muapi today, but not yet verified end-to-end from inside this repo. AEO Foundations is Coming Soon — it depends on aeo.content_audit (schema/FAQ-specific auditing), which isn't live yet.

Contributing

See Agency Agents OS CONTRIBUTING.md.

License

MIT