yaojingang/GEOFlow

Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates.

GEOFlow – Open‑source AI‑augmented GEO (search‑engine‑optimized) content operations platform

What it is – GEOFlow is a Laravel‑based web application that ties together a knowledge base, AI‑driven content creation, automated quality‑gate checks, human review, multi‑site publishing, and analytics. It is aimed at companies that run GEO (search‑engine‑optimized) websites, sub‑channels, or industry‑specific content portals and need a single system to manage the whole content lifecycle.

Key capabilities

Feature What you get
Knowledge & asset hub Centralised storage for facts, titles, keywords, images, prompts and AI model configs. Supports structured slices, optional semantic planning, vector‑search (via pgvector) and fallback to deterministic data.
AI content generation Calls external LLMs (configurable per task) to draft articles using the stored knowledge.
AI quality gate Automatic checks for evidence, citations, ad‑policy compliance, SEO context, etc. Scores and audit trails are recorded; failing items stay in draft.
Human review workflow Draft → review → publish → recycle bin, with full audit of who approved what and when.
Multi‑site publishing Generates SEO‑ready front‑ends (robots.txt, sitemap.xml, Open Graph, Schema, llms.txt). Can host sites directly, expose a WordPress‑compatible REST API, or push to generic HTTP endpoints.
Analytics dashboard Shows content performance, traffic, top articles, AI‑crawler activity and trends.
CLI & Agent bin/geoflow CLI for programmatic management; a “GEOFlow Agent” package that can be installed on each published site to keep sitemaps in sync.
Updater & backup Stand‑alone Updater component handles signed releases, full backups, environment validation and point‑in‑time roll‑backs (requires admin password + 6‑digit token).
Chrome publishing assistant Browser extension that lets operators claim a publishing task, fill a draft and send back a signed receipt for final release.

Typical use‑cases

  • Corporate website with continuous SEO‑focused content.
  • Sub‑domains or separate directories for product‑specific “GEO channels”.
  • Industry‑wide knowledge portals that need verifiable sources (RAG‑style).
  • Internal content platforms where the same workflow (knowledge → AI → review → publish) is reused across teams.

Tech stack

  • Backend: Laravel (PHP 8.3+), PostgreSQL (recommended with pgvector), Redis, Docker‑Compose.
  • Frontend: Vue/React‑style admin UI (responsive, PWA, six language localisations).
  • AI integration: Configurable LLM endpoints; AI queues run in separate Docker services.
  • Deployment: Docker for dev; production uses docker-compose.prod.yml with Nginx + php‑fpm.

License & commercial model

  • Core code is released under AGPL‑3.0 (free for personal, internal, or SaaS use as long as source is offered to users).
  • A separate commercial licence is available for organisations that need to waive the AGPL source‑distribution requirement (white‑label, OEM, etc.).

Getting started

git clone https://github.com/yaojingang/GEOFlow.git
cd GEOFlow
cp .env.example .env
docker compose build && docker compose up -d
# admin UI → http://localhost:18080/geo_admin/login

The README also provides detailed production‑deployment steps, upgrade guides from 2.x to 3.0, and links to multilingual documentation.

Bottom line – GEOFlow is a full‑stack, open‑source platform that combines AI‑assisted content creation with rigorous editorial controls and automated SEO publishing, targeting enterprises that need a unified workflow for GEO‑focused web properties.

Related

  • Project
    bytedance/deer-flow

    DeerFlow is an open‑source framework that lets you build autonomous AI agents capable of orchestrating sub‑agents, using tools (web search, sandboxed code execution, RAG), and managing memory. It supports many LLM providers, offers a web UI, a terminal UI, and integrates tracing services, all deployable via Docker.

  • Project
    mars-tw/open-seo-advisor-skill

    Open SEO Advisor is an open‑source CLI and AI‑agent skill that audits websites for SEO health, suggests technical fixes, checks security, generates SEO‑friendly content with LLMs, scaffolds WordPress plugins, and can orchestrate multi‑agent marketing workflows. It runs locally, integrates optional paid APIs, and provides detailed reports and a static site skeleton for further development.

  • Project
    yaojingang/yao-geo-skills

    Yao GEO Skills is an open‑source catalog of 24 reusable “skill” packages that automate the end‑to‑end workflow of Generative Engine Optimization – making web pages and brand content AI‑search‑friendly, generating knowledge graphs, titles, comparison reports, and tracking the impact of those assets. Each skill includes clear documentation, a manifest, templates, validation tests and example outputs (Markdown, HTML, DOCX, PDF). The repo is geared toward marketing, SEO and growth teams that need repeatable, auditable processes for AI‑driven search, and integrates with the GEOFlow platform.

  • Project
    yaojingang/GEORank

    An open-source workbench for Generative Engine Optimization (GEO) that helps brands diagnose and improve their visibility in AI-powered search engines.

  • Project
    aigclink/geolook

    An open-source, self-hosted platform for Generative Engine Optimization (GEO) that helps brands increase their visibility and citations in AI engine answers through a structured audit-to-execution workflow.