GenieHelper runs on IONOS dedicated hardware — Ubuntu 24, 16 GB RAM, 1 TB NVMe. No cloud uploads, no vendor data harvesting, no OpenAI dependency.
What GenieHelper does
| Capability | What actually happens |
|---|---|
| Multi-platform management | Connect OnlyFans, Fansly, Instagram, TikTok from one interface — scrape stats, track engagement, manage sessions |
| AI content drafting | Uncensored Ollama models write captions, fan messages, and post concepts in your voice |
| Content taxonomy | A 3,205-node proprietary adult taxonomy classifies every piece of content automatically |
| Post scheduling | AI-suggested calendar with tier-enforced queue limits and BullMQ reliability |
| Fan intelligence | Per-fan CRM with 71 engagement fields, purchase history, message sentiment, and follow-up tasks |
| Media pipeline | Watermarking, teaser clipping, thumbnail generation, and metadata stripping — all local FFmpeg |
| HITL scraping | Human-in-the-loop browser automation for platforms that block headless Chrome |
| Private AI chat | Dolphin 3 8B (Llama 3.1) + Qwen 2.5 running locally — zero OpenAI dependency |
| Custom content requests | Track fan requests from initial ask through negotiation, fulfillment, and payout |
| Leak tracing | Fan-specific steganographic watermarks embedded at delivery — identify the source of any leak |
| Fan memory injection | Durable per-fan facts surface automatically when drafting replies |
| Per-fan voice personas | Each fan gets a customized AI writing style — vocabulary, tone, and formatting specific to that relationship |
| Creator persona system | Define your own voice with lexicon rules, banned phrases, and tone preferences |
| Automation triggers | Rule-based chains fire on fan behavior: win-back, upsell, birthday, re-engagement — all auditable and pausable |
Capability areas
Stage UI
The theatrical UI model where the AI drives the interface. Center Stage, Left/Right Wings, The Pit, and the NavRail — assembled by the agent, not the user.
Fan CRM
71-field fan profiles, cross-platform identity linking, fan memory injection, per-fan AI personas, scoring, and subscription lifecycle tracking.
Content & Publishing
Idea inbox, post drafts, editorial series, campaign management, scheduling queue, and the creator persona system.
Media Pipeline
BullMQ-powered local FFmpeg processing — convert, resize, crop, watermark, clip, compress, and steganographically mark every asset.
Analytics
Earnings history, creator goals, platform growth curves, campaign ROI, and live post performance snapshots.
Automation & Messaging
Message templates, segment broadcasts, rule-based automation chains, and the HITL approval queue.
Subscription tiers
| Tier | Price | Audience |
|---|---|---|
| Starter | $0/mo | Try the platform |
| Creator | $49/mo | Solo creators |
| Pro | $149/mo | Power users with advanced fan CRM access |
| Studio | $499/mo | Agencies and multi-account creators |
Feature availability is enforced at the tier level. The
subscriptionValidator.js middleware checks quotas against tier_rate_limits.json on every API call. The Pro and Studio tiers unlock extended fan CRM access via the Directus Pro Policy.Technical foundation
| Layer | Technology |
|---|---|
| LLM inference | Ollama — Dolphin3 8B, dolphin-mistral 7B, Qwen 2.5 (CPU-bound, ~4.8 GB pinned) |
| Agent orchestration | AnythingLLM fork — multi-user, per-workspace isolation |
| CMS / data layer | Directus 11 — all collections, flows, and extensions |
| Primary database | PostgreSQL 16 — pgvector (RAG), AGE (graph), supabase_vault (credential encryption) |
| Job queue | BullMQ + Redis — concurrency 1, sequential execution, 9 core job types |
| Browser automation | Stagehand (Playwright) — HITL escalation for blocked platforms |
| Frontend | React 18 + Vite + Tailwind — 20 pages, 17 panels |
| Agent tools | Unified MCP server — 83 tools across 6 namespaced plugins |
| Memory | Python + DuckDB — 191 skills, Hebbian decay, RRF retrieval, LIF neurons |