Nine minutes on why "AI on your data" tools get this wrong — and what Cortex does differently. Local-first, BYOK, no surprises.
Cortex is the missing layer between your folders, your memory, and your AI. An unobtrusive background daemon that watches the directories you choose, indexes every file with a local or self-chosen cloud LLM, and makes everything searchable in milliseconds — by meaning, not just by keyword.
Bring your own LLM: Ollama, LM Studio, llama.cpp locally — or OpenAI / Anthropic / Voyage in the cloud, if that's what you want. You keep full control over where your content goes, who sees it, and how much it costs. No vendor lock-in, no forced cloud upload, no hidden token bills.
Pick any folders for Cortex to watch — any size, any count. Network drives included. No cloud upload, everything stays on your machine. Splitter detects sensitive files (.env, keys, professional-secret documents) and excludes them automatically from cloud processing.
Full-text (FTS5) plus semantic (vector embeddings) plus metadata — combined via Reciprocal Rank Fusion. Ask in natural language: “Which client asked about GDPR audit in 2024?" — Cortex returns the right hits.
Bring your own LLM: Ollama, LM Studio, llama.cpp locally — or OpenAI / Anthropic / Voyage in the cloud, if you want. Area-51 Vault for sensitive directories runs LOCAL-ONLY, regardless of the global cloud-AI setting.
Client files, contracts, correspondence — searchable by content and context, not just by filename. Sensitive client folders stay in the Area-51 Vault, everything else benefits from faster research.
PDFs, notes, research dumps — semantic search across years of material. Ask for concepts, not keywords. Your second brain, which forgets nothing and forwards nothing to third parties.
Source trees, architecture docs, decision records, old Slack exports — Cortex finds the context you only vaguely remember. All local, even when your repo is under NDA.
For one person, one device:
For small teams & power users:
Setup, understanding, workflows:
All prices net, plus applicable VAT. License renewal (12 more months of updates) is available exclusively in the mrocon portal.
Drop your email — we'll send the download link for the 14-day trial. No credit card, no auto-subscription. After 14 days the trial simply expires.
No, not without your explicit consent. Cortex runs locally by default. If you choose to use cloud LLMs (OpenAI, Anthropic, Voyage) for embeddings or answers, ONLY the snippets you allow are sent to the respective provider. Folders inside the Area-51 Vault are hard-coded local-only and ignore the global cloud setting.
Local: Ollama, LM Studio, llama.cpp (all GGUF models), Open-WebUI. Cloud: OpenAI (GPT-4 family, embeddings), Anthropic (Claude family), Voyage (embeddings), Mistral, Cohere. The list keeps growing — bring your own also means: any OpenAI-compatible endpoint works.
Windows Search and Everything find files by name and path. Cortex finds them by meaning. Ask “which file describes our 2024 GDPR audit procedure" — Cortex pulls the right PDFs even if neither “GDPR" nor “audit" appears in any filename.
No. Cortex is explicitly local-first. With a 7B or 13B model on Ollama you get usable embeddings without spending a cent on cloud. Cloud LLMs are optional and only kick in when you actively configure them.
Yes. The 14-day trial includes the full feature set. No Stripe account, no subscription — just enter your email, get the download link, install. After 14 days the trial expires; a regular order can follow if you like.
Every Personal or Pro lifetime license includes 12 months of updates. After that the app keeps running — you just stop receiving new versions. If you want to keep updating, you take a low-cost update subscription in the mrocon portal (Personal €19.90/year, Pro €29.90/year). You can pause or cancel renewal at any time.
Plannable via retainer. Scalable with automation and YouTube workflows.
Personal 1:1 sessions
No pressure, no jargon
Quick Start · Clarity · Deep Dive
Prioritised, recurring monthly
Clean docs, no black box
Automation & small integrations
Audit, workflow, pipeline/QA
Packaging & publishing flow
Apps: Niche Revealer, Video Release Mixer