Cortex AI IDE is a privacy-first agentic IDE for Windows, built and backed by Pasons Group, a diversified business group established in 1986 and headquartered in Dubai, UAE. Cortex shipped its first public release, v2.7.0 for Windows 10 and 11, on July 9, 2026, and has kept a rapid release rhythm ever since. This is the story of why it exists, who stands behind it, and the design principle at its core: your prompts and your code should never touch anyone else's server.
The company behind Cortex
Pasons Group has grown from a single supermarket and catering service in 1986 into a group of companies spanning hypermarkets and supermarkets, shopping malls, restaurants and catering, wholesale and mobile trading, e-commerce, and real estate: more than 70 outlets serving millions of customers across the UAE. Cortex AI IDE is the group's technology venture: the same long-term, customer-first philosophy, "Your Satisfaction Is Our Priority", applied to developer tools.
That backing matters for a practical reason: an IDE is infrastructure. Developers who build their daily workflow around a tool deserve to know there's an established organization behind it, one with decades of operating history and a name it protects, not an anonymous app that might vanish next quarter. Cortex is free to use with your own API keys, and it's run with the patience of a group that has been serving customers since 1986.
Why build another AI IDE at all?
Because the tools we wanted to use kept failing the same tests. They treated Windows as an afterthought: Electron wrappers and "just use WSL." They asked developers to trust a subscription with unbounded inference costs. And above all, they asked everyone to route code and prompts through their servers and take their word for what happened there. The 2026 consolidation wave made the trust question sharper, not softer: the major AI IDEs are now business units inside giants, and your relationship is with whoever owns them this quarter.
Cortex takes the opposite path: the capabilities the big tools have (agentic loops, multi-provider models, MCP, semantic search) built into one native Windows IDE that belongs to its users. Free to use with your own keys. No subscription required to code.
The architecture is the privacy policy
Cortex's privacy story isn't a promise in a policy document, it's how the software is wired:
- Cortex is the wrapper; the model is the brain. When you chat, your prompt and code go directly from your machine to the LLM provider you chose (Anthropic, DeepSeek, OpenAI, MiMo, Qwen, OpenRouter) over TLS. There is no Cortex proxy in the middle. Architecturally, our servers cannot read your prompts or code, which is a much stronger guarantee than "we don't."
- Downloading is anonymous. Grab the installer and go, no account, no sign-up wall.
- Signing in reveals exactly one thing: your email. That plus your plan is all the server knows. What you're building, what you're asking, which files you open, nothing is tracked, because the tracking was never built.
- Your API keys never leave your machine: Windows Credential Manager, DPAPI-encrypted, with an AES-256-GCM local backup.
Why "trust us" isn't good enough
The industry has already seen what happens when developers take a vendor's word for it: popular AI coding tools have been caught sending far more of a project than any coding task required, with the data controls users relied on making no difference. The lesson is general: when your tool routes data through a vendor, you're trusting configuration you can't see, changeable remotely, by people you'll never meet.
The only architecture that survives that lesson is the one where the data never leaves in the first place. That's Cortex's design, and it's why the code is being opened for inspection: core components are public on GitHub today, with full open-sourcing planned as each part clears security review, so third parties can verify the no-tracking claim instead of taking ours on faith. Fitting, for a product whose whole thesis is verify, don't trust.
Shipping in public
Development ends the day real users arrive; then the real education starts. The changelog is public and unvarnished:
- July 9: v2.7.0. Launch: agentic editing, BYOK for five providers, full editor, terminal, project memory.
- July 10-11: v2.7.1 through v2.7.6. Reality arrives: saved API keys silently ignored after install, panels rendering blank on certain GPUs, a ghost "capsule" window. Five releases in three days, fixing what testing on one machine can't catch, other people's machines.
- July 12: v2.8.0. MCP support, Live Preview, and performance work that took a 40-second chat-open freeze to near-instant.
- July 13: v2.8.1. Core source code lands on GitHub, and the loop engine's token/dollar budgets become real enforcement, not a checkbox.
- July 14-18: v2.8.2 through v2.8.6. Antivirus stutter fixed with background-thread writes, vision-model image handling rebuilt, Claude Sonnet 5 and Kimi K3 added within days of their releases.
On Windows, the hardware and antivirus matrix is the boss fight, features are easy compared to running correctly on every GPU driver and under every real-time scanner.
No forced subscription, that's the style
The IDE is free with your own API keys, forever, you pay model providers directly, and at BYOK prices that's dramatically cheaper than fixed AI-IDE fees. The $10/month Pro plan exists for the things that genuinely need servers, hosted web search, semantic embeddings, OCR, MCP connections, and as a way to support the project if you believe in it. Subscribe when you need it, cancel when you don't, and the IDE keeps working either way. No pressure, no forced auto-renewal games. Pasons Group built its name on putting the customer first; Cortex's business model has to live up to that name.
What's next
The roadmap runs on the same loop as the product: real user reports in, verified fixes out, every release note answers an actual email. If you want to pressure-test it, download Cortex, hand it a real task, and tell us what breaks at [email protected]. Anonymous downloads mean we won't know you're there, so the emails are how we learn.