Why I Built My Own AI: The Case for Self-Hosted Domain Agents (Kulvex)

Bruno Galtranch built Kulvex AI, a self-hosted AI platform running an 80-billion parameter model on consumer GPUs, after growing frustrated with privacy and cost concerns from cloud-based AI services like OpenAI. Kulvex operates 17 specialized domain agents—handling tasks from home automation to code maintenance—and includes a "Self-Evolution" agent that autonomously fixes bugs and improves its own codebase. The author notes that while self-hosting offers privacy, cost savings at scale, and reliability, it requires significant hardware investment and is best suited for heavy users rather than casual ones.

Originally published on the AstroLexis blog. Cross-posted here for the community. In 2024 I got tired of paying OpenAI to know everything about my house, my conversations, my calendar, my code, and my family. So I built Kulvex AI — a self-hosted AI platform that runs an 80-billion parameter model on a pair of consumer GPUs in my office, exposes 17 domain agents over a private API, and handles everything from Zigbee lights to messaging across eight platforms. Here's why I built it, what it actually does, and where the trade-offs land in 2026. For about eighteen months I lived inside the OpenAI / Anthropic ecosystem like everyone else. Then a few things piled up at once: The breaking point was simple: I wanted an AI that would still work in five years exactly the way it works today, on hardware I own, that I could point at any task without asking anyone for permission. That product didn't exist. So I built it. Three pieces: "AI assistant" is too vague. What Kulvex actually does is split work across specialized agents: 🏠 Home Automation · 📱 Messaging Hub · 📅 Calendar · 📧 Email · 📰 News Curation · 🎵 Music · 🌤️ Weather · 📷 Cameras Hikvision · 💡 Lights Zigbee + Tuya · 🔌 Energy/Solar · 🍔 Food · 🚗 Vehicle · 📚 Research · 💰 Finances · 📝 Notes · 🛠️ Code · 🧬 Self-Evolution Each agent has a narrow job, its own toolset, and its own context budget. When the user says "turn off the kitchen lights and tell me what's on the calendar tomorrow," the platform routes to two agents in parallel. Neither agent needs to know about the other. This design made Kulvex tractable for me as a solo developer. The general-purpose "do everything" AI model is hard to make good. Seventeen narrow agents, each replaceable independently, is much easier to ship. One of the 17 agents is called Self-Evolution. Its job is to read Kulvex's own codebase, identify bugs or improvements, write the fix, run the test suite, and — if everything passes — commit and deploy. Three guardrails make this safe: OWNER-DIRECTIVES.md at the repo root, which tells it what it's allowed to modify typos, dead code, small refactors, dependency upgrades and what it's NOT auth, payments, model selection logic, API surfaces .In four months: ~340 PRs opened, ~280 merged. Meaningful chunk of the 200K-line codebase maintenance offloaded. Self-hosted AI in 2026 means buying GPUs: The math gets better the more you use it. Hardware costs the same whether I run 10 queries or 10,000. After breakeven, marginal cost approaches zero. For users who don't want to run their own GPU, Kulvex has a hosted "Home" tier where we run the server on shared infrastructure — still no cloud LLM vendor in the loop, model weights pinned, but you're renting compute instead of buying. The 80B model on the RTX 5090 produces output that, for 95% of tasks code review, drafting, knowledge retrieval, agent orchestration , is roughly comparable to GPT-4-class. The frontier Claude Opus 4.x, GPT-5 still beats it on hard reasoning. For those cases Kulvex's orchestrator can route to Claude or GPT if the user opts in. I rarely turn that on. Privacy + cost + reliability beat marginal capability for my workload. Honest list: For casual AI users, cloud is still better. Kulvex makes sense once your usage is heavy enough that the privacy + cost + reliability balance flips. The on-prem tier never phones home except for license validation. — Bruno Galtranch, founder, AstroLexis LLC. If you self-host or are considering it: contact@astrolexis.space.