Fractera
One-Click Open-Source AI Coding Infrastructure on Your VPS
Open-source platform that deploys your complete AI development infrastructure on your own VPS in 10 minutes: Hermes orchestrator, LightRAG memory, 5 AI platforms (Claude Code, Codex, Gemini CLI, Qwen, Kimi), auth, database, and file storage. Zero API fees. No Clerk. No Supabase. Your server, your stack, your data.
Deploy My ServerThe AI-Native Self-Hosting Platform
Hermes Orchestrator: Multi-Model Agentic Loops
Hermes Agent by Nous Research, deployed and configured on your VPS. Coordinates Claude Code, Codex, and Gemini CLI through shared context. Switch to API mode for autonomous agentic workflows that run without your input — every loop refines the next.
LightRAG: Persistent Memory for AI Agents
A persistent vector store by HKUDS, shared across all five coding platforms. Your codebase, every architectural decision, every solved problem — always in context. No more starting each AI session from scratch. The company brain that compounds with every iteration.
Five AI Coding Platforms, One Server
Claude Code, Codex, Gemini CLI, Qwen Code, and Kimi Code — all preconfigured on your server. Run on your existing AI subscriptions. No API keys to manage, no per-token billing. Switch platforms mid-task without losing your project context — LightRAG keeps the thread.
Dedicated VPS Environment with Custom Domain
Dedicated Ubuntu 24.04 VPS configured automatically. Custom domain provisioned, SSL issued, Nginx routed — before you write the first line of code. Recommended provider: Contabo. 4 cores and 6 GB RAM is the minimum we recommend.
Pre-Configured Secure Database & Auth Stack
Google OAuth, magic-link email, SQLite with WAL mode, file storage, and vector store — preconfigured on your server. No Clerk subscription, no Supabase invoice, no separate email provider. One stack, owned by you, billed once through your VPS provider.
Monetize AI Workflows via Skills Marketplace
Package the workflows you've solved into reusable AI Skills. Sell them in the community marketplace, share them free, or buy battle-tested recipes from other builders. Your AI infrastructure becomes a passive revenue stream — your best work earns while you sleep.
Step by step, how it works
Full Stack Ownership: Your Server, Your Domain, Your Product
Modern AI coding is easy — the hard part is owning the infrastructure. Fractera makes ownership effortless: a dedicated Ubuntu VPS, an automatic custom domain with SSL, and a production-ready product stack — all yours, forever.
Your Own Server
Your Own Domain
Your Own Product
AI in your browser
Project memory
Hermes orchestrator
One-click deploy
Skills marketplace
Backup & ownership
Your Own Server
Dedicated VPS, never rented
Your Own Domain
SSL + DNS + Nginx — automatic
Your Own Product
Code ownership, no lock-in
Your Own Server
Dedicated VPS, never rented
A dedicated Ubuntu VPS, yours forever — not a platform you rent
Vercel and Netlify deploy you in seconds — but your code, database, and users live on their infrastructure. Fractera deploys a real Ubuntu 24.04 VPS in 10 minutes. Your hardware. Your storage. Your terms. No platform repricing can take your product offline.
AI Platforms
Core AI Generation Engine: Five Platforms, One Environment
No API keys. No local setup. All five coding platforms run on your server with full terminal access and persistent LightRAG memory.
Claude Code
Writes, runs, and fixes code in your terminal. The gold standard for AI-assisted development workflows.
Codex
Browser-native AI coding agent. Full project context, no terminal required.
Gemini CLI
Long-context AI coding. Understands your entire project structure in one prompt.
Qwen Code
Open-source coding agent. No subscription lock-in — powerful and free.
Kimi Code
Context-first AI for large codebases. Excellent for refactoring and architecture work.
LightRAG
Your company brain. Persistent vector memory shared across all five AI platforms.
* The project runs on your own subscriptions to the AI platforms — Fractera does not charge any additional fees or commissions for their use. You are free to connect one, several, or all five platforms — at your own discretion.
Why it matters
The Hidden Costs of Fragmented AI Development Stacks
Modern AI development stacks are fragile, expensive, and forgetful. Here is what that costs you in practice.
The problem
Auth, storage, database, email — each service bills separately and scales with traffic. Free becomes paid, paid scales with load. Miss one payment and your live product goes dark.
How Fractera solves it
Fractera runs auth, databases, and storage on one server. One subscription, one bill. Cost does not scale with your users. Pause the business — your data stays safe.
MCP · AI Agents
Complete Server Management via Claude Code MCP Server
Building and managing a production server through an AI agent inside your chat has never been this seamless. Connect Claude, Codex, or Gemini to the Fractera MCP server — deploy infrastructure, monitor installation, and launch new environments without leaving your conversation. You can also use the MCP server to diagnose and resolve any deployment issues directly from your AI chat.
Fractera MCP server URL
https://www.fractera.ai/api/mcp* Never used MCP before? Just copy the URL above and ask your AI agent (Claude, Codex, Gemini): "please connect the MCP server at this URL." The AI will walk you through what to click inside its own interface — setup takes no more than 15 seconds. Once connected, tell the agent: "deploy Fractera for me" or "my deploy failed, here is the server_token" — it takes over from there.
What's included
Production-Ready Full-Stack Engineering Features
Fractera Lite covers 90% of what a professional application needs. Fractera Pro unlocks the remaining 10%.
Voice AI Commands
Issue coding commands and navigate content hands-free via microphone. AI agents respond to natural voice input in real time.
Auth Stack Built-in
Google OAuth, magic-link via Resend, and Credentials — all pre-configured with role management and enterprise sessions.
Database & Storage
SQLite with WAL mode, object file storage, and media service included. Scales with your project without extra subscriptions.
GitHub & Dev Workflow
GitHub sync, production coding and local development unified. Push, pull, and deploy directly from the admin panel in one click.
Platforms in 50ms
All five coding platforms preconfigured and ready to use. LightRAG global memory initialized on first start. Zero setup time.
Skills Marketplace
Discover, buy, and sell AI workflows in the community library. Share free skills or monetise your own automation recipes.
SEO, PWA & i18n
Production-grade SEO, Progressive Web App support, and multi-language routing — all configured before your first user arrives.
Element Highlighting
Click any UI element to capture its exact identifier. Communicate precise changes to the AI — fewer tokens, faster iterations.
Hermes AI Agents
Fully configured agents with self-learning memory. The most powerful AI technology available in seconds — not hours of setup.
Fork and Build a Custom White-Label AI Platform
Fractera is fully open source. Anyone can fork the GitHub repository, self-host their own instance, and build products with AI development tools — at minimum for themselves, at maximum to launch a business: deploy servers for clients and provide consulting services.
Your Private Hermes AI Agent on an Apple Silicon Appliance — Run by Voice from Telegram, Delivered as a Web Page
For B2B leaders who want an AI executive assistant, not another chat window. Hermes lives on a Mac mini or Mac Studio in your office, you brief it from your phone, it ships finished work back as a link you can open on any screen.
Fractera Black Box is a Hermes-powered AI orchestrator, shipped as a physical Apple Silicon appliance (Mac mini or Mac Studio) and configured personally by the Fractera founder. Hermes is the agent at the centre: it understands intent, plans the work, delegates to the best specialist AI for each step, and ships back a finished result — an analysis, a deck, a website, an app, an email reply — as a link you open from any device. Nothing leaves your office. Nothing lives in someone else's cloud.
How it actually works in your day
01
Brief it from Telegram, by voice
Open Telegram on your phone, hit record, speak the task: "analyze our Q3 cashflow", "find Series-A investors active in our sector", "parse the pricing pages of these 10 competitors", "reply to today's investor emails in my tone", "turn yesterday's voice memos into a strategy deck", "build a one-page site for the new product". Hermes hears you and gets to work.
02
Answers come back as a web page, not a wall of text
Hermes ships every result as a clean URL — public or password-protected. Open it on your phone in the car, project it on the boardroom screen at the start of the meeting. This is the Iron Man moment: results, not chat scrollback. A deck is a real deck. A site is a real site. An analysis is a real document. You share the link, your team opens it.
03
Runs on demand or on schedule, 24/7 in your office
Throw a single ad-hoc task at it, or set recurring jobs: "every Monday at 8 a.m., summarize last week's emails and highlight what needs my attention", "every quarter end, refresh the competitor pricing report", "every evening, draft replies to anything an investor sent today". The device works while you sleep — you wake up to finished links in Telegram.
04
Five AI platforms work behind the curtain
Hermes routes each piece of work to the best available specialist — Claude Code for engineering, Codex for general agentic work, Gemini for long-context analysis, Qwen and Kimi for cost-effective bulk passes, and LightRAG as your company's persistent memory. You never touch them directly. You speak to Hermes; Hermes decides who does what.
Pricing & delivery
By agreement — each Black Box engagement is scoped individually because each business is different. Every package includes: founder-led process audit, the Apple Silicon device (Mac mini or Mac Studio), full Hermes + LightRAG + five-platform pre-installation tuned to your business, hands-on training for you and your team, and 12 months of post-delivery support, updates and process refinement. Year two and beyond — by separate agreement.
Strictly limited capacity
A small number of partner businesses per quarter. The depth of personal involvement by the Fractera founder is the value — and that requires bandwidth. If the next slot is full, we will tell you a realistic date.
Apply for a founder consultation
Tell us about your business, the current AI stack you use (if any), and what work you would hand to Hermes first if it were on your desk tomorrow. A short conversation with the Fractera founder is the first step — no commitment, no pitch deck, just a working session to see whether Black Box belongs in your office.
Support the project
Become a sponsor — keep Fractera free and open
This project is built by one person. Many exciting features are still ahead — and your support keeps the lights on.
If you have the means to help, your name will appear on the «Sponsors» tab of our project here and on GitHub.
Coffee tier — every dollar counts
Supporter — fuel the roadmap
Champion — featured on Sponsors page
Sign in first to become a sponsor
What sponsors get
- ★Your email listed on the Sponsors page (here and on GitHub)
- ★Access to a private Telegram group for sponsors
- ★Direct line to share feature requests
Our sponsors
See everyone who supports Fractera →
FAQ
Fractera Technical Architecture FAQ
Everything you need to know before getting started.
Be so involved they can't tell if you're crazy or a genius.
Roma ArmstrongFounder at Fractera.ai