Nebula

The description states that Nebula is an AI assistant that connects local AI models, persistent memory, project context, research, voice, and computer tools through one interface. It supports:

• Chat with locally hosted models via LM Studio
• Automatic model routing for conversation, coding, and review
• Persistent conversations, folders, search, memory, and project context
• File inspection, terminal commands, app launching, and execution receipts
• Approval, Safe, and session-only Full Access execution modes
• Web search and research with source cards
• Voice interaction and a desktop ambient overlay
• A private iPhone companion connected to the PC
• Diagnostics, timelines, skills, task history, and model health information
• Cancellation and Stop Agent behavior across model and tool operations

The PC remains the source of truth; models, private memory, tools, and project files stay on the user’s computer.

The description states that Nebula was built to feel like a real part of the user's computer rather than another website. It positions itself as a local-first AI operating layer with one consistent identity across Windows and iPhone.

It also claims to be a private assistant that avoids cloud dependency, supports persistent memory, and integrates safely with local tools.

The description states that Nebula is built for users who want an AI assistant that feels like a real part of their computer. It targets individuals who value privacy, local control, and integration with existing tools.

It also implies a personal user base rather than enterprise or B2B customers.

The description does not state anything about pricing, monetization, or business model. It is described as an independently built prototype for a hackathon.

The project uses:

• React and TypeScript for interfaces
• Tauri and Rust for native Windows capabilities
• SQLite for durable local data
• LM Studio’s OpenAI-compatible API for local inference
• Capacitor for mobile client
• Server-sent events (SSE) for streaming communication between mobile and desktop

It includes a central orchestrator that selects models, builds context, loads memory, invokes skills, executes approved tools, and returns unified responses.

The description states that Nebula was built independently by a 14-year-old developer. It shipped a public Windows build while keeping models and private data separate.

It also mentions accomplishments such as:

• Built a working local AI platform rather than a static demonstration
• Connected Windows and iPhone through a private streaming bridge
• Created durable conversations, memory, project awareness, and diagnostics
• Implemented model routing and local tool execution

However, there is no evidence of user adoption, customer feedback, or usage metrics.

The description does not mention any competitors or market context. It is self-contained and does not reference existing solutions in the local AI assistant space.

• Unverified claims: All descriptions are self-reported and unverified.
• No commercial traction: No evidence of revenue, customers, or adoption.
• Limited team size: Only one developer (a 14-year-old) is involved.
• Prototype nature: The product is described as a hackathon submission, not a mature product.
• No safety or compliance data: No mention of regulatory or ethical safeguards.
• Unclear scalability: No evidence of how the system would scale beyond a single developer’s environment.

1. What is the actual user base, if any, for Nebula?
2. Has the product been tested with real users beyond the developer?
3. How does Nebula handle model updates and compatibility across different local AI environments?
4. Are there plans to monetize or commercialize this product?
5. What are the technical limitations of the current architecture that would prevent scaling?
6. How is data privacy and security ensured in a local-first environment?
7. What is the roadmap for expanding beyond Windows and iPhone?