AI app for it and development · no coding needed
Local assistant desktop console with model hub
Reduce tool sprawl while keeping assistant data and workflows on the buyer's own machines.
Made for: Developers and IT teams who need a local AI assistant they control
What it does for you
The problem
Teams rent several desktop AI chat tools and cannot keep prompts, files, models and automations in one owned environment.
What it gives you
A source-linked assistant and administrator console
What you give it
Installed desktop runtimelocal modelsAPI keysMCP connectionsfile collections
Build your own version of Qwen Chat for Desktop, Alice 4.0 and more
One app with what these 3 AI tools do, yours to keep and change: Qwen Chat for Desktop, Alice 4.0, Jan.
Everything these tools do, in one app
- Native desktop app Runs as an installed application on your computer for smooth integration.Found in Qwen Chat for Desktop, Alice 4.0, Jan
- Local AI chat Lets you chat with an AI directly on your device.Found in Qwen Chat for Desktop, Alice 4.0, Jan
- MCP support Enables smarter and faster local agent interactions.Found in Qwen Chat for Desktop, Alice 4.0
- Multitasking and parallel processing Handles multiple concurrent agent processes to improve efficiency.Found in Qwen Chat for Desktop
- User control over environment Gives you control over your local environment and workflows.Found in Qwen Chat for Desktop
- Hotkey summon and overlay Calls the assistant from any app with a single hotkey for fast, in-context interactions.Found in Alice 4.0, Jan
- Custom assistants Lets you create and save assistants that remember context, documents, and preferences.Found in Alice 4.0
- App integrations and automations Connects to services like MCP, Zapier, Make, custom APIs, and webhooks to run workflows and interact with local files.Found in Alice 4.0
- Multi-model support Lets you use multiple AI models, including offline options.Found in Alice 4.0, Jan
- Use your own API keys Allows you to provide your own API keys for model access.Found in Alice 4.0
- Pre-built prompts and snippets Provides ready-made prompts, assistants, and snippets to speed up use.Found in Alice 4.0
- Open-source The software is open-source for community development and transparency.Found in Jan
- Offline operation Runs entirely offline on your computer to keep data private.Found in Jan
- Built-in API server Provides a local API server that mimics OpenAI capabilities for integration with compatible applications.Found in Jan
- Model Hub Access and manage a range of AI models, including drop-in replacements for OpenAI’s API.Found in Jan
- Connect to cloud AIs Offers the option to connect to cloud-based AI models.Found in Jan
- Chat with your files Helps you interact with and extract insights from your digital content.Found in Jan
- Third-party extensions Supports 3rd party extensions and adjustable AI parameters for customization.Found in Jan
How it works, step by step
- Install and run as a native desktop application
- Chat with a local AI on the device
- Connect MCP tools for local agent actions
- Run multiple agent processes in parallel
- Let the operator control the local environment and workflows
- Summon the assistant from any app by hotkey overlay
- Create and save custom assistants with context and documents
- Connect services, APIs and webhooks for automations
- Switch between multiple models, including offline ones
- Accept the user's own API keys
- Provide pre-built prompts, assistants and snippets
- Keep the source open for community development
- Operate fully offline when required
- Expose a local OpenAI-compatible API server
- Manage models through a model hub with drop-in replacements
- Connect to cloud AI models when the operator allows it
- Chat with local files and extract insights
- Support third-party extensions and adjustable parameters
- Compare the reviewed result with the recorded baseline and value assumptions
- Capture corrections and named-owner approval before consequential use
- Export a versioned source-linked assistant and administrator console with source references and unresolved questions
Build it yourself with your AI system
Build this app yourself, no coding needed
Start with a quick version you can try in a few minutes. Like it? Then build the full app by copying and pasting our step-by-step instructions: everything is prepared for you.
Sign in to see how to build it yourself
Build a quick version to try, or get the full app pack for Local assistant desktop console with model hub with the step-by-step building instructions. You don't need any technical skills: you copy, paste and answer a few questions. Both are included in the membership.
4 Have it built for you days to a few weeks
Rather not do it yourself, or want it fully tailored to your data, your way of working and your brand? Nexibeo builds Local assistant desktop console with model hub with you.
What's in the app pack
Included in the Complete AI Training membership.
- The building instructions your AI follows, step by step
- The questions your AI will ask you about your business before it starts
- A clickable demo you can open in your browser, to see how it should work
- A detailed blueprint of the screens, the information it keeps and the checks it runs
Become a member to get the app packAlready a member? Sign in
The files, for the technically curious
- START-HERE.mdHow to build it with your own AI (read first)3 KB
- README.mdOverview and links4 KB
- questions.mdQuestions to answer before you build2 KB
- prompt-cloudflare.mdThe full build prompt, hosted on Cloudflare25 KB
- prompt-vps.mdThe same build on your own server (Docker)25 KB
- spec.jsonData model, API, AI pipeline, acceptance criteria12 KB
- demo/index.htmlThe working demo on sample data196 KB
Questions
Do I need to know how to code?
No. You copy and paste the prompts on this page into ChatGPT or Claude, and the AI does the building. When it asks you something, you answer in your own words.
What does it cost?
The quick version, the app pack and the step-by-step instructions are for members: you pay the membership price, not a price per app (see the plans). Building the full app uses your own ChatGPT or Claude subscription. Putting it online is often cheap or no cost at the start, and your AI tells you before anything costs money.
How long does it take?
The quick version: about two minutes. The real app: an afternoon for a first version you can use, longer if you want every feature.
Can I change it to fit my business?
Yes. Tell your AI what to change in plain words, like “add a column for the price” or “use our logo and colours”. Or have Nexibeo build and customise it for you.
More detailsHow the AI works, safeguards and what to build first
Reduce tool sprawl while keeping assistant data and workflows on the buyer's own machines. For developers and IT teams who need a local AI assistant they control, convert installed desktop runtime, local models, API keys, MCP connections and file collections into a source-linked assistant and administrator console. The benefit is a testable hypothesis, measured through tasks completed per operator hour and corrections after assistant output; do not assume that AI output alone produces business value.
Confirm the buyer's problem and scope, collect installed desktop runtime, local models, API keys, MCP connections and file collections, then follow this sequence: 1. Install and run as a native desktop application. 2. Chat with a local AI on the device. 3. Connect MCP tools for local agent actions. 4. Run multiple agent processes in parallel. 5. Let the operator control the local environment and workflows. 6. Summon the assistant from any app by hotkey overlay. 7. Create and save custom assistants with context and documents. 8. Connect services, APIs and webhooks for automations. 9. Switch between multiple models, including offline ones. 10. Accept the user's own API keys. 11. Provide pre-built prompts, assistants and snippets. 12. Keep the source open for community development. 13. Operate fully offline when required. 14. Expose a local OpenAI-compatible API server. 15. Manage models through a model hub with drop-in replacements. 16. Connect to cloud AI models when the operator allows it. 17. Chat with local files and extract insights. 18. Support third-party extensions and adjustable parameters. Resolve uncertain cases with qualified reviewers, approve a source-linked assistant and administrator console, and measure tasks completed per operator hour and corrections after assistant output against a documented baseline.
How the AI works
Use AI to interpret permitted inputs, suggest structured mappings and generate candidate outputs for the stated task modules. Use deterministic code for arithmetic, schema validation, hard constraints and reproducible tests. Review source-linked explanations and uncertainty before accepting results. Local model choice, offline mode and API keys remain under operator control; final code, configuration and security decisions remain human. A model suggestion is never a verified fact, professional decision or authorization to act.
Safeguards
Preserve operator control, source attribution, credential handling and usage permissions. Operators approve substantive changes and external actions. One desktop operating system and one local model runtime; final code, configuration and security decisions remain human. Keep all consequential actions under authorized human control and do not fabricate missing inputs, permissions, professional judgments or market evidence.
What to build first
Pilot scope: One desktop operating system and one local model runtime; final code, configuration and security decisions remain human. Implement one approved input format, a bounded representative case set and the first two task modules: install and run as a native desktop application; chat with a local AI on the device. Support the remaining modules with operator review: connect MCP tools, run parallel agents, hotkey summon, custom assistants, automations, multi-model switching, own API keys, pre-built prompts, open source, offline mode, local API server, model hub, cloud connections, file chat and extensions. Include source references, corrections, basic organization access, approval states, export and value measurement. Use managed operator assistance for unresolved exceptions. The cost estimate covers this narrow prototype, not unrestricted multi-tenant scale, complex production integrations, specialist certification or physical operations.
What it can connect to
Operator-owned models, API keys, MCP servers, local files and permitted cloud AI endpoints. Cloud asset storage, design-file import/export and publishing destinations. Start with file exchange and validate destination specifications before promising direct publishing. Start with authorized file exchange. Validate current provider access, usage rights and schema behavior before promising a connector.
The screens in detail
Primary screens: Assistant workspace, Model and connection settings, Admin console. Use a left rail for assistants, chats and files, a large central chat and task canvas, and a right-hand panel for sources, model choice and run state. Let users compare model outputs side by side. Display draft, needs review and approved states. Provide a local API endpoint view with request logs. Make the task-specific outcome a source-linked assistant and administrator console visible beside its evidence, review state and value baseline.
