Wandesk
Build Your Own AI Desktop
Start new thread

Wandesk - Build Your Own AI Desktop

by•
Wandesk is an AI desktop. Build the apps you need just by describing them. Plug in Claude Code, Codex, DeepSeek, OpenAI, Kimi, Qwen — anything OpenAI-compatible. Apps share context. AI remembers you. All local. No signup.

Add a comment

Replies

Best
Maker
📌

Hello everyone 👋

I'm Yang, building Wandesk for a while now.

The short version: Wandesk is an AI desktop. You describe an app, AI builds it right there on your machine — a calorie tracker, a reading list, an invoice generator, whatever.

Apps live alongside chat, files, tasks, and memory. AI remembers context across all of them. Plug in your own API keys (Claude, OpenAI, DeepSeek, Kimi — anything OpenAI-compatible).

🔒 100% local. 🆓 100% free. No signup, no account, no cloud lock-in. Your apps, your data, your machine.

Why we built it: AI products today still treat conversation as the only surface. Conversation is good for intent, bad for persistence — you don't balance your budget in a chat window. We wanted a place where AI-generated software has shape and stays.

Available now on macOS and Windows.

Would love to hear:

- What's the first app you'd want it to build for you?

- Where does it break in the first 5 minutes? (it will. tell us.)

— Yang

 what a cool idea, congrats on launching! I'd probably want it to build me some sort of productivity tracker that reflects tasks across different categories (work, side projects, life admin). To this point, is there shared context across apps? If I build a fitness tracker and productivity tracker can the fitness tracker pass context to the productivity tracker?

Maker

   Yes, all applications can share context. It will remember your preferences and help you handle more continuous real-world tasks.

Maker

 thank you 🙏 Yes — shared context is the whole point.

The apps aren't wired together directly. They live in one workspace with one AI and one shared memory above them, so the AI just reads one app and acts on another.

For your cross-category tracker: tell it once "I'm training for a marathon, keep mornings free" and it factors that in everywhere. Memory carries across every app.

 how does the crossapp shared context compare to using standard MCP bridges when calling different agents?

Maker

 Wandesk's cross-app context isn't a bridge. Apps share one local store + one memory, with the AI sitting above all of them — so context is ambient and persistent, no per-pair wiring. Tradeoff: it's scoped to that one local workspace.

Complementary, not competing — and Wandesk can speak MCP when it needs to reach out.

 gotcha

 Big fan of the AI remembers context across apps framing. That persistence layer is genuinely what most AI desktops are missing.

Quick technical question on the MCP side, since Rick mentioned Wandesk can speak MCP when it needs to reach out: does Wandesk surface available MCP servers for the AI to discover, or does the user have to manually add each one by URL? Asking because if there's a registry pattern, that changes how MCP server builders should be packaging things to show up natively in Wandesk apps.

love the "it will" first 5 minutes quote! love you for your brutal honesty.

 The local-first approach is refreshing — especially seeing you prioritize data residency over the cloud-convenience trap. The context memory across apps/chat/files sounds like it solves a real friction point where most AI tools force you to re-explain yourself constantly. Curious if you're seeing users request specific integrations yet, or if the OpenAI-compatible setup is handling most early needs.

the positioning sits in an interesting gap between something like Raycast AI and a full local IDE. curious who your early users actually are because i can picture two very different people finding this useful. one is a developer who wants a faster way to prototype throwaway tools without spinning up a project. the other is a non-technical person who genuinely can't code and needs something that works end to end without touching a terminal. those two users need pretty different things from the same product

Maker

 thank you, Ansari, this is definitely something we ran into during development. Many details were designed for non-technical users, but in reality, developers may end up using it more. That’s also one of the reasons we made it open source: capable developers can optimize it themselves, while non-technical users can follow the standard workflow.

   I was going to ask if you saw this as a developer tool - thanks for the reply.

Maker

 That’s a very accurate read.

Our earliest users are mostly the first group: developers/builders who want to prototype useful local tools without spinning up a full project every time.

The second group is where we want Wandesk to go, but it needs much more polish: safer defaults, stronger templates, better error recovery, and less visible technical surface area.

So we’re starting with builders, but the long-term direction is exactly: anyone should be able to create their own local apps without touching a terminal.

 That tension is real for almost every developer tool trying to cross over to non-technical users. The features that make it powerful for developers are usually the same ones that make it confusing for everyone else.

Maker

   Agreed, balance is key. I believe AI will eventually reach general users and benefit everyone.

I like the natural language angle here, especially if the output stays editable and understandable. The hard part is not just generating the first version, but helping users keep control once the project grows.

Maker

   Yes, that’s exactly what we designed it for: users can customize the apps they need without losing control of version management.

   That version management part is important. Natural language is great for starting fast, but once people begin customizing, they need to understand what changed and be able to roll things forward without losing control.

Maker

 agreed — the first version is the easy part, keeping it manageable as it grows is harder.

Our approach is structure: every app is generated in a clear, layered shape (UI / logic / data + an the AI reads before changing anything), so edits stay scoped instead of rewriting the whole thing. They're real editable files too, so you can adjust by hand or have the AI touch just one part.

Still rough in places, and we're improving it as we go.

 That structure makes a lot of sense. as a source of truth is a smart way to keep the AI from treating every edit like a blank slate. Scoped changes + real editable files feels much more sustainable than “generate once and hope it doesn’t drift.”

Congrats on the launch, looks like a cool idea! I'm currently planning an app launch myself and ticking off hundreds of tasks across 12+ weeks. A small Wandesk app that holds the checklist, tracks status, lets me add notes per task, and surfaces what's overdue could be genuinely better than what I'm using now (a Notion page!) Will take it for a spin.

Maker

 Thank you so much, and feel free to give it a try. If you have any suggestions, we’d love to hear your feedback anytime.

Maker

 thanks! That's a great fit — a launch checklist with per-task notes, status, and an overdue view is exactly the kind of focused tool it does well.

Tip when you build it: describe it in one go, including the "surface what's overdue" part, then refine in chat ("group by week", "add a notes field", etc.) — iterating beats trying to get the perfect prompt first time.

Would genuinely love to hear how it stacks up against the Notion page once you've used it for a bit.

I love this! The first thing I am going to do is build a grocery calculator for me and my roommates! <3

Maker

 Thank you! Glad it’s helpful for you. If you run into any issues while using it, feel free to reach out to us anytime.

Maker

 love it 😄 roommate grocery splitting is a perfect first build. Tip: tell it who's in the house up front and it'll keep the running balances per person. Let me know how it goes! 🙏

The "local, free, no signup" part is what I actually care about here, since most of these tools quietly require a cloud account the moment you want to save anything. Very cool pros

What model is running the generation locally, and how far does a mid-range machine get before output quality starts to drop? Also curious what "describe any app" means in practice when the description is vague or contradicts itself.

Maker

 Thank you, Florent. In fact, you can choose any mainstream model you like. Our product runs on your personal computer, so it's compatible with most computers. You just need to describe your needs clearly in natural language, and I believe Wandesk won't disappoint you. Go ahead and give it a try.

Maker

 thanks 🙏 — one honest clarification, because it matters:

Wandesk doesn't run the model itself. "Local" means your apps, data, files and memory stay on your machine — not that inference is local. You plug in your own API key (Claude, OpenAI, DeepSeek, Kimi…) and generation goes to that provider.

So your hardware doesn't gate output quality — that's on whatever model you point it at. A mid-range machine is fine; it's just running the desktop, a couple of Node services, and writing the app's files. Quality scales with the model, not your RAM.

(And since it takes anything OpenAI-compatible, if you want truly local inference you can point it at Ollama / LM Studio — then it's local end to end.)

On "describe any app": it's iterative, not one-shot. Vague → it makes reasonable assumptions and builds a v1 you refine in chat. Contradictory → it picks an interpretation and you correct it. Small focused apps come out solid; big complex ones it'll struggle with on the first pass — being honest there.

the shared memory across apps sounds useful but also a little scary. if one app pulls in a bunch of work context and another is personal stuff, can you scope what each app can see or is it one big pool?

Maker

 today it's effectively one shared pool — the AI sees your memory across apps, there's no per-app permission boundary yet. You're pointing at a real tradeoff.

What softens it now: it's 100% local (nothing leaves your machine), and memory is opt-in — you choose what gets saved, so keeping work and personal separate is in your hands, just not enforced per-app.

Per-app scoping ("this app can't see that") is exactly the kind of control we want to add. Genuinely useful flag — thanks 🙏

Maker

Hello everyone 👋

Excited to share Wandesk.

Wandesk is built around a simple but often overlooked idea: AI shouldn’t live only inside a chat box.
For many people—especially those who don’t write code every day—software is much easier to understand and use when it actually takes shape. It should have windows, panels, notebooks, boards, and files—not just repeated prompts and results buried in a long chat history.

Wandesk is a graphical AI desktop 🖥️
You can start with an idea, turn it into a usable app, and keep using, modifying, and managing it in the same workspace.

More importantly, Wandesk aims to make AI-generated software not just something that gets “generated,” but something that can truly stay, be organized, and continue serving your daily work and life.

  • Your apps don’t disappear into prompts ✨ — They stay on your desktop as real tools that you can reopen, reuse, and keep improving.

  • Different kinds of work stay in their proper place 🗂️ — Notes, ledgers, boards, and files can live side by side instead of being piled into one endless conversation.

  • AI works across the entire workspace 🤝 — Apps can share context, remember preferences, and help with more continuous, real-world tasks.

  • It’s built for personal software 🛠️ — Whether it’s small utilities, internal tools, personal projects, mini games, or quirky but useful workflows, they can all be created more easily.

  • You stay in control 🔓 — Wandesk is open source and free, so you can inspect it, use it, and adapt it to your own needs.

AI is making software creation easier than ever, but it can also make things messy very quickly.
If everyone can generate tools, then people also need a clearer and more stable way to hold, organize, and manage what they create. That’s the layer Wandesk wants to provide: making AI-generated software something truly usable, sustainable, and within your control.

If this direction sounds interesting, we’d love for you to download it and give it a try 🚀, and we’d really love to hear your honest feedback.
If anything feels awkward, unclear, or still far from good enough, please tell us directly. Honest feedback is exactly what helps us make it better 💬

If you believe in this direction, we’d also really appreciate your support with an upvote 🙏

Where does the shared context and memory live, and can you inspect or wipe it per app?

Maker

 it all lives locally in the app's workspace folder (~/Library/Application Support/…/workspace): app data in per-app SQLite DBs, memory in a memories table, files on disk.

Inspect: the Memory app lists every memory — read, edit or delete each one; app DBs are plain SQLite you can open.

Per-app wipe: app data, yes (delete its DB). Memory is currently one shared pool, not partitioned per app — so you wipe memories individually, not "this app's memories" as a group yet. That scoping is on our list.

Full reset: uninstall + delete the workspace folder

This reminds me of a new version of Perplexities. Computer. I’m intrigued for sure to say the least. I used an old laptop. Gutted it and created an openclaw-puter would love to see what this can do

Maker

 

haha an openclaw-puter — honestly that's exactly the kind of setup I was hoping someone would point at this 😄

Light enough to run on a gutted old laptop (the heavy lifting goes through your API key, not the CPU). And the fun bit: you don't have to drive it from the chat box — you can point an external agent at Wandesk and let it run the desktop for you. So your openclaw could literally be the thing driving it.

Would love to see that combo in action. Go break it and tell me what falls over 🛠️

12
Next
Last