Invoke Studio is a desktop AI coding IDE with visual planning, design canvas, and intelligent agents. Map features on Boards, draw dependencies, and let AI build them in order. Design pages in Canvas — drag, resize, edit visually — then export as production code. Experiment safely in Sandbox with AI-powered merging. Run parallel agents, create custom subagents and agents. Works with Claude, OpenAI, Google, xAI, and Ollama. Free with your own API keys.
Hey Product Hunt 👋 I'm Bharath, the maker behind Invoke Studio.
Every AI coding tool today can write, edit, and review code. That's table stakes. What's missing is everything around the code — planning what to build, designing how it looks, and safely experimenting before committing.
Invoke Studio is a desktop IDE that covers the full development loop:
Boards — Lay out features as cards on a canvas, draw dependency arrows, @mention files, hit Build. The AI implements the whole plan in order.
Canvas — Describe a page, AI generates it with real design. Edit visually — drag, resize, tweak — then export into your actual codebase as production code.
Sandbox — Fork your entire project into an isolated copy. Experiment freely. When you're done, AI merges your changes back — even if your main project has changed since. It understands the intent of both sides, resolves conflicts intelligently, and explains its reasoning..
Skills — Teach your agents reusable capabilities with instructions, scripts, and references. Follows the open Agent Skills spec — cross-compatible with Cursor and Claude skill directories.
And yes — it has a full code editor with TypeScript LSP, integrated terminal, live preview, AI code review, parallel agents, subagents, checkpoints, memory, and browser automation built in.
Works with Claude, OpenAI, Google, xAI, and local models via Ollama. Every feature is free with your own API keys. Use WELCOME70 for 70% off your first month if you want built-in credits.
the "draw dependency arrows, hit Build" approach is interesting, most agentic IDEs just hand the whole task list to the model at once and hope it figures out the order.
does the dep graph actually affect parallelism, like does it run independent branches concurrently or is it always sequential?
This looks awesome, congrats! Any plans for team collaboration features or is it mainly solo for now?
I like the visualization on dependencies and data flow. This is personally something I plan out before rolling out a feature, and it takes time. Looks interesting and useful.
Visual planning boards for agentic coding is a good call. The hard part isn't getting agents to write code - it's defining what to build clearly enough that they build the right thing. Multi-model support across Claude, OpenAI, Google, xAI, and Ollama is a lot to maintain but the flexibility is real. If you want to catch bugs while launch traffic is up, we built a free community stress-testing tool called VibeFix Playground. Post your URL, people try to break it, reports come in with screenshots.
the board and sandbox together make sense, but after a few iterations things usually start drifting a bit, do people keep updating the board or does it get ignored over time?
This is exceptional, I was using clickup and the claude code as well as the Xcalidraw to manage my projects, an all in one solution was much needed thanks man!
The Boards + dependency mapping before agents start building is a legitimately different take. Most coding agents are just "here's a prompt, generate code" - having explicit task ordering baked into the IDE means the agent isn't deciding what to tackle next based on vibes. How does it handle when a dependency is partially built? Does the dependent task queue or does the agent try to work around it?
