Invoke - Agentic coding IDE with visual planning boards and canvas
by•
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.
Replies
Invoke
@mention @yugintech How well does the AI handle merging complex changes in large TypeScript/React codebases with multiple devs, like resolving intent across divergent branches?
Invoke
@swati_paliwal Right now Sandbox is designed for single-dev workflows. You fork your own project, experiment, and merge back. It's not handling multi-dev branch merging across teams yet.
It works well on large codebases. The AI reads both sides, understands what changed and why, and merges accordingly. It's not just doing line-level diffs, it looks at the context around the changes.
That said, we're still improving it. The more complex the divergence, the more careful it needs to be. We're shipping updates regularly and this is one of the areas we're actively working on.
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?
Invoke
@mykola_kondratiuk Thanks! That's exactly why we built it that way. Most agents just take a prompt and figure it out on the fly — Boards lets you lay the whole thing out first so the agent actually knows what it's working with.
You can use it for dependency ordering, but it's also just for showing how features connect and relate to each other. Like "auth flow ties into dashboard which ties into user settings" — the agent sees that full picture, not just isolated tasks.
When you hit Build, everything on the board — features, descriptions, file references, connections — goes to the agent as one structured prompt. It reads the flow, respects the order, and builds with the whole system in mind.
For your question about partial builds — right now the whole board goes as a single plan, so the agent works through it sequentially following the connection order. It's not a separate queue system yet, but that's something we're thinking about. We're constantly shipping improvements so this kind of feedback genuinely helps shape what comes next.
@yugintech That makes sense - the upfront planning cost is worth it when agents are doing complex multi-file work. Excited to try it out.
Invoke
@mykola_kondratiuk Absolutely! That's the core idea behind Boards, spend a few minutes planning visually upfront and the AI executes way more accurately across multiple files. Excited to hear how it goes! Also we're offering 70% off your first month with code WELCOME70 and 50% of unused credits roll over to the next month so nothing goes to waste. Let us know if you need any feature or improvement!
@yugintech Shipping it - will report back.
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!
Invoke
@nayan_surya98 Thanks so much! That's exactly the problem we wanted to solve — too many tools, too much context switching. Give it a try and let us know how it goes. We're constantly improving based on feedback like yours!
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?
Invoke
@artem_kosilov Fair point. Most planning tools end up like that, you make a plan and never look at it again.
Boards are a bit different though because the agent actually reads them every time you hit Build. So there's a real reason to keep them updated. Add new features, rework connections, change the flow, and the agent picks it all up.
Some people use them as a one-shot plan and move on, that works too. For bigger stuff, creating separate boards per milestone works better than trying to maintain one giant one.
With Sandbox, the combo is nice. Plan on the board, experiment in sandbox, and if things drift you can rethink the board and spin up a fresh sandbox.
We're also thinking about the agent suggesting board updates based on what actually got built. Appreciate the feedback!
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.
Invoke
@syaman Thanks! Planning dependencies and data flow before building saves so much time, especially when AI agents are handling the implementation. That’s exactly why we built Boards so you can visually map it all out and let the agent follow the plan. Give it a try and if you need any feature or improvement, let us know. We’re constantly improving it!
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.
Invoke
@onryo_builds Thanks! You are right, the hard part isn't getting agents to write code, it's defining what to build clearly enough. That's exactly why we built Boards so you can visually define the plan before agents start executing. Appreciate the kind words!
This looks awesome, congrats! Any plans for team collaboration features or is it mainly solo for now?
Invoke
@ermakovich_sergey Thanks so much! Right now Invoke is focused on the solo developer experience. Team collaboration is something we’re exploring but we want to make sure the core product is solid first. Would love to hear what kind of team features would be most useful for you, that’ll help us prioritize what to build next!