For you, your agent, your coworker and their agent. It holds the team's critical know-how, research, decisions and data. But it's not a dead storage. It's a workspace that makes the context workable for humans as well as agents.
@floschirmer Yes!! I think we all learned our lesson from tools that came before. You need something that can work with local agents + is interoperable.
This idea of a shared brain for both humans and agents is really interesting . Most tools stop at documentation but this feels more like active thinking infrastructure.
@aarav_pittman Thats exactly what we are going for! Normal when you think about context management for AI you would think "lets upload 100k slack messages and search them" but we found most value in context that is checked and handcrafted by humans. AI can then work on top of it and actually produce good output.
@aarav_pittman on the point! you can aggregate all your team work with their agents, plus make your local/coding agent connected to the context and vice versa
@aarav_pittman Yes, the shared brain isn't just an archive of md files. It's also about being able to seamlessly levarge all the context you've been building.
@aarav_pittman active thinking interface thats exactly it
Report
The Claude chats plus Obsidian plus docs plus Slack mess is very real. Nice to see someone attacking the workflow around the work, not just another chat UI.
@amara_diarra canvas is really a different UI but works so well for thinking work. I am coming from design background so canvases feels like home for iterative creative work. Happy you like it!
@amara_diarra Yes, navigating the mess of AI tools and artifacts is what big part of work in 2026 is about. With Kanwas we don't want to throw another tool into the mess, but actually make the whole process simpler, more powerful and collaborative.
Hey, I'm working on Kanwas with Johan, Predrag and Anja. We went really deep into how collaboration between humans and AI actaully happens and Kanwas is a result of months and months of hard thinking, listening and building. We've decided that open source is the best model for something that should became a central tool in the stack of our users. Hope you all like it. Let me know if you need help with anything, run into any problems or have ideas what we should add.
Been working on kanwas for a few months now. Super excited about it. We use it everyday with a team for multiple hours.
Makes it so easy create a board, iterate on it and then import entire context into my coding agent and just ship a feature thats perfect.
I always wanted a place where AI helps me think. Not output more and more and more stuff. But output less with higher quality. Now we build it for ourselves :)
Hey product people. I am in charge of the canvas interface of Kanwas.
Kanwas is built with the idea of moving from chats to shared spatial context space, where you, your team, and your agents can work together and build on top of it.
My favourite part is being able to control context in the easy way, starting from scratch, or starting from yesterdays research, or just cross referencing latest positioning angle with the newest competitor updates.
From the start of building it we are using it as team, and collaborating through all the challenges, from working on strategy and gtm, to updating feature specs, doing users insights from the posthog events and user calls, and even doing this product hunt launch.
Happy to see you using it and getting the feedback! Here to answer any question!
Report
What about using this tool as a collaboration tool for creating presentations? At work I see a lot of presentations which are just not well designed - it makes it hard to follow the speaker. It would be great to have an agent design a good presentation all within Kanvas where multiple people can interact with it in the creation process.
VEED
Kanwas
@floschirmer @marek_vybiral chose well :)) we really think that if you commit into product like this, you should feel safe with your data
Kanwas
@floschirmer Yes!! I think we all learned our lesson from tools that came before. You need something that can work with local agents + is interoperable.
Kanwas
@floschirmer I agree completly and thank you for noticing the licensing specifics because it much more important than most people realise.
Kanwas
@floschirmer Appreciate you noticing, that was a big reason for us choosing Apache 2.0!
Bababot
This idea of a shared brain for both humans and agents is really interesting . Most tools stop at documentation but this feels more like active thinking infrastructure.
Kanwas
@aarav_pittman Thats exactly what we are going for! Normal when you think about context management for AI you would think "lets upload 100k slack messages and search them" but we found most value in context that is checked and handcrafted by humans. AI can then work on top of it and actually produce good output.
Kanwas
@aarav_pittman on the point! you can aggregate all your team work with their agents, plus make your local/coding agent connected to the context and vice versa
Kanwas
@aarav_pittman Yes, the shared brain isn't just an archive of md files. It's also about being able to seamlessly levarge all the context you've been building.
Kanwas
@aarav_pittman active thinking interface thats exactly it
The Claude chats plus Obsidian plus docs plus Slack mess is very real. Nice to see someone attacking the workflow around the work, not just another chat UI.
Kanwas
@amara_diarra canvas is really a different UI but works so well for thinking work. I am coming from design background so canvases feels like home for iterative creative work. Happy you like it!
Kanwas
@amara_diarra Yep I think we are all starting to get tired of chat UIs :)
Kanwas
@amara_diarra Yes, navigating the mess of AI tools and artifacts is what big part of work in 2026 is about. With Kanwas we don't want to throw another tool into the mess, but actually make the whole process simpler, more powerful and collaborative.
Kanwas
@amara_diarra Thank you! Hope to see you working in canvas view!
Kanwas
Hey, I'm working on Kanwas with Johan, Predrag and Anja. We went really deep into how collaboration between humans and AI actaully happens and Kanwas is a result of months and months of hard thinking, listening and building. We've decided that open source is the best model for something that should became a central tool in the stack of our users. Hope you all like it. Let me know if you need help with anything, run into any problems or have ideas what we should add.
Kanwas
Been working on kanwas for a few months now. Super excited about it. We use it everyday with a team for multiple hours.
Makes it so easy create a board, iterate on it and then import entire context into my coding agent and just ship a feature thats perfect.
I always wanted a place where AI helps me think. Not output more and more and more stuff. But output less with higher quality. Now we build it for ourselves :)
Kanwas
Hey product people. I am in charge of the canvas interface of Kanwas.
Kanwas is built with the idea of moving from chats to shared spatial context space, where you, your team, and your agents can work together and build on top of it.
My favourite part is being able to control context in the easy way, starting from scratch, or starting from yesterdays research, or just cross referencing latest positioning angle with the newest competitor updates.
From the start of building it we are using it as team, and collaborating through all the challenges, from working on strategy and gtm, to updating feature specs, doing users insights from the posthog events and user calls, and even doing this product hunt launch.
Happy to see you using it and getting the feedback! Here to answer any question!
What about using this tool as a collaboration tool for creating presentations?
At work I see a lot of presentations which are just not well designed - it makes it hard to follow the speaker.
It would be great to have an agent design a good presentation all within Kanvas where multiple people can interact with it in the creation process.