kanwas-ai

kanwas-ai / kanwas

Public

Kanwas — open source thinking space for teams and agents

86
22
100% credibility
Found Apr 30, 2026 at 86 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Kanwas is a shared digital board where teams collaborate with AI agents on documents, research, and decisions in real-time.

How It Works

1
🌐 Discover Kanwas

You hear about a fun shared board where teams and smart helpers work together on ideas and plans.

2
💻 Get it ready

Download the simple files and connect your favorite thinking helper so it can join the fun.

3
🚀 Start with one click

Press go and watch your shared workspace come alive on your computer.

4
🖥️ Open in browser

Jump into your web page and see the big empty board waiting for your thoughts.

5
📝 Build your first board

Drop in notes, pictures, or questions, and let the helper suggest next steps.

6
Work solo or with friends
😊
Solo adventure

Play with ideas and let the helper build plans just for you.

👥
Team party

Share the link and watch everyone add thoughts together.

🎉 Ideas come alive

Your board fills with smart plans, decisions, and everyone sees the magic happen in real time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 86 to 86 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is kanwas?

Kanwas is an open-source TypeScript canvas app that builds a multiplayer thinking space for teams and AI agents. Drop docs, images, and notes on an infinite canvas; invoke agents via Anthropic or OpenAI to analyze, generate PRDs, or plan tasks, with their reasoning and tool calls streaming live into the shared timeline. It runs via Docker Compose, exports everything as git-backed markdown folders for zero lock-in.

Why is it gaining traction?

It fuses real-time collaborative canvas editing with agentic AI on one surface—teams watch agents work over shared evidence without app switching. Features like workspace invites, connections to external tools (Slack, etc.), and task tracking make AI output traceable and executable. Developers dig the quickstart and Apache 2.0 license for self-hosting AI workspaces.

Who should use this?

Product managers dropping interview clips and tickets to auto-generate sourced PRDs. Devs pulling specs onto a kanwas canvas to collaborate with agents on implementation plans, then `kanwas pull` to repo. Founders juggling fundraising decks, interviews, and hiring plans in one team space.

Verdict

Promising early project (86 stars, 1.0% credibility score) with strong Docker setup and system docs, but light on tests—fork and harden for production. Grab it if you need a canvas syndrom-free agent+team hub.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.