KaibanJS – JavaScript Framework for Building Multi-Agent Systems
Hey HN, A couple of friends and I spent the last three months working on KaibanJS, an open-source framework for building AI multi-agent systems. Honestly, we’re not 100% sure it’s fully ready for launch. But we’d love to get your feedback on it. The idea came from us trying to find a native JS solution for working with AI agents, and we couldn’t find anything that really fit well with the JS ecosystem… stuff like React, Next, State management, etc. So, we decided to build it ourselves. Because KaibanJS runs in the browser, we also built a cool UI—a Kanban board, kinda like Trello, that lets…
In plain words
KaibanJS is an open-source JavaScript framework for building multi-agent AI systems designed to integrate with the JS ecosystem including React, Next.js, and state management tools. It runs in the browser and includes a Kanban board interface for visualizing agent activity, providing an alternative to console logging. The framework aims to simplify multi-agent development for JavaScript developers while remaining flexible for complex setups.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, A couple of friends and I spent the last three months working on KaibanJS, an open-source framework for building AI multi-agent systems. Honestly, we’re not 100% sure it’s fully ready for launch. But we’d love to get your feedback on it. The idea came from us trying to find a native JS solution for working with AI agents, and we couldn’t find anything that really fit well with the JS ecosystem… stuff like React, Next, State management, etc. So, we decided to build it ourselves. Because KaibanJS runs in the browser, we also built a cool UI—a Kanban board, kinda like Trello, that lets you visualize your agents as they work. It's much better than having to look at AI agent logs in the console ;) KaibanJS is designed to make working with agents easier for JS devs, without dealing with all the low-level stuff, but it’s flexible enough to handle more complex setups if needed. (We even use LangChain behind the scenes for some of the orchestration.) We’re excited to hear what you think, and any feedback would be super helpful. Thanks in advance
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com