Meeting Notes Summarizer
Turns a meeting transcript into clean notes with decisions and action items
by Pawel Huryn
LobeHub
Lets you build a team of AI agents that chat, write and run scheduled tasks for you
What it does
LobeHub, formerly LobeChat, is an open source workspace for chatting with AI models and building agents that work for you. You describe an agent once, give it skills and MCP plugins from its library, and can put several agents on one task, schedule runs and keep a memory you can edit. You can use the hosted version at app.lobehub.com or run your own copy with Docker and your own model keys. It suits people who want one place to run several AI helpers.
It treats agents as teammates: you can group them on one job, schedule their work and see or edit what they remember about you.
Before you start
- 1A computer with macOS, Linux, Windows or a web browser.
- 2Docker on Linux or macOS; on Windows, run the setup inside WSL 2
- 3An API key from a model provider such as OpenAI, or models running in Ollama
- 4Free ports 3210, 9000, 9001, 8787 and 8788 on the machine you install it on
- 5Optional: a LobeHub account to use the hosted version at app.lobehub.com instead
- !License conditions: Free to use, including commercially as a hosted service, if you do not change the code; building and distributing a modified version needs a commercial license from LobeHub.
- !Pay per use. The AI service it calls charges for what you use.
How to start
- Install itPaste the install request into an AI agent you already use, or run the official command yourself or follow the official guide.macOS, Linux, Windows
mkdir lobehub && cd lobehub bash <(curl -fsSL https://lobe.li/setup.sh) -l en docker compose up -d - Open itFollow the first-run steps in the app.
- Give it a first taskDescribe what you want in your own words, and check the first result before relying on it.
Steps follow the creator's instructions.
Stuck setting it up?
Tell us what happened. We confirm scope and price before any paid work.
