JellyfishBot
Building agents simpler
Quick Start
Three ways, pick what fits you
Download & Run · One-Click Install
Desktop app, ready to use, perfect for individual exploration
Couldn't auto-detect latest version. Click below to download manually from GitHub Releases.
M1/M2/M3/M4 chips
Intel-based Mac
x64 installer
Runs on Your Machine
Laptop, cloud server, or Raspberry Pi. One Docker command to start the full platform. All data is just JSON files in a folder. Your data stays yours.
What It Does
WeChat AI Customer Service
“Upload product docs, share a QR code, customers chat with your AI on WeChat.”
- 1Configure Service → Enable WeChat → Generate QR Code
- 2Customer scans → Chats with your Agent in WeChat
- 3Images, voice, and text fully supported
One step back. A little simpler.
In an ever-more-complex agent ecosystem, the jellyfish chooses to step back — but back into a closed loop.
OpenClaw
Hyper-private by design — high risk of agent overreach, no real multi-user story, and distribution is out of the question.
Hermes
Full automation sounds great, but you can only guide it through conversation — config, memory, and distribution silos are still yours to stitch.
JellyfishBot
Built for tight, high-quality ops (≤50 people). Like Cursor's co-pilot, your agent sits beside you helping you build the next agent.
Flowise
Node-based prototyping. Maintenance gets hard once logic grows.
n8n
A workflow automation giant — AI is just one of its later-added nodes.
Dify
Building workflows / chatflows is painful. The graph structure is complex, and the best use case is still unclear.
Light, yet closed-loop. The jellyfish answer to 'simpler.'