🐟MiroFish
A Simple and Universal Swarm Intelligence Engine, Predicting Anything.
⭐ Hugely popular: 71k stars, gaining about 381 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- One of the clearest live examples of multi-agent simulation moving from research demo to a deployable product.
- Instead of an LLM writing text about predictions, it runs actual social emergence, where individual interactions aggregate into collective behavior no one directly specified.
- Ships with Qwen-plus as its default backbone, part of the broader trend of open Chinese models becoming real downstream infrastructure.
under the hood
- A five-stage pipeline: GraphRAG graph building with persona injection, environment setup with entity extraction, full parallel simulation, a ReportAgent phase, and a deep interaction layer.
- Python backend with a Vue frontend, deployable via Docker or from source.
- Zep Cloud handles the long-term memory layer for individual agents, and a live public demo is available.
our take from PR#31, 2026-04-08
star history
- PR#31 50k 2026-04-08
- now 71k + 21k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Multi-agent swarm intelligence engine for predicting real-world outcomes
similar projects
compare these →- 🦾 crewAI
MIT licensed
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
57k ACTIVE - 🤖 nanobot
MIT licensed
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
47k ACTIVE - 📖 ai-agent-book
leaner, 38k stars · Apache-2.0 licensed
AI Agent PDF
38k ACTIVE
comments
Sign in with GitHub to add your blip on MiroFish.