666ghj/mirofish

★ 61,177PythonAudience · pm founderComplexity · 4/5MaintainedLicenseSetup · hard

Mindmap

mindmap
  root((repo))
    What it does
      Simulates AI agents
      Predicts outcomes
      Analyzes interactions
    How it works
      Builds knowledge graph
      Creates agent personalities
      Runs parallel simulation
      Generates reports
    Use cases
      Financial forecasting
      Political scenarios
      Public opinion analysis
      Story prediction
    Tech stack
      Python backend
      Node.js frontend
      LLM APIs
      Zep Cloud memory

mindmap root((repo)) What it does Simulates AI agents Predicts outcomes Analyzes interactions How it works Builds knowledge graph Creates agent personalities Runs parallel simulation Generates reports Use cases Financial forecasting Political scenarios Public opinion analysis Story prediction Tech stack Python backend Node.js frontend LLM APIs Zep Cloud memory

Things people build with this

USE CASE 1

Forecast financial market movements by simulating how traders and investors will react to economic events.

USE CASE 2

Model political scenarios and predict how policy changes might shift public opinion across different demographics.

USE CASE 3

Analyze how rumors or news stories will spread and evolve through a population of simulated agents.

USE CASE 4

Predict how a fictional story might develop by simulating character interactions and decision-making.

Tech stack

PythonNode.jsOpenAI SDKQwen-plusZep CloudDocker Compose

Getting it running

Difficulty · hard Time to first run · 1day+

Requires Docker Compose orchestration, multiple API keys (OpenAI, Qwen, Zep Cloud), and coordination between Python and Node.js services.

Use it freely, but if you run it as a network service, you must release your changes to users. Strongest copyleft for SaaS.

In plain English

MiroFish is a multi-agent simulation engine that tries to predict future outcomes by creating a digital world populated with thousands of AI characters who interact with one another. The problem it aims to solve is that traditional forecasting methods rely on statistics and historical patterns, which struggle with complex social phenomena where the behavior of individuals affects the behavior of others in cascading ways. MiroFish approaches this differently: you feed it real-world seed material, such as a news article, a policy document, or financial data, and it builds a simulated environment with AI agents representing people or entities, each given their own personality, memory, and decision-making logic. These agents then interact freely over many simulated time steps, and the resulting collective behavior is used to generate a prediction report. The workflow has four stages: first it builds a knowledge graph from the seed material; then it creates the simulated environment and configures agent personalities; then it runs the simulation on two parallel platforms; and finally a dedicated reporting agent synthesizes the interactions into a readable prediction. You can also directly chat with any agent in the finished simulation to explore specific scenarios. The tech stack uses Python on the backend and Node.js for the frontend, with support for LLM APIs in the OpenAI SDK format (the documentation recommends Alibaba's Qwen-plus model). Agent memory is handled by Zep Cloud. The application runs either from source code or via Docker Compose. The project is aimed at use cases including financial forecasting, public opinion analysis, political scenario modeling, and even more creative applications like predicting how a fictional story might end. Topics listed include multi-agent simulation, knowledge graphs, and financial forecasting.

Copy-paste prompts

Prompt 1

I have a news article about a tech company layoff. How do I use MiroFish to simulate how this will affect stock prices and investor sentiment?

Prompt 2

Set up a MiroFish simulation with agents representing different political viewpoints to predict how a new policy proposal will be received.

Prompt 3

Walk me through the four stages of MiroFish: knowledge graph building, agent creation, simulation, and report generation.

Prompt 4

How do I configure agent personalities and memory in MiroFish to make the simulation more realistic for my use case?

Prompt 5

Can I chat with individual agents after the simulation runs to explore alternative scenarios or ask them about their decisions?

Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.