repowise666ghj/mirofish

666ghj / mirofish

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Python★ 76,613
Use in your agentAsk this codebase

github.com/666ghj/mirofishIndexed at 96096eaUp to date with upstream

What is mirofish?

mirofish is a Python-based swarm intelligence engine for predicting outcomes from seed materials such as reports, policy drafts, financial signals, or stories. It builds a simulated digital world where agents interact, then produces prediction reports and supports interaction with the simulated environment.

Written by a model from the README and the source

55 files and 596 symbols in 3 modules, led by Python (35 files) and JavaScript (9).

Start reading

Code health

4.6out of 10Needs work

Hotspots average 3.8, the place fixes pay off most.

Full health report

Use 666ghj/mirofish in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/666ghj/mirofish
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is mirofish put together?")
  • get_why("why is mirofish structured this way?")

Explore mirofish

Key features of mirofish

  • MiroFish extracts seed information and constructs a parallel digital world with interacting agents.
  • MiroFish supports graph building with seed extraction, memory injection, and GraphRAG construction.
  • MiroFish configures entities, relationships, personas, and agents for simulation.
  • MiroFish runs parallel simulations with dynamic temporal memory updates.
  • MiroFish generates prediction reports and supports interaction with simulated agents and ReportAgent.

How 666ghj/mirofish works

Input enters through uploaded seed materials and natural-language prediction requirements. backend/app/services/simulation_config_generator.py generates simulation configuration, while backend/app/api/simulation.py exposes simulation operations. Graph building extracts seeds, injects individual and collective memory, and constructs GraphRAG data before environment setup extracts relationships and generates personas. backend/app/services/simulation_runner.py runs the parallel simulation and updates temporal memory. backend/app/services/report_agent.py generates reports and interacts with the post-simulation environment, while backend/app/services/zep_tools.py provides tools for that interaction. The frontend directory provides the user interface for starting simulations and interacting with agents and reports.

The codebase has 55 files and 596 symbols in 3 modules, led by Python, JavaScript and Dockerfile. Code health is 4.6 out of 10, rated needs work.

Getting started with mirofish

  1. Copy the example configuration file and edit .env with the required API keys.
    cp .env.example .env
  2. Install all root, frontend, and backend dependencies.
    npm run setup:all
  3. Start the frontend and backend from the project root.
    npm run dev
  4. Alternatively, configure environment variables and start the Docker deployment.
    docker compose up -d

Commands copied from the README

666ghj/mirofish FAQ

What is mirofish?

mirofish is a swarm intelligence engine for predicting outcomes from seed materials. It creates a simulated digital world with interacting agents and returns prediction reports.

How does mirofish work?

mirofish extracts seed information, builds a graph and agent environment, runs parallel simulations, and generates reports. Users can interact with simulated agents and ReportAgent.

How do I install mirofish?

mirofish installs with npm run setup:all, which installs root, frontend, and backend dependencies. The backend setup can also run with npm run setup:backend.

What language is mirofish written in?

mirofish is primarily written in Python, with JavaScript used for frontend files.

How is the mirofish code organized?

mirofish is organized mainly into backend and frontend directories, with localization files in locales. Backend services include simulation configuration, simulation execution, reporting, and Zep tools.

Who is mirofish for?

mirofish is for decision-makers testing policies or public relations and for users exploring scenarios such as novel endings. It supports serious predictions and creative simulations.

What license does mirofish use?

mirofish uses the AGPL-3.0 license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of 666ghj/mirofish from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.