# mirofish-offline-simulation

A skill that walks you through a local multi-agent simulation engine on Neo4j and Ollama: agents debate a document and shift opinions hour by hour.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1400 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/mirofish-offline-simulation/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/mirofish-offline-simulation

## What it does

The skill covers setting up MiroFish-Offline, an engine that takes a document — a press release, a policy draft, a financial report — and turns it into a graph of entities and relations using an LLM. From that graph it generates hundreds of agents, each with its own personality and memory, and lets them post, argue and change their minds on simulated platforms. A ReportAgent then interviews a focus group, searches the graph and writes up the analysis. You can also chat with any single agent, and its memory sticks.

Under the hood: a Flask backend on Python 3.11, a Vue 3 frontend on Node 18, Neo4j CE 5.15 over bolt, models served by Ollama through its OpenAI-compatible `/v1` endpoint, and `nomic-embed-text` embeddings at 768 dimensions. Search is hybrid — 0.7 vector similarity plus 0.3 BM25. Two install paths exist: Docker Compose, or a manual build of Neo4j, Ollama, backend and frontend. Settings live in `.env`: LLM endpoint and key, Neo4j credentials, embedding model.

The main model `qwen2.5:32b` is roughly 20GB and wants 24GB of VRAM, so without that headroom pick `qwen2.5:14b` at 10GB. You can swap Ollama for any OpenAI-compatible provider by changing `LLM_BASE_URL` and the key. Simulation runs as a blocking call, so production use needs an async wrapper.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill mirofish-offline-simulation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/mirofish-offline-simulation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/mirofish-offline-simulation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill mirofish-offline-simulation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/mirofish-offline-simulation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill mirofish-offline-simulation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/mirofish-offline-simulation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills mirofish-offline-simulation
```

2. **Manually: put the files in place**
- File: `.github/skills/mirofish-offline-simulation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill mirofish-offline-simulation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/mirofish-offline-simulation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/mirofish-offline-simulation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill mirofish-offline-simulation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/mirofish-offline-simulation/SKILL.md

## When to use it
- build an entity and relation graph from a document
- generate hundreds of agents with personalities and memory
- model hour-by-hour reaction to a press release
- get a report with sentiment shifts and influential agents
- interview one agent and trace its reasoning

## Example prompts
- Set up mirofish offline simulation on my machine with Neo4j and Ollama
- Build a graph from `press_release.txt` and run a 200-agent simulation
- Generate a report from the last simulation with a 10-agent focus group

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 139 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md