crowdcast

Crowdcast

**Multi-agent social simulation as a Claude Code skill.**

Drop in a document, describe what you want to predict — Crowdcast spawns dozens of AI agents that argue, post, react, and evolve on a simulated platform. Then it writes you a report.

No APIs to configure. No databases to run. No web server. Just `/crowdcast simulate`.

Why Crowdcast over MiroFish?

[MiroFish](https://github.com/666ghj/MiroFish) is the original multi-agent prediction engine that inspired this project. It's a great tool — but it comes with friction:

	MiroFish	Crowdcast
Setup	Python + Node.js + Docker + env vars	git clone into ~/.claude/skills/
External APIs	Zep Cloud ($25/mo) + LLM API ($5-15/run)	None — included in Claude subscription
Rate limits	Zep free tier: 1 simulation/month	Unlimited
Infrastructure	Flask server + Vue.js frontend + Zep + OASIS	Zero — runs inside Claude Code
Resume after crash	Manual — restart from scratch	/crowdcast resume picks up where it stopped
Agent scale	Up to millions (via OASIS)	Up to ~100 (practical limit)
Agent depth	Uniform — all agents use same LLM prompt	Hybrid — key agents think deeply, crowd is batched
Creative mode	Limited (primarily forecast-oriented)	Full narrative simulation with character arcs
Interview agents	Requires running server	/crowdcast interview — instant, in terminal

**TL;DR:** MiroFish is more powerful at massive scale. Crowdcast is simpler, cheaper, and more accessible for most use cases. If you need to simulate a million agents, use MiroFish. If you need a quick prediction from 50 agents with zero setup, use Crowdcast.

What It Does

Upload a document (news article, research report, novel) and describe what you want to simulate:

1. Analyze — extract entities, relationships, and context from your documents

...