Decision information
Manual verification pending- Ecosystem category
- Infrastructure
- Content type
- Product
- Pricing
- Open Source
- Open source
- Yes
- License
- Not recorded
- Maintenance
- Unknown
- Install methods
- Source
- Platforms
- Not recorded
Security signals (informational, not a security certification)
Overview
MiroFish is an open-source, next-generation AI prediction engine based on multi-agent swarm intelligence. By extracting "seed information" from the real world—such as breaking news, policy drafts, or financial signals—it automatically constructs a high-fidelity parallel digital world. Within this sandbox, thousands of AI agents interact, debate, and evolve, allowing users to accurately deduce future trends.
Core Features
- Swarm Intelligence Simulation: Hosts thousands of AI agents, each equipped with an independent personality, long-term memory, and unique behavioral logic.
- Dynamic Variable Injection: Allows users to act from a "God perspective," dynamically introducing variables (like a PR statement or policy change) to observe chain reactions in real-time.
- Knowledge Graph Construction: Utilizes GraphRAG technology to deeply analyze uploaded materials, building dynamic knowledge graphs that inject initial memories and context into the agents.
- Comprehensive Reporting: Automatically generates detailed prediction reports while offering users a highly interactive digital world to explore and interrogate.
- OASIS Engine Integration: Built upon the high-performance social media simulation framework developed by the CAMEL-AI team.
Use Cases
- Enterprise & Policy Makers: Serves as a risk-free rehearsal laboratory to test public relations strategies, policy shifts, and market responses before real-world implementation.
- Individual Creators: Acts as a creative sandbox for writers, researchers, and thinkers to simulate story endings, brainstorm ideas, and explore complex "what-if" scenarios.
Background
MiroFish was developed by Gen-Z developer Guo Hangjiang (BaiFu) utilizing the "Vibe Coding" methodology—a highly AI-assisted development approach. Following the massive success of its predecessor, BettaFish, MiroFish quickly reached the #1 spot on the GitHub global trending list in early 2026. The project's immense potential earned it a 30 million RMB strategic investment from Shanda Group founder Chen Tianqiao to further its vision of creating a mapping of real-world swarm intelligence.