MiroFish
🇹🇭 ภาษาไทย
Next-generation AI prediction engine ที่ใช้ multi-agent simulation สร้าง “parallel digital world” จาก seed information แล้วให้ agent หลายพันตัววิ่ง social evolution เพื่อ predict อนาคต
GitHub: github.com/666ghj/MiroFish | Demo: 666ghj.github.io/mirofish-demo Backed by: Shanda Group | Engine: OASIS (CAMEL-AI)
“Rehearse the future in a digital sandbox, and win decisions after countless simulations.”
แนวคิดหลัก
MiroFish เชื่อว่า prediction ที่ดีที่สุดไม่ได้มาจาก statistical model แต่มาจาก Swarm Intelligence — emergent behavior ที่เกิดจาก agent จำนวนมากที่มี personality และ memory ของตัวเอง interact กัน ผลลัพธ์คือ collective emergence ที่ยากจะ derive จาก top-down model
Workflow
1. Graph Building → Seed extraction, GraphRAG construction, memory injection
2. Environment Setup → Entity extraction, persona generation per agent
3. Simulation → Dual-platform parallel sim, dynamic temporal memory (Zep Cloud)
4. Report Generation → ReportAgent with rich toolset
5. Deep Interaction → Chat with any agent in the simulated world
Use Cases
| ระดับ | ตัวอย่าง |
|---|---|
| Macro | ทดสอบนโยบาย, simulation ข่าว public opinion, prediction การเงิน |
| Creative | ต่อจบนิยาย, สำรวจ what-if scenarios |
Tech Stack
| Component | Technology |
|---|---|
| Simulation engine | OASIS (CAMEL-AI) |
| Agent memory | Zep Cloud |
| Graph/retrieval | GraphRAG |
| LLM backend | OpenAI-compatible API (แนะนำ Qwen-plus) |
| Frontend/Backend | Node.js 18+ / Python 3.11–3.12 |
Related
- Swarm Intelligence — ปรัชญาหลักที่ MiroFish ยึด
- Multi-Agent Simulation — framework ที่ MiroFish สร้างขึ้นบน
- RAG vs Wiki — MiroFish ใช้ GraphRAG เพิ่ม dimension ที่สามใน spectrum
🇬🇧 English
Next-generation AI prediction engine that uses multi-agent simulation to construct a “parallel digital world” from seed information, then runs thousands of agents through social evolution to predict future outcomes.
GitHub: github.com/666ghj/MiroFish | Backed by: Shanda Group (incubation)
“Rehearse the future in a digital sandbox, and win decisions after countless simulations.”
Core Concept
MiroFish’s thesis: the best predictions don’t come from statistical models but from Swarm Intelligence — emergent behavior arising from many agents with individual personalities and memories interacting together. The collective emergence is something that cannot be derived from any top-down model.
Workflow
1. Graph Building → Seed extraction from inputs, GraphRAG construction, memory injection
2. Environment Setup → Entity relationship extraction, persona generation per agent
3. Simulation → Dual-platform parallel simulation, dynamic temporal memory (via Zep Cloud)
4. Report Generation → ReportAgent with rich toolset, deep interaction with post-sim environment
5. Deep Interaction → Chat with any agent in the simulated world, follow-up with ReportAgent
Use Cases
| Level | Examples |
|---|---|
| Macro / Serious | Policy testing, news public opinion simulation, financial prediction |
| Micro / Creative | Completing novel endings (e.g. Dream of the Red Chamber), exploring what-if scenarios |
Technical Stack
| Component | Technology |
|---|---|
| Simulation engine | OASIS (CAMEL-AI open-source framework) |
| Agent memory | Zep Cloud (long-term per-agent memory with temporal tracking) |
| Graph/retrieval | GraphRAG |
| LLM backend | OpenAI-compatible API (Alibaba Qwen-plus recommended) |
| Frontend | Node.js 18+ |
| Backend | Python 3.11–3.12, uv |
Unlike MemPalace which runs fully locally, MiroFish requires an LLM API key and a Zep Cloud account (free tier available).
Memory Approach Comparison
| System | Memory Approach |
|---|---|
| MemPalace | Verbatim conversation storage + semantic retrieval |
| LLM Wiki Pattern | Compiled synthesis in wiki pages |
| MiroFish / Zep | Per-agent identity memory for simulation continuity |