---
language:
- en
license: apache-2.0
tags:
- agent
- multi-agent
- langgraph
- gguf
- lora
- qwen
- prediction-markets
- mad-gambit
- solidity
- tandem-core
- agent-q3
- agent-q3-hq
- agent-q3-evo
pipeline_tag: text-generation
---

# Agent Q3

> **MAD Gambit** — Multi-agent intelligence layer
> Contains both **Agent Q3 [HQ]** (production orchestration) and **Agent Q3 [Evo]** (self-improving research pipeline)

---

## Variants

| Variant | Role | Key Tech |
|---------|------|----------|
| **Agent Q3 [HQ]** | Production orchestration | Tandem Core · ComputeRouter · LangGraph · MCP · Solidity audit |
| **Agent Q3 [Evo]** | Self-improving research | LoRA fine-tuning · arXiv ingestion · ChromaDB · Unsloth · benchmarks |

---

## File Structure

```
Agent-Q3/
├── README.md
│
├── hq/                          ← Agent Q3 [HQ] — Production
│   ├── Dockerfile
│   ├── docker-compose.yml
│   ├── requirements.txt
│   ├── .env.example
│   ├── orchestrator.py          ← FastAPI + ComputeRouter
│   ├── compute_router.py        ← Multi-backend weighted routing
│   ├── tandem_core.py           ← Gemma4 Reasoner + Qwen3.5 Coder chain
│   ├── langgraph_graph.py       ← StateGraph agent orchestration
│   ├── mcp_config.json          ← 14 MCP server connectors
│   ├── litellm_config.yaml      ← LiteLLM routing config
│   └── metrics.py               ← Prometheus /metrics endpoint
│
├── evo/                         ← Agent Q3 [Evo] — Research
│   ├── Dockerfile
│   ├── requirements.txt
│   ├── .env.example
│   ├── training_pipeline.py     ← Unsloth LoRA fine-tuning
│   ├── arxiv_ingestor.py        ← arXiv fetch → chunk → embed
│   ├── chromadb_store.py        ← Vector store (nomic-embed-text 384-dim)
│   ├── feedback_collector.py    ← DPO/RLHF signal capture
│   ├── benchmark_runner.py      ← Domain QA evaluation
│   ├── lora_pusher.py           ← Push adapters to HF
│   └── langgraph_graph.py       ← StateGraph agent orchestration
│
└── shared/                      ← Shared utilities
    ├── auth.py
    ├── logger.py
    └── config.py
```

---

## HQ — Quick Start

```bash
cd hq
cp .env.example .env
docker compose up --build
```

**Endpoints:**
- `POST /v1/chat` — auto-classify → Reasoner or Coder
- `POST /v1/reason` — force Gemma4-E4B (planning, research, audit)
- `POST /v1/code` — force Qwen3.5-4B (code, debug, file ops)
- `POST /v1/tandem` — Gemma4 reasons → Qwen3.5 implements
- `GET  /health` — backend health + loaded models
- `GET  /metrics` — Prometheus metrics

## Evo — Quick Start

```bash
cd evo
cp .env.example .env
pip install -r requirements.txt
python training_pipeline.py
```

---

## Linked HF Assets

| Type | Label | Link |
|------|-------|------|
| Model | Agent Q3 (unified) | [madDegen/agent-q3-core](https://hf.co/madDegen/agent-q3-core) |
| Dataset | Agent Q3 (unified) | [madDegen/agent-q3](https://hf.co/datasets/madDegen/agent-q3) |
| Space | Agent Q3 (unified) | [madDegen/agent-q3-space](https://hf.co/spaces/madDegen/agent-q3-space) |

---

## License

Apache 2.0