Ginko
GINKO

銀子Ginko

The Ginko tree waits in silence for centuries. Then blooms all at once.

Multi-agent LLM system for detecting silent accumulation phases in Solana tokens — finding the pre-bloom window before market discovery.

$GINKO : 4T3kHiJGmMoiLWhaK76CBq3rxwt69myvNoJbMfNEpump
Launch AppDocumentationGitHub
4
LLM Agents
5
Bloom Phases
0-100
Bloom Index
Ginko

Four Independent Agents

Ginko uses four independent LLM agents to analyze tokens from different angles, then combines their insights into a single Bloom Index score.

DormancyAnalyzer

[01]

Measures how long and how deeply a token has been dormant.

Silence depthQuiet day countPattern class

HolderAnalyzer

[02]

Analyzes holder composition and quality.

Veteran ratioDiamond handsOrganic growth detection

AccumulationAgent

[03]

Detects smart money accumulation patterns.

Smart wallet detectionBuy/sell ratioConviction score

DiscoveryAgent

[04]

Estimates proximity to market discovery.

Community readinessTrigger signalsViral coefficient

Engine Architecture

Token Historical Data
        │
┌───────────────────────────────────────────────────────┐
│                    GINKO ENGINE                        │
│                                                        │
│  DormancyAnalyzer        HolderAnalyzer               │
│  • Silence depth         • Veteran ratio              │
│  • Quiet day count       • Diamond hands              │
│  • Pattern class         • Organic growth             │
│         │                        │                    │
│  AccumulationAgent       DiscoveryAgent               │
│  • Smart wallet          • Community readiness        │
│    detection             • Trigger signals            │
│  • Buy/sell ratio        • Viral coefficient          │
│  • Conviction score      • Estimated days             │
│         │                        │                    │
│         └──────── BLOOM INDEX ───────────┘            │
│                    (0-100)                            │
│                       │                               │
│             PHASE CLASSIFICATION                      │
│  DORMANT → ROOTING → BUDDING → EMERGING → BLOOMING   │
└───────────────────────────────────────────────────────┘
        │
  React Dashboard

Bloom Index Weights

Accumulation35%

Smart money entry patterns

Dormancy25%

Length and depth of silence

Discovery25%

Proximity to market discovery

Holder Quality15%

Veteran ratio, organic growth

Installation

Get started with Ginko in seconds.

pip install

Install via PyPI

pip install ginko

From source

Clone and setup manually

git clone https://github.com/theGinkodev/-Ginko.git
cd -Ginko
pip install -r requirements.txt
cp .env.example .env

Docker

Run with Docker Compose

docker compose up

Configuration

.env
ANTHROPIC_API_KEY=your_key_here
GINKO_MODEL=claude-haiku-4-5-20251001
GINKO_CACHE_TTL=300

Without an API key, all agents run in heuristic mode (no LLM calls). Full test suite passes without a key.

Quick Start

example.py
from ginko import GinkoEngine, TokenSnapshot
import time

engine = GinkoEngine()

result = engine.analyze("YourCA...", "TOKEN", snapshots)
print(f"Bloom Index: {result.bloom_index}/100")
print(f"Phase: {result.bloom_phase.value}")
print(f"Action: {result.recommended_action}")

Dashboard

terminal
cd dashboard
npm install
npm run dev
# → http://localhost:5173