AsahiLMv0.1
AppLabSignalsSDKCLIDocsAbout
Launch
AppLabSignalsSDKCLIDocsAbout
Launch App
Back

Documentation

Complete reference for AsahiLM — the meme token narrative intelligence framework.

Python SDK

pip install asahi

View SDK

CLI Reference

Analyze from terminal

View CLI

Interactive Lab

Test signals live

Open Lab

Introduction

AsahiLM is a meme token narrative intelligence engine for Solana. Language models read sequences — they weight context, measure coherence, track how meaning accumulates across positions. AsahiLM applies the same lens to on-chain meme tokens.

Every meme has a sequence: early signal, growing resonance, coherent narrative, viral escape velocity. Most traders read the chart. AsahiLM reads the structure beneath it — measuring whether a token's signals are coherent and directional, or just noise.

Installation

# Install from PyPI
pip install asahi

# No external dependencies. Pure Python 3.10+.

Quick Start

from asahi import classify, MemeTokenContext

ctx = MemeTokenContext(
    token_mint="AsahiXyz...pump",
    symbol="ASAHI",
    price_usd=0.00082,
    price_change_1h_pct=38.0,
    price_change_24h_pct=180.0,
    volume_1h=480_000,
    volume_24h=1_200_000,
    holder_count=4_200,
    holder_count_prev=3_100,
    market_cap_usd=560_000,
)

report = classify(ctx)

print(report.state)            # NARRATIVE
print(report.narrative_score)  # ~67.4
print(report.insight)          # "Coherent narrative in motion..."
print(report.triggered_count)  # 3
print(report.is_coherent)      # True

Core Concepts

Narrative Score

A 0-100 score representing overall narrative coherence. Higher scores indicate stronger, more directional market signals.

Phases

Four phases based on narrative score thresholds:

NOISE
0-25
SIGNAL
26-50
NARRATIVE
51-75
VIRAL
76-100

The Name

Asahi means morning sun in Japanese. The moment just before sunrise when light starts to differentiate signal from darkness. That's what this engine does: it reads the on-chain sequence and finds where the narrative is actually forming — before it becomes obvious.

Getting Started

IntroductionInstallationQuick StartCore Concepts

Signal Reference

Velocity SignalResonance SignalDepth SignalCoherence Signal

Python SDK

MemeTokenContextclassify()classify_batch()loudest()

CLI Reference

asahi analyzeasahi scanasahi watch

Lab & Testing

Interactive LabParameter TestingSignal Debugging
AsahiLM

Meme token narrative intelligence engine for Solana. Four signals measuring whether a token's market signals are coherent and directional, or just noise.

Product

  • App
  • Lab
  • Signals
  • About

Developers

  • Documentation
  • CLI
  • SDK

Connect

  • GitHub
  • X / Twitter

MIT License - AsahiLM