Documentation Index
Fetch the complete documentation index at: https://mintlify.com/alphaleaks60-maker/docs2/llms.txt
Use this file to discover all available pages before exploring further.
Alpha Leak exposes a live signal feed and a set of REST endpoints. This guide walks through connecting to both — from opening the SSE stream on page load, to reading and interpreting the full signal payload. No SDK required; the API is plain HTTP and SSE.
Base URL
All endpoints are served from your hosted instance. Replace your-instance throughout this guide with the host you’ve been given.
https://your-instance/api
Connect to the live feed
The primary interface is a Server-Sent Events stream that pushes signals, graduations, and anti-signals in real time as they occur on-chain. This is the fastest way to consume Alpha Leak data — no polling required.const es = new EventSource('https://your-instance/api/live/feed');
es.addEventListener('signal', (event) => {
const data = JSON.parse(event.data);
if (data.type === 'genesis_signal') {
// New token scored highly in its first 60 seconds
console.log('Genesis:', data.data.symbol, `score: ${data.data.genesisScore}`);
} else if (data.type === 'anti_signal') {
// Active token flagged — adversarial conditions detected
console.warn('Anti-signal:', data.data.tokenMint, data.data.reasons);
} else {
// Standard tracked-wallet signal
console.log('Signal:', data.data.tokenMint, data.data.action);
}
});
es.addEventListener('graduation', (event) => {
const token = JSON.parse(event.data);
console.log(`${token.symbol} graduated — ${token.volume} SOL total volume`);
});
es.onerror = () => {
// SSE clients reconnect automatically — no manual handling required
};
The stream sends a heartbeat event every 15 seconds to keep connections alive through proxies and load balancers. You do not need to handle reconnection logic manually.
Fetch recent data on load
Before the live stream has delivered events, use the /api/live/recent endpoint to populate your initial state. Call this once on page load; the SSE stream takes over from that point forward.const res = await fetch('https://your-instance/api/live/recent?limit=20');
const { signals, graduations, largeTrades } = await res.json();
// signals — recent buy/sell signals with ML scores
// graduations — recently graduated tokens
// largeTrades — recent trades >= 1.0 SOL
Understand signal types
Alpha Leak emits three distinct signal types on the live feed. Each type has a different trigger and a different action implication. signal
genesis_signal
anti_signal
A tracked wallet — one the system has built a quality profile for — has made a significant buy. The payload includes the wallet’s alpha score, ML probability score, token state, buy rank, velocity data, and creator risk.This is the primary actionable signal type. High-quality signals have high alphaScore, low buyRank, rising velocity, and a lifecycleState of momentum or early_accumulation.
A newly created token scored highly across the genesis model’s 75-feature vector during its first 60 seconds of life. No tracked wallet is needed — this is purely based on launch dynamics: early buyer composition, velocity shape, and price action.
A token with recent buy signals has triggered 2 or more adversarial detection rules simultaneously — for example, a coordinated bundle combined with a high bot buyer percentage. Any system acting on the original signal should treat this as an exit cue.
Query historical data
All historical signal, wallet, and token data is available via REST. Use these endpoints to backfill state, build dashboards, or validate signal quality against outcomes.// Signals with ML scores — paginated
const signals = await fetch('/api/signals?min_ml_score=0.80&limit=50').then(r => r.json());
// Tracked wallets with alpha scores
const wallets = await fetch('/api/wallets?min_alpha=70&active_only=true').then(r => r.json());
// Token data including lifecycle state and risk scores
const tokens = await fetch('/api/tokens?graduated=false').then(r => r.json());
// Current pipeline stats and market regime
const stats = await fetch('/api/stats').then(r => r.json());
Interpret a signal payload
Here is a full buy signal payload with field-by-field annotations.{
"type": "signal",
"data": {
"tokenMint": "So11...", // Token being bought
"wallet": "ABC1...", // Wallet that triggered the signal
"action": "buy",
"solAmount": 0.5, // Size of this specific buy
"buyRank": 4, // This wallet was the 4th buyer on this token
"curvePct": 0.12, // Bonding curve is 12% filled
"curveSol": 8.3, // 8.3 SOL currently in the curve
"buysLast60s": 12, // 12 buys on this token in the last 60 seconds
"buysLast300s": 34, // 34 buys in the last 5 minutes
"walletStats": {
"alphaScore": 84, // Wallet quality score (0–100)
"graduationRate": 0.41, // 41% of tokens this wallet bought graduated
"winRate": 0.68, // 68% of positions closed in profit
"captureEfficiency": 0.72 // Captures 72% of available peak return on average
},
"tokenState": {
"lifecycleState": "momentum", // Token lifecycle classification
"riskScore": 18, // Token-level risk score (low = safer)
"bundleConfidence": 0.12, // Low bundle confidence — looks organic
"creatorRiskScore": 24 // Creator has a solid track record
}
}
}
| Dimension | High-quality indicator |
|---|
alphaScore | 75 or above |
buyRank | 5 or lower — earlier entry is better |
| Velocity | buysLast60s trending up relative to buysLast300s |
riskScore | Below 30 |
bundleConfidence | Below 0.25 — organic buy pressure |
lifecycleState | momentum or early_accumulation |
An anti_signal for a token you are holding should be treated as an immediate exit cue. The system triggers anti-signals only when two or more adversarial detection rules fire simultaneously — this is a high-confidence fraud or rug indicator, not a soft warning.