Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/0xW1re/solvedocs/llms.txt

Use this file to discover all available pages before exploring further.

Alpha Leak exposes a Server-Sent Events stream for real-time signal delivery and a set of REST endpoints for historical data, wallet intelligence, and pipeline health. All endpoints are available at your hosted instance URL. Replace your-instance throughout this reference with the host you have been given.
https://your-instance/api

Live feed

GET /api/live/feed

A persistent Server-Sent Events stream that pushes signals, graduations, and anti-signals in real time as they occur on-chain. This is the primary interface for consuming Alpha Leak data — no polling required.
SSE clients reconnect automatically on disconnect. No manual reconnection logic is needed. To detect a stalled feed without a dropped connection, monitor the heartbeat event — it fires every 15 seconds.
Event types
EventDescription
signalA tracked wallet has made a significant buy. Includes ML score, wallet stats, token state, and velocity.
genesis_signalA newly created token scored highly across the genesis model’s 75-feature vector in its first 60 seconds.
anti_signalA token has triggered 2 or more adversarial detection rules simultaneously. Treat as an exit cue.
graduationA token has graduated from the Pump.fun bonding curve to a full DEX listing.
heartbeatEmitted every 15 seconds to keep connections alive through proxies and load balancers.
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
};

GET /api/live/recent

Returns a snapshot of recent events for populating initial state before the live stream has delivered data. Call this once on page load, then let the SSE stream take over.
limit
integer
Number of recent events to return.
Response fields
signals
array
Recent buy and sell signals with ML scores.
graduations
array
Recently graduated tokens.
largeTrades
array
Recent trades of 1.0 SOL or more.
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

Historical data

GET /api/signals

Returns paginated historical signals with ML probability scores.
min_ml_score
float
Filter by minimum ML probability score. Range: 0–1. A value of 0.80 returns only signals where the model gave at least 80% probability.
limit
integer
Maximum number of results to return.
const signals = await fetch('/api/signals?min_ml_score=0.80&limit=50').then(r => r.json());

GET /api/wallets

Returns tracked wallets with alpha scores and performance data.
min_alpha
integer
Filter by minimum alpha score. Range: 0–100. Wallets above 75 have significantly higher historical hit rates.
active_only
boolean
When true, returns only wallets that have been active within the recent scoring window.
const wallets = await fetch('/api/wallets?min_alpha=70&active_only=true').then(r => r.json());

GET /api/tokens

Returns token data including lifecycle state and risk scores.
graduated
boolean
Filter by graduation status. Pass false to return only tokens still on the bonding curve; true for tokens that have graduated.
const tokens = await fetch('/api/tokens?graduated=false').then(r => r.json());

GET /api/stats

Returns a pipeline health snapshot covering WebSocket ingestion, signal counts, wallet coverage, market regime, ML model state, uptime, and memory usage.
const stats = await fetch('/api/stats').then(r => r.json());
{
  "ws": { "connected": true, "eventsPerSec": 42, "totalEvents": 4320000, "currentSlot": 312450000 },
  "signals": { "total": 84200, "last24h": 1240 },
  "wallets": { "tracked": 2840, "scored": 1920, "bots": 340 },
  "regime": { "state": "bull_normal", "confidence": 0.6 },
  "models": { "loaded": 4, "scored": 81200, "fallbacks": 42 },
  "uptime": 86400,
  "memMb": 312
}
ws
object
WebSocket ingestion state.
signals
object
Aggregate signal counts.
wallets
object
Wallet coverage summary.
regime
object
Current market regime classification.
models
object
ML inference state.
uptime
integer
Pipeline uptime in seconds.
memMb
number
Current process memory usage in megabytes.

Signal payload reference

Signal

A signal event is emitted when a tracked wallet — one the system has built a quality profile for — makes a significant buy. The payload includes the wallet’s alpha score, ML probability score, token lifecycle state, buy rank, velocity data, and creator risk.
{
  "type": "signal",
  "data": {
    "tokenMint": "So11...",
    "wallet": "ABC1...",
    "action": "buy",
    "solAmount": 0.5,
    "buyRank": 4,
    "curvePct": 0.12,
    "curveSol": 8.3,
    "buysLast60s": 12,
    "buysLast300s": 34,
    "walletStats": {
      "alphaScore": 84,
      "graduationRate": 0.41,
      "winRate": 0.68,
      "captureEfficiency": 0.72
    },
    "tokenState": {
      "lifecycleState": "momentum",
      "riskScore": 18,
      "bundleConfidence": 0.12,
      "creatorRiskScore": 24
    }
  }
}
type
string
Always "signal" for standard tracked-wallet signals.
data
object

Anti-signal

An anti_signal event is emitted when a token with recent buy signals triggers 2 or more adversarial detection rules simultaneously. Any system acting on the original signal should treat this as an exit cue.
{
  "type": "anti_signal",
  "data": {
    "tokenMint": "...",
    "severity": 3,
    "reasons": [
      "Creator risk score 92/100 (87% rug rate across 34 tokens)",
      "71% of buyers are bots",
      "Coordinated bundle detected (89% confidence, 52% of buyers)"
    ]
  }
}
type
string
Always "anti_signal".
data
object

Signal quality guide

Not all signals carry equal weight. The following combination of fields indicates a high-conviction signal: walletStats.alphaScore above 75 — wallets above this threshold have significantly higher historical hit rates than those below 50. This is the single most important quality indicator. Low buyRank — a wallet entering early (rank 1–5) captures more of the available price movement than one entering later. Higher ranks suggest the opportunity may be further along. Rising velocity — a high buysLast60s relative to buysLast300s indicates accelerating buying pressure. Flat or declining velocity is less actionable. tokenState.bundleConfidence below 0.15 — values in this range indicate organic-looking buying activity. Above 0.7 is a strong negative signal and warrants caution even on an otherwise high-quality wallet signal. tokenState.riskScore below 70 — composite token risk below this level means no severe risk factor clusters are present. Above 70, multiple risk factors are active simultaneously. tokenState.lifecycleState of "momentum" or "early_accumulation" — these are the most actionable lifecycle stages. A state of "distribution" is a warning that smart money may already be exiting.
The canonical high-quality signal pattern is: high alphaScore, low buyRank, rising velocity (buysLast60s accelerating relative to buysLast300s), low bundleConfidence, and a lifecycleState of "momentum" or "early_accumulation".

Build docs developers (and LLMs) love