Rules trade, LLMs explain. Live, non-custodial, with receipts.
Open the app · Telegram bot · Kakao channel · API docs
- Signals you can act on, with context. Not "BUY" —
GO / WATCH / HOLD+progress_pct(0–100% lifecycle) + entry / stop / target. - It explains itself. Every signal has a structural cause (multi-timeframe alignment, state machine phase) that an LLM translates into plain language.
- Same engine, two markets. Crypto (24/7) + Korean equities (KOSPI + KOSDAQ, Beta).
- Use it your way. Web app, Telegram, Kakao channel, REST API, or MCP server inside Claude / Cursor.
"Where are we in the current structural cycle — and what's the next optimal move?"
| Path | Best for | Start |
|---|---|---|
| 📱 Web app | Most people — full dashboard, mock trading, KRX watchlist | decker-ai.com — sign up free |
| 🤖 Telegram bot | Quick signal checks on your phone | @deckerclawbot — /start |
| 💛 Kakao channel | 한국 사용자, KRX 시그널 알림 | pf.kakao.com/_RxlxjVX |
| 🧠 MCP server | Claude / Cursor / Codex users | decker-ai.com/mcp — 2-min setup |
| 🛠 REST API | Developers building bots & apps | DEVELOPER_README.md |
Free tier is generous (30 calls/day on the API; Web + Telegram included). During Beta, signed-up users get PRO access for free.
Start here — 30 seconds. No signup, no key.
curl -s https://api.decker-ai.com/api/v1/public/demo | jq .
progress_pct + operation_gate + entry / stop / target.
Every morning (08:00 KST): the engine's view per symbol — baseline, what winning and losing look like, and a pick you can answer. Evening: the same view scored against what actually happened — hits and misses alike, on the record. We stamp our wrong calls too.
Web hub: decker-ai.com/briefing · Subscribe: @deckerclawbot → /briefing
1. progress_pct — every signal has a lifecycle.
A signal at 25% progress is a different trade than the same signal at 80%. Most tools just say "BUY"; Decker tells you where in the move you are.
Entry Target
0%──────────33%──────────50%──────────67%──────────83%────────100%
Wait Entry Active Late TP Final TP Exit
2. GO / WATCH / HOLD — three gates, not binary.
| Gate | Meaning |
|---|---|
| GO | Structure confirmed — entry conditions met |
| WATCH | Signal forming — monitor, no entry yet |
| HOLD | Active position — no new entry signal |
WATCHis the gate most tools skip. It's why users enter too early.
3. Deterministic + traceable. LLM explains, doesn't decide.
| Typical AI signal | Decker | |
|---|---|---|
| Source | ML / LLM price prediction | Deterministic state machine |
| Output | BUY / SELL | progress_pct + operation_gate + ranked choices |
| LLM role | Makes the call | Explains the structural state |
| Auditability | ❌ Black box | ✅ Every signal has a trace_id |
| Cost per signal | High | $0 on the rules path |
| Reproducibility | ❌ | ✅ Same input → same output, always |
| Tier | Price | Daily API limit | MCP | Auto-trade |
|---|---|---|---|---|
| FREE | $0 forever | 30 calls/day | read-only (1d cache) | ❌ |
| PRO | $20 / mo · 7-day trial | 10,000 / day | full (7 tools) | virtual + real |
| ENTERPRISE | Contact us | 100,000+ / day · custom | full + per-org skill catalog | + custom integration |
Beta (now): all authenticated users get PRO for free via
BETA_TIER_OVERRIDE=PRO. No payment required.
Web sign-up and Telegram bot are always free for the basics.
Building a bot, app, or agent on top of Decker? Everything you need — REST endpoints, MCP server (Claude / Cursor / Codex), Python SDK, OpenClaw skill, self-host — lives in one place:
# 60-second smoke test (no auth needed)
curl https://api.decker-ai.com/api/v1/public/demo# With an API key (decker-ai.com → Settings → API Keys, or Telegram /apikey)
curl "https://api.decker-ai.com/api/v1/public/signals/BTCUSDT/latest?timeframe=1h" \
-H "X-API-Key: dk_live_xxx"Prefer a runnable file? → examples/quickstart.py — zero dependencies (stdlib only), no key, prints the composed view + receipts in one run. Wrapping Decker for an agent crew: examples/langgraph_decker_tool.py. More in examples/.
The demo returns the composed view — the same card our daily briefing sends:
{ "layer": "STATE_VIEW", "symbol": "BTCUSDT", "ref_price": 63650.0,
"lines": ["■ BTC — 층간 힘겨루기: 주 판 아래쪽 · 지금 판 위쪽", "…"],
"wait_target": "...", "invalidation": "...",
"verdict_recent": [{"briefing_date": "2026-07-05", "slot": "morning", "verdict": "hit"}],
"provenance": { "composer": "briefing_story.compose_card" } }Add to Claude Desktop / Cursor (MCP): guided 2-minute setup with per-client config → decker-ai.com/mcp.
Cursor (~/.cursor/mcp.json) takes a remote server directly:
{
"mcpServers": {
"decker": {
"url": "https://api.decker-ai.com/api/v1/mcp/sse",
"headers": { "X-API-Key": "dk_live_YOUR_KEY" }
}
}
}Claude Desktop / Codex reach it through the mcp-remote bridge (needs Node/npx) — see decker-ai.com/mcp or DEVELOPER_README.md (endpoints · auth · rate limits · MCP 7 tools · SDK · OpenClaw · self-host).
Running a multi-agent crew (TradingAgents / LangGraph / AutoGen)? Give your analysts one deterministic market-state instrument — with receipts — instead of re-deriving structure per prompt: → docs/integrations/multi-agent-frameworks.md
Raw OHLCV candles
↓ Sequence Labeler → every candle gets a role (anchor / test / signal)
↓ State Machine → C_SET → B_FORMING → B_SET → A_FORMING → W_PENDING
↓ Operation Gate → GO · WATCH · HOLD
↓ RULES Engine → 9-layer YAML rulebook → strategy + ranked choices
↓ AI Consultation → LLM translates structural state → plain language
↓
"67% progress. B-leg confirmed. Recommended: 30% partial TP or hold to target."
No price prediction. No black box. Every output traces to a formal structural cause.
Deep dives: Sequence Engine · Labeling Algorithm · Market State Theory
Crypto (GA): BTCUSDT · ETHUSDT · SOLUSDT · BNBUSDT · XRPUSDT · DOGEUSDT — timeframes 30m, 1h, 4h, 1d.
KRX (Beta, free): KOSPI 948 + KOSDAQ 1,822 = 2,770 tickers. Universe = top 200 by trading value ∪ user watchlist ∪ momentum spike ∪ volume spike. Timeframe 1d only (1w expanding). Daily evaluation at 16:30 KST.
KRX details: docs/krx/KRX_BUSINESS_MODEL_AND_ROADMAP_2026-05-09.md.
We don't publish a headline win rate. Backtest numbers without method and sample size are marketing, not evidence — and easy to cherry-pick.
What we stand on instead:
- Deterministic & reproducible. Same input → same output, always. The rules path has zero LLM in it, so a signal is not a model's opinion — it's a formal structural verdict you can re-derive.
- Auditable. Every read carries its
provenance(composer + the versioned rulebook contract) and traces back to the exact engine emit. The full RULES.yaml is open, so you can re-derive any verdict yourself. - Scored in public, daily. The morning briefing's view is graded against what actually happened that evening — hits and misses alike, on the record. → decker-ai.com/briefing · a GitHub Action stamps the daily scorecard straight into this repo: TRACK_RECORD.md
Method and rulebook are open: Model & Algorithm · Operation Rules (YAML) · Signal Performance.
For information only. Not investment advice.
| DEVELOPER_README.md | API · MCP · SDK · OpenClaw · self-host — start here if you're building |
| Developer API Guide | Auth · rate limits · FAQ (long form) |
| Architecture | Pipeline, state engine, modules |
| Model & Algorithm | How the signal engine works |
| Operation Rules | Open YAML rulebook (v2.4.7+) |
| Article Series (1–15) | Deep dives on Medium |
| Roadmap | What's next |
| llms.txt | LLM / AI agent discovery manifest |
| Web app | https://decker-ai.com |
| API docs | https://api.decker-ai.com/docs |
| Telegram bot (crypto) | https://t.me/deckerclawbot |
| Telegram bot (KRX) | https://t.me/krxdeckerbot |
| Kakao channel | https://pf.kakao.com/_RxlxjVX |
| X / Twitter | https://x.com/blockoceandev |
This repository is the public hub for Decker AI — SDK, samples, rulebook, architecture docs, OpenClaw skill packages. Production application code runs in a private monorepo. All listed endpoints, channels, and the web app are live.
Built by gigshow (Dohyung Kim · 김도형) — founder. Open to investor / partnership conversations.