Compare
Chart Library vs Unusual Whales — what flow is doing now versus what setups like this did next.
Unusual Whales is a window into right now: unusual options activity, dark-pool prints, gamma exposure, congressional trades. It tells you how positioning and flow are skewing in the moment — a real-time sentiment-and-positioning feed.
Chart Library answers a historical, calibrated question instead: “given this exact price/volume setup, what did its closest historical analogs do over the next 1/5/10 days, and how often did the band hold?” It’s precedent with a receipt, served to an agent over API/MCP — not a live flow ticker. The two are complementary: flow is a now signal, base rates are a what-usually-follows signal.
Real-time flow vs calibrated precedent
- Unusual Whales = present positioning. Who’s buying what, unusual contracts, GEX, sweeps — the live tape of option flow and crowding.
- Chart Library = historical base rates. For a setup, the analog cohort’s forward-return distribution with an audit receipt (nominal 80% band held 80.8% across 300K+ audited cases). Never a directional call.
- Different time axes. Flow describes the present; Chart Library quantifies what historically followed comparable presents. An agent can read flow and ask Chart Library “how did setups like this resolve?”
- Agent-native & calibrated. Chart Library is an MCP/REST endpoint that returns a calibrated distribution, not a dashboard a human watches.
Frequently asked questions
- Does Chart Library show options flow, GEX, or dark-pool data?
- No. It's a retrieval-and-calibration engine over historical price/volume analogs. For live options flow, use Unusual Whales (or an options-analytics feed); Chart Library supplies the calibrated historical base rates for the setup.
- Is it an Unusual Whales alternative?
- Not directly — different time axis and different question. Unusual Whales tells you what flow is doing now; Chart Library tells you what historically followed setups like this, calibrated. Many traders/agents use both.
- Does it predict direction from flow?
- Never. It surfaces what historical analogs did next as a calibrated distribution with a coverage receipt — similarity-only, no forecast.
Try it
Run a cohort_analyze call.
Free Sandbox tier — 1,000 calls/day, no authentication. MCP install for Claude or Cursor takes 30 seconds.