BTC · ETH · SOL

Your market question. Years of evidence.

Find similar moments, study what followed an event, and compare it with ordinary market behavior.

Explore research → Open the chart

Free during research preview · no card, no account

BTC · BTCUSDT · 4h
—
loading market memory…
One past day, and what followed Open that day →

NEW / EVENT RESEARCH

A market move.
A question worth checking.

What followed a sharp fall? Did a breakout hold? What did SOL do after BTC moved? Ask a specific question, then see the events and the ordinary windows beside them.

PATHDid +2% or −2% happen first?LEVELSWhat followed a break of yesterday’s high?CROSS-MARKETBTC fell. What did SOL do?
Explore the research desk

Original charts · uncertainty shown · no account needed

HOW THE EVIDENCE IS BUILT
01

Say what actually happened.

A fall inside the day is different from a lower daily close. Define the event first, including recoveries and when the observation starts.

The diagrams illustrate the method; dots are not sample counts.

The platform

A shared memory for people and agents.

Explore historical patterns on the chart, or investigate an event with the research desk. Your assistant can query the same engine and share the original evidence.

01 / CRYPTO

Crypto Market Memory

Find comparable moments in stored history, inspect the actual candles, and see what followed beside an ordinary-market background.

  • Similar candles with dated historical episodes
  • Event studies beside ordinary market windows
  • First-touch, level and cross-market research
Open /candles
02 / RESEARCH ENTITY New

Market memory for your assistant

Ask your own questions through an MCP assistant. The engine returns the actual event definition, sample counts, uncertainty and original evidence.

  • Events, sequences and cross-market questions
  • Pinned snapshots and shareable original charts
  • Works in Claude, Cursor, ChatGPT, Codex + RLXBT Docker trial
Connect your assistant

FOR YOUR AI ASSISTANT

The same evidence.
In your own conversation.

Ask about events, sequences, first-touch paths or another market’s response. Your assistant gets pinned results, explicit sample counts and links to the original charts.

Connect Claude, Codex or another MCP client ↗
TRY ASKING

“BTC fell 5% within a day.
What usually happened next?”

Events + ordinary windows + original evidence
Try the same study on the website →
Explore the existing agent tools and standing-watch demo +
A real research result · SOL3 Oct 2026 · 12:00 UTC

If SOL reaches $120,
what happened next?

From a $119.48 query close, we inspected similar situations over the next 10 hourly candles. Target: $121.20. Invalidation: $118.80.

13 of 20

historical analogues reached $120

Among those 13 episodes, after reach:

Target first
6
Invalidation first
3
Unknown event order
2
Unfinished within the horizon
2

Observed historical counts, not a future probability or strategy win rate. Unknown order and unfinished cases stay in the result.

Run this example →View recorded evidence

How it works

From your idea to historical evidence.

01

Choose a market question

Start with an event, a path question or similar candles. See the exact condition before running the study.

02

Keep a fair comparison

Compare what followed independent events with ordinary windows under the same context. See the difference and its uncertainty.

03

Replay the dated episodes

Open the examples behind the counts. Inspect the whole path and weigh the evidence for your idea.

Dated evidence

Every match is a real window with a date you can open and replay.

Path, not just final price

See which levels were reached first, even when the final close tells a different story.

Uncertainty stays visible

Counts include unknown event order and unfinished cases. Sample size is always shown.

Browser and AI agents

Run your research directly or let your assistant use the same evidence through MCP.

Check the quality behind the range estimate.

Compare range estimates with an all-history baseline for each market and timeframe. These scores evaluate ranges; they do not establish that a level hypothesis is a profitable strategy.

See the full record and method →

Bring a question. Inspect the evidence.

Search crypto market memory, or hand it to your AI agent.

Open Market Memory → Check a hypothesis