Pick a name. We find similar market states in history and show the range of what followed. Then we write one note a day on the stock people are already arguing about, and we score it when the window closes. Not a forecast. Not a buy or sell.
Free. No account. Agents can use the same memory.
Start with a ticker and a completed trading day, in the browser or through an agent.
Read how many comparable days we found, and the range of what followed.
A similar-looking day can still have different news. Missing evidence stays missing.
One trending name, the range from similar history, and a score at the close.
Read the notesWhat the low, middle, and high numbers mean, and when history is a poor guide.
How it worksWe found historical matches, then looked at the hour before each one. The clock and the earlier move changed the comparison.
Read the case
We test what makes a useful comparison, where similar-looking history breaks down, and what the evidence can support. Failed tests stay in the record.
Closer historical matches had less spread among their later outcomes. This does not establish a narrower forecast band for the stock being examined or predict its direction. Study 101 tested the weighting follow-up.
Widening ranges on non-earnings gap days improved coverage in the held-out test. More later outcomes fit inside the range, at the cost of a wider range.
Matching the event type did not produce narrower ranges at equal coverage. The test also exposed weak coverage on event days, which Study 103 investigated.
Each result belongs to its own question, sample, and date. A pass does not bless every other page on this site.
Connect through MCP or REST. Each public tool answers a research question with dates, sample sizes, and limits your agent can keep next to its answer.
https://chartlibrary.io/mcpAn example question
What does AAPL’s latest completed session resemble in history?
market_state(symbol="AAPL")What the tool returns
These ranges describe the historical sample. They are not automatically calibrated forecasts.
Illustrative call. This example does not run a live request.
An example question
What does the published daily research show, and how were its examples selected?
daily_note()What the tool returns
Keep the publication date and selection rule. Outcomes that have not settled remain unknown.
Illustrative call. This example does not run a live request.
An example question
Which method does the published calibration evidence actually evaluate?
research_quality()What the tool returns
A finding applies to the method and sample it names. It does not validate every comparison.
Illustrative call. This example does not run a live request.
Chart Library is the public market-history tool. Alphaforge writes the daily notes using that history. Both are free. Neither is a recommendation.