Give AI agents access to comparable market history and what followed. Explore the evidence yourself, with research written for people and tools built for agents.
Free public research access. Start without an account or API key.
Start with a stock and a completed trading session, through your agent or in the browser.
Read comparable observations, what followed, and how much evidence is available.
Use the research to question similarities, understand context, and recognize the limits.
Connect through MCP or REST. Each public tool answers a research question independently, with evidence your agent can keep alongside its answer.
Explore the agent toolsAn 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.
Choose a stock, inspect comparable moments and read the range of historical outcomes.
Search a stockFollow one chart through its historical matches. See what looks similar and what changes the comparison.
Read the Chart CasebookA fixed rule selects unusual stock observations. Read the historical ranges and later outcomes as they become available.
Explore daily examplesNew to ChartLibrary? Follow a real chart through a two-minute research example.
We found historical matches, then looked at the hour before each one. The clock and the earlier move changed the comparison.
Read the case and inspect the charts
We study what makes a useful comparison, where apparent similarities break down, and what the evidence can support. We publish the work so people and agents can examine it.
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.
We publish the question, the test, and the finding, including ideas that did not work. Each result belongs to its own method, sample, and date.
Chart Library brings historical market evidence into AI workflows and human research. Connect an agent, investigate a stock, or follow a study from question to finding.