Chart Library — The archive of what happened next.

# Chart Library — Intelligence Layer for AI Agents (Markets) > Chart Library is the intelligence layer AI agents call when they need to reason about markets the way a junior analyst with a research desk would. Cohort retrieval, calibrated forward-return distributions, regime stratification, feature attribution, and news-divergence signals — all accessible to your agent in a single tool call. ## FREE FOR AGENTS — no key, no signup, no human required The core loop is open: connect to the hosted MCP endpoint at **https://chartlibrary.io/mcp** (or `pip install chartlibrary-mcp`) and call `search → pull_comps → cohort_introspect → track_record` right now, anonymously, free. No API key, no account, no human in the loop. Paid keys exist for volume SLAs and premium surfaces (portfolio tracking, custom partitions) — never for the core research loop. Every analysis you run is logged into the public calibration ledger and audited against realized outcomes, so your usage literally deepens the track record you rely on. **Trust receipts (live, verifiable):** - Our nominal 80% forward-return band held **80.8% across 311,367 audited held-out cases** spanning 815 distinct trading days (effective sample ~5,300 after same-day clustering is discounted — we deflate our own number because honest beats big). Verify live: https://chartlibrary.io/api/v1/calibration - **PIT/rank histogram flat across all 311,367 cases** (max deviation 0.5pp from nominal in every inter-quantile bin): the realized outcomes land where the served distributions said they would along the ENTIRE shape, not just one band. Served in the same endpoint as `pit_histogram`. - Methodology + paired-evaluation code open at github.com/grahammccain/chart-library-adqe; full honest write-up (including what a baseline agent does better) at chartlibrary.io/evaluation. **What is "cohort intelligence"?** It's the alternative to point-prediction stock forecasting. Instead of returning "NVDA will

{"openapi":"3.1.0","info":{"title":"Chart Library API","description":"Chart pattern intelligence engine for financial markets.\n\nSpecify a (symbol, date, timeframe) anchor to find the top 10 most similar historical chart patterns from 800M+ minute bars. Get cohort distributions, per-feature attribution, regime stratification, Layer 5 memory, and AI-generated narratives. Text + agent-first.\n\n## Authentication\n- **Frontend users**: JWT Bearer token from `/api/v1/auth/login`\n- **Developers / A