UP RATE
73%
Market memory · 25M+ indexed analogs · evidence you can audit
The market has seen versions of this before. Chart Library finds them.
Anchor a stock, date, and timeframe. Retrieve comparable historical situations, inspect what happened next, and preserve evidence your research—or your agent—can audit.
For traders & researchers
Replace hours of chart review with an auditable comp set.
Start with a real market situation. Retrieve comparable cases, qualify what belongs, then inspect outcomes and the evidence behind them.
NVDA · 1h · illustrative interfacenot a live result
Uptrend 28%Sharp choppy 10%Sideways 44%Downtrend 18%
25M+
indexed patterns
10yr
across 19K symbols
80.8%
held-out band coverage, not edge
For AI agents & agent builders
Give your agent memory, not another opinion.
MCP and API deliver the same auditable research loop. Start free and keyless; production plans add capacity, workflow tools, and support.
# Hosted MCP — no account requiredhttps://chartlibrary.io/mcp # or run it locally$ pip install chartlibrary-mcp # the canonical loopsearch → pull_comps → introspect → track_record
Trust receipts · live, verifiable
80.8%
Coverage record, held out
Nominal 80% forward-return band held 80.8% across 310,592 audited cases — an audit of past predicted-vs-realized coverage, not a forward claim.
PIT / rank histogramflat across 311K+ audited cases — max deviation 0.5ppRealized outcomes land where the served distributions said they would along the entire shape, not just one band. Served as
pit_histogram in the same endpoint.Live example · NVDA · as of 2026-05-28
300 analogs from 10 years, split into 4 outcome paths.
Not a forecast. The empirical split of what historical analogs actually did over the next 5 trading days. Hover a mode to read its distribution.
Outcome moden5d medianup rate
Uptrendclean continuation84+5.2%73%
Sharp choppy uptrendvolatile, net up31+2.8%67%
Smooth sidewaysrange-bound drift132+1.1%62%
Downtrendfailed breakout53-2.1%43%
Forward-return distribution · 5d
Uptrend
IQR (25–75)
+1.8 / +8.9%
A new way to query markets
Start with the chart. Then ask whether the situations belong together.
Old way · indicator search
Search by formulas someone wrote.
- Define a “rising wedge” with a math expression.
- Scan the universe for charts matching the rule.
- You query in indicator space — the same query for everyone.
- Limited to patterns someone bothered to formalize.
TradingView · ThinkOrSwim · Finviz · Trendspider
Chart Library · pattern search
Use shape to find candidates. Use context to qualify them.
- Take an actual chart — a real stock on a real date.
- Retrieve the closest historical shape matches as a candidate set.
- Refine by news, regime, liquidity, fundamentals, and other conditions.
- Then inspect outcome modes, drivers, sample size, and the audit record.
25M+ patterns · 19K symbols · 10 years
How a query flows
Retrieve. Qualify. Remember.
01 / ANCHOR
Anchor
Your agent picks any (symbol, date, timeframe). NVDA · today · 1h — the chart you want to understand.
02 / MATCH
Match
The system finds historical days with similar price + volume shape, then lets you qualify the set by the conditions that made the trade what it was.
03 / STRATIFY
Stratify
Cluster the 500 analogs into 3–4 outcome modes by what they did next. Each reports count, median, up rate, and distinguishing features.
How the agent talks to you
We don’t script the agent. We hand it the comp set.
The MCP tool returns descriptive comp-set fields — comp strength, match quality, conditions, coverage record, and the drivers that separated past winners from losers. Your agent reads them and writes the answer in its own voice. Numbers stay in parentheses.
pull_comps returned · comp set summary
comp set
comp_strength=lowmatch_quality=looseconditions=normalcoverage=0.81
drivers
sector_laggingnarrative_passiveearnings_near
caveat_flags
soft_in_regime_sampleregime_was_derived
sample
quality=okn_in_regime=21n_total=132
CLagent reads the flags and writes in its own voice ↓
“Honestly, this one reads like a coin flip. NVDA’s in-regime analogs printed about the same as everything else — the comp set doesn’t separate up from down here.”
Of the 132 closest analogs, 21 printed under a regime like today’s. Their 5-day median was +0.09% with a 52% hit rate — small enough that the regime isn’t doing much work.
What I’d watch
- Sector lagging hard. XLK 60-day RS is −10.4 — skews tech reads lower until it turns.
- News without follow-through. Pulse +0.29 — looks like vol repricing, not a narrative change.
- Earnings in 16 sessions. Pattern reads weaken this close to the print.
POST /api/v1/pull_comps · NVDA · 2026-05-11 · 1h● ~9ms retrieval · 1-3s warm call · not financial advice
Every read is grounded in the 13 canonical tools your agent can also call directly: search pull_comps cohort_introspect cohort_members cohort_groupby cohort_rerank symbol_intelligence analyze context explain portfolio track_record report_feedback — pull_comps is the front-of-house comp-set primitive (cohort_analyze remains available with its original field names).
The coverage record · held-out, symbol-disjoint
80.8%
Our nominal 80% forward-return band held 80.8% across 310,592 audited cases (5-day horizon, no same-stock leakage). It is an audit of past predicted-vs-realized coverage, not a forward claim — and it is live: call /api/v1/calibration and check it yourself.
Against an ungrounded LLM on 300 out-of-sample setups, that band matched the model’s own 80% interval on coverage (~83%) in a band 44% tighter — same honesty, half the vagueness, reproducible from the public API.
Separately, in a blind paired evaluation a judge — not told which agent held which tools — preferred the grounded reasoning on every scenario, across all six dimensions below. An agent given a research desk investigates more, so a gap is expected by construction; what the blind judge adds is that the grounded reasoning was preferred even when both agents reached the same conclusion.
Read the full methodology →For developers
Market memory for any AI agent.
MCP-native. Works with Claude Desktop, Cursor, Hermes Agent, or any MCP-capable client. Under a minute to install.
# Install$ pip install chartlibrary-mcp # Register with Hermes Agent$ hermes mcp add chartlibrary \ --command "chartlibrary-mcp" # Also works with Claude Desktop & Cursor✓ 13 tools registered · ready
Free
Generous limits for experimentation
$0
Production
Higher-volume research · workflow tools · support
from $29/mo
Enterprise
Custom capacity · integration help · service commitments
Talk to us
Read the API docs
13 canonical tools, calibration report, methodology
Built inside AlphaForge
The product is the memory. The firm is the proving ground.
Chart Library retrieves and preserves comparable cases, evidence, and falsifications. AlphaForge uses that memory to formulate, preregister, and test strategies—and only moves toward trading after they survive. We do not present retrieval accuracy or calibration as proof of trading edge.
01 / REMEMBER
Chart Library
Canonical market events, point-in-time context, comparable situations, outcomes, provenance, and the negative results worth remembering.
02 / TEST
AlphaForge research
Human-led setup selection, disjoint cohorts, immutable preregistration, outcome locks, realistic costs, and explicit kill criteria.
03 / EARN
AlphaForge trading
Shadow and paper execution first. Small live capital only after clean historical evidence and forward behavior agree.
What we are building toward
An honest path from market memory to deployed capital.
The roadmap closes one full research loop before it expands the surface area. Each layer must leave auditable evidence for the next.
Now
Evidence memory
Canonical events, point-in-time context, provenance, calibrated analogs, and durable records of what failed as well as what survived.
Next
Research integrity
Immutable cohorts, outcome locks, experiment registries, execution-aware testing, and a strategy lab that makes self-deception harder.
Then
Execution intelligence
Shadow, paper, and eventually small live deployment—only for strategies that survive disjoint testing and realistic implementation costs.
Chart Library
Give your research a memory it can defend.
Anchor a market situation, retrieve its comp set, and reason from auditable evidence—not a generated opinion.