v4.2.0

Evidence-First Financial AI

Every signal traces to a real SEC filing.

Agent Research API · MCP · LangChain/LlamaIndex · pip install yuclaw
Disclaimer — Research & education only. Not investment advice. Signal labels are research classifications, not buy/sell recommendations.
Current signals — Forward Tracking Ledger
TickerSignal labelScore
AMATSTRONG_BULLISH+0.596
BACBULLISH+0.548
WFCBULLISH+0.533
CBULLISH+0.526
XBIBULLISH+0.514
AXPBULLISH+0.494
XLFBULLISH+0.479
JPMBULLISH+0.447
KREBULLISH+0.441
INTCBULLISH+0.434
VBULLISH+0.431
IBBBULLISH+0.429
MSBULLISH+0.410
PYPLBULLISH+0.405
SMHNEUTRAL+0.367
XLINEUTRAL+0.352
LRCXNEUTRAL+0.345
MANEUTRAL+0.333
ABBVNEUTRAL+0.320
JNJNEUTRAL+0.308
DIANEUTRAL+0.286
TSLANEUTRAL+0.285
DHRNEUTRAL+0.281
MRKNEUTRAL+0.278
IWMNEUTRAL+0.275
GSNEUTRAL+0.274
UUPNEUTRAL+0.268
AAPLNEUTRAL+0.263
AMDNEUTRAL+0.262
MDYNEUTRAL+0.260
DELLNEUTRAL+0.242
XLYNEUTRAL+0.241
XLVNEUTRAL+0.237
METANEUTRAL+0.235
IEFNEUTRAL+0.233
XLKNEUTRAL+0.232
MUNEUTRAL+0.231
TLTNEUTRAL+0.231
TMONEUTRAL+0.229
TAILNEUTRAL+0.217
SPYNEUTRAL+0.216
XLCNEUTRAL+0.211
LLYNEUTRAL+0.209
UNHWATCH+0.186
QQQWATCH+0.182
GOOGLWATCH+0.181
ABTWATCH+0.180
AMZNWATCH+0.178
XLBWATCH+0.155
MSFTWATCH+0.144
MRVLWATCH+0.137
LUNRWEAKENING-0.135
PSXWATCH+0.134
HPEWATCH+0.134
BMYWATCH+0.118
GLDWATCH+0.115
PGWATCH+0.110
EEMWATCH+0.090
NVDAWATCH+0.086
CVXWATCH+0.085
KOWATCH+0.078
XLREWATCH+0.065
XOMWATCH+0.065
ARMWATCH+0.063
CRCLWATCH+0.063
FXIWATCH+0.058
COPWATCH+0.054
SLBWEAKENING-0.041
RKLBWEAKENING-0.033
XLEWEAKENING-0.032
VIXYWATCH+0.027
SLVWEAKENING-0.024
PEPWATCH+0.019
PFEWEAKENING-0.016
VXXWATCH+0.008
XLUWATCH+0.007
WMTWATCH+0.004
XLPWEAKENING-0.003
COSTWATCH+0.003
data as of 2026-07-06 17:00 UTC · landing page rebuilt 2026-07-06 23:00 UTC
Public signal vocabulary

Labels are research classifications, not buy/sell recommendations:

STRONG_BULLISH · BULLISH · NEUTRAL · WATCH · WEAKENING · NEGATIVE_EVENT · BEARISH_WATCH · RISK_ALERT

There is no SELL or SHORT label. The SDK's _validate_label() is invoked on every signal-bearing return.

How it works

1 · Evidence layer

SEC EDGAR filings (Form 4, 8-K, 10-Q, 10-K, 6-K) are extracted with a local Llama 3.1 70B model. A deterministic SourceLock Guard validates every extraction against the source text before any signal sees it.

2 · Composite scoring

Nine components combine into a confidence-weighted composite. C6 event impact carries the highest weight (0.18) — by design, the evidence layer leads.

3 · Time-machine replay

Any signal can be recomputed as of a past date. Point-in-time filtering (available_as_of <= as_of) is leak-audited; reproducible via the yuclaw replay CLI or REST API.

4 · Verified Research Ledger

Each day's published signals have their content hashes committed to a public git repo (yuclaw-trust). Anyone can call yuclaw verify to confirm a signal hasn't been edited since publication.

Full disclaimer & methodology

Open-source equity research where every composite signal traces back to a verifiable SEC filing or deterministic supply-chain cascade. Replayable point-in-time. Tamper-evidenced via a public git-anchored Verified Research Ledger. Research and education only.

Disclaimer — YUCLAW research output. Not investment advice. Past performance does not guarantee future results. Signal labels are research classifications, not buy/sell recommendations. YUCLAW is not a registered investment adviser. Past results — in-sample or forward-tracked — do not predict future performance.
Install + try it
pip install yuclaw
yuclaw demo                         # 3-minute guided "Why AMD?" journey
yuclaw why NVDA                     # signal + evidence trail
yuclaw verify NVDA --as-of 2026-05-20   # check the public ledger

SDK + REST API + MCP server documented at github.com/YuClawLab/yuclaw-brain. REST API terms at /API_TERMS.md.