Seiche — funding-stress terminal

The live money-market funding-stress reading: a 0-100 composite index, the regime (CALM/EROSION/STRAIN/STRESS), per-component decomposition, the market-stress 'Tell', and any data faults. Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity c

Forward odds of a funding-stress event over the next 5/10/21 business days from six independent views: three P(event) models (term structure, first-passage physics, gradient boosting) and three stochastic scenarios on the index (regime-transition Markov, OU plus jump analytic marginal, Monte Carlo p

The historical days most similar to today's funding conditions, and how often those analogs led to a stress event, plus a novelty flag for whether today has any close precedent. Use to ground a 'what usually happens from here' question in real history.

Reconstruct the entire funding-stress board as it read on a historical date, point-in-time with no lookahead: the composite, the regime, the per-component decomposition and the crunch windows for that date. Use to test whether Seiche would have flagged a past liquidity episode, or to align a backtes

The backtest scoreboard, stated honestly: recall and precision with 95% confidence intervals over labelled funding events, an orthogonal robustness test, every named episode (hits and misses), and the caveats. Use to judge how much to trust the readings.

Freshness, provenance, and fault status for every underlying series (FRED, NY Fed, OFR, Treasury). Call this to confirm the board is current before relying on a reading.

Labelled crypto stress episodes (Black Thursday 2020, Terra, FTX, the SVB/USDC weekend, the Oct-2025 liquidation cascade, the Ethena unwind) replayed point-in-time against the dollar-funding board. External wrecks show transmission; crypto-native wrecks show the board correctly staying quiet. Use fo

The stance (risk_on / risk_off / neutral) and positions implied by the stress read, with the walk-forward Sharpe, the live as-published record, and the ensemble event odds. Not investment advice, a codified reading. Built from free public data.

The full human-readable desk brief for today as markdown, a narrative summary of the whole board. Good when you want prose to quote or summarise rather than structured fields. Built from free public data.

Ask a natural-language question about funding conditions, answered strictly from the live board with the grounding cited. Requires an LLM endpoint configured on the server; if none is configured the tool says so instead of guessing.