Seiche — world-markets evidence terminal

SEICHE

Release scope: 28 October 2026

Eight public research tools are available: source_rights_status, money_market_context, market_workbench, world_markets_context, gift_city_context, gold_inventory_carry, research_network, data_health. Start with source_rights_status. Retired forecasts, backtests, editorial, composite and derived legacy tools are unavailable for every caller while their source reuse rights and replacements remain unqualified. A bearer token or payment does not unlock them. Do not reconstruct withheld observations from metadata, cached history or prior responses. Direct publisher observations keep their own dates; restricted inputs remain explicitly metadata-only. Authenticated callers can additionally discover five private, non-executable Agent Room tools. Earlier feature descriptions below are historical context where they conflict with this release scope; they do not advertise availability.

Connect and ask one question

Hosted Streamable HTTP MCP; no local server or API key for public read-only tools. Add the products you need to Claude Code:

claude mcp add --transport http seiche https://api.seiche.info/mcpclaude mcp add --transport http liquilens https://api.liquilens.in/mcpclaude mcp add --transport http undertow https://api.seiche.info/undertow/mcp

Try this first: What is the current US funding stress regime, and which dated funding events are next? Cite source dates and missing evidence.

Try it in your browser · Cursor configuration · Codex commands · Free three-product starter kit and skill

For a connected review, ask for institution evidence → funding context → BTC exit estimates, with each source date, coverage gap and limitation kept separate. Client/model costs and fair-use limits may apply. Research calls do not execute trades.

Choose the tool by the answer you need

Start with source_rights_status for feature availability and data_health for source clocks and faults. The broader tools have different jobs:

Start with the row matching the task. The tool selection guide includes all public tools, example questions and a repeatable funding-review workflow.

Public US dollar funding research from source-dated Fed and Treasury observations. Live board: seiche.info.

Dated answers to common research questions explain the numbers, source dates and limits.

LiquiLens, Seiche and Undertow are connected research products from LIQUILENS PRIVATE LIMITED, a registered company in India. Built for international review workflows: institution evidence → funding conditions → market liquidity. Market coverage, source clocks and authority remain specific to each product. Company and investors · Company profile · Try the connected workflow.

[sealed record]

A seiche is a standing wave in an enclosed body of water — invisible from the shore, until it sloshes over the edge. Funding stress behaves the same way.

Seiche is a free, open source (AGPL-3.0-or-later) money-, foreign-exchange and capital-market evidence terminal organized around the dollar funding system — US money markets, 22 public H.10 currency reference series, the Treasury capital-market complex, the global basins connected through swap lines, and the offshore-dollar crypto basin moored to the T-bill market through stablecoins. The core US board and USD desk use free official/public APIs (FRED, NY Fed Markets, OFR STFM, Treasury FiscalData, CFTC, ECB Data Portal, DeFiLlama, Coinbase Exchange). The global market-pack catalog can also declare licensed or tenant sources, but public outputs obey each source's redistribution policy and never expose restricted raw values.

Seiche publishes a construction-PIT historical diagnostic—with misses and eligibility limits kept visible—and is now accruing a separate as-published forward record that can be verified instead of reconstructed. Licensed terminals provide much broader real-time data and execution workflows, while OFR and NY Fed dashboards provide authoritative source views. Seiche is a narrower, opinionated research layer: forward-looking, alerting-ready, and provenance-honest. It is not a Bloomberg/Reuters replacement, a real-time quote service, or an execution venue.

The lab

Seiche is one of three altitudes in a single liquidity lab that fills that gap: Seiche reads the plumbing, LiquiLens organizes institution evidence for review, and Undertow measures market liquidity itself (who provides depth in each segment, what an exit at position size costs today). The wiring between the three is real, not a brochure: the desk assistant pulls the LiquiLens failure board over MCP, the MARKET tab renders Undertow's published pack live, and the Windfetch engine reads the FETCH pack built in the Undertow repo back into this board. On names: the internal composite engine called "undertow" (critical slowing down, engines/undertow.py) is unrelated to the Undertow sister product.

For a first connected review, start with funding context in the browser. The shared portfolio plan prioritizes a recurring reviewer task while keeping each product's evidence and authority separate.

For a recurring agent workflow, the free starter kit combines Seiche funding context with LiquiLens bank evidence and Undertow exit estimates. Use the Hermes or OpenClaw setup guide. The selected public tools need no API key; fair-use limits and separate model-provider costs apply.

Use Seiche everywhere

Seiche is distributed as software, an MCP service, a research dataset, and machine-readable catalog metadata. Status is receipt-based: listed means a durable public record and receipt exist, prepared means an owner-controlled submission or publication remains, and blocked means a named prerequisite must clear first. “Usable in repo” describes local artifact readiness, not a ledger status. The auditable source of truth is distribution/submissions.csv.

Version 0.16.3 estuary checks the four monthly OFR money-market-fund series and six quarterly BIS series daily while preserving their observation dates and native release cadence. Signed deployment and publication acceptance are required before this source change is live.

Version 0.16.2 estuary prepares the reviewed Google-Extended policy, three dated dollar-funding answers and Riptide's public paper allocation beside the Market desk. The policy permits grounding/training only on three reviewed original explanations; source data, archives and other pages remain excluded. New signed application and publication receipts are required before these changes are live. The inherited 0.16.1 release connects the UAE DONIA reference to GIFT City's AED card and retains country funding and sovereign references for China, Japan, South Korea, Taiwan, Australia, the United Kingdom, all 21 euro-area countries and seven other European countries. Official observations retain their source dates, native frequency and gaps. The eight public MCP tools expose the country catalog through money_market_context(section="countries"); add country="JP" for a country desk or use section="india" for the India desk. New official SOFR, EFFR, IORB, overnight reverse-repo and New York Fed funding observations can reach the daily review without waiting through the previous four-to-twelve-hour cache windows. Failed refreshes retain the original source dates and stale warnings. Deployment and immutable package publication remain subject to signed release gates.

The verified NY Fed historical importer covers 34 canonical instruments. Archived observations retain unknown publication clocks and actual ingestion times, preserve existing live vintages, and remain excluded from forecast inputs that require known publication clocks. The structured funding, forex and China workbench retains exact source dates, units, capture evidence and missing states. Numerical China context requires its independent signed acceptance. Verify deployment and package availability from the release receipts and linked registries.

Eight research tools remain anonymous and free. Legacy derived tools are unavailable; client and catalog copy must preserve that boundary. See the distribution and container trust guide for verification and release invariants.

v2 "Deep Water" — an accountable engine fleet, layered analytics, one terminal

v2.3 "Letters of Marque" (built in tandem across two sessions) adds the forecast layer and the layer that makes every other layer accountable: Undertow (critical slowing down — the basin's damping, measured on ordinary days), the Swell Forecast (the funding-stress forward curve — P(pop ≥ x bp) by date, six weeks out, from the public forcing calendar), The Stack (walk-forward ensemble of every event forecaster — rule, ML, analogs, Swell — plus The Tell, with a disagreement gauge), The Book (HELM tab — explicit daily positions on 2y/10y duration proxies, S&P and BTC over a T-bill base, walk-forward P&L with costs, block-bootstrap Sharpe CIs and mandatory benchmarks, verdict printed even when it loses), a hash-chained as-published track record shipped inside the static publish (nobody, including the operator, can quietly rewrite a bad month), and the Far Basin — Palimpsest's censorship-fear channel (palimpsest.info), a policy confession signal no market data vendor carries, honestly quarantined until it accrues testable history.

★ = methods invented for this tool.

The desk assistant: seiche ask "why is the index elevated?" (or the Ask box on BOARD) answers strictly from a deterministic context pack of the live board — every number cited to its engine and as-of date, "not on the board" instead of improvisation. Routed through free-llm-router's free tiers, or any OpenAI-compatible endpoint via SEICHE_LLM_BASE_URL; with neither configured it returns the context pack itself.

The analytics layers on top:

• The Tell — plumbing percentile minus market-priced-stress percentile (VIX, HY/IG OAS, rates vol). Positive = the basin is sloshing and the screens haven't noticed. The whole thesis in one tradeable number.
• The Estuary — upstream FX/material pressure minus the funding pressure already priced in SOFR and commercial paper. A positive Passage gap says the cash burden is running ahead of its usual landing zones; the discovery/holdout map then shows which links actually survived unseen history. Monthly physical breadth is never filled forward into the daily evidence, and the cash lab never pretends user assumptions are observed exposures.
• The Navigator — an LLM forecaster made accountable: one committed P(funding event, 5bd) per data-day, grounded strictly in the live board, written into the hash-chained record. An LLM cannot be honestly backtested (it has read the history), so its FORWARD record is its only evidence and its weight stays zero until that record earns a hearing. seiche navigator.
• The Communiqué — FOMC statements read as vintage-stamped data: frozen deterministic lexicons score policy direction, balance-sheet bias and funding-stress vocabulary per statement; the change vs the previous statement is the signal, and the Time Machine replays text as it stood.
• The TED bridge — the ML Lab pretrains on the TED spread's 1990–2018 funding-stress record (2008/2011/2016) in the same feature slots, down-weighted, and publishes the transfer gain vs the SOFR-only model either way.
• The Stack + The Book — the rule index, ML Lab, Tide Tables analogs, the Swell curve and Bathymetry's first-passage odds all emit P(funding event, 5bd); the Stack calibrates and blends them walk-forward (publishing the equal-weight mean whenever the fitted blend can't beat it), publishes member dispersion as a first-class ambiguity signal, and the Book converts the result into explicit daily paper positions with costs, benchmarks and bootstrap CIs. Every view's daily forecast and every position is appended to the hash-chained PIT record — a track record no reconstruction can polish.
• Turn Barometer — forecasts the next month/quarter-end turn's severity with leave-one-out cross-validation, always benchmarked against a naive forecast. When the model can't beat naive, it says so and publishes naive instead.
• Playbook — what S&P/VIX/OAS/yields did the last N times the board looked like this, in native units, with n printed. Decision support, not advice.
• PROOF — the construction-PIT diagnostic lab: the index rebuilt with expanding-window statistics only (causal truncation is unit-tested, but source history is final/current-vintage), recall/precision with Wilson 95% intervals, run-level precision (alert days are serially correlated; runs are the honest trials), episode-by-episode lead times including the ones it missed — and the orthogonal signal test: the same event-capture with the target's own variable family (spread/tails) removed from the signal. At build: orthogonal recall 69% [CI 42–87] vs 62% full, with the structural components alone at the 98th–100th percentile 42 days before the Sep/Dec-2025 squeezes. The claim is causal structure, not autocorrelation.
• Time Machine — final/current-vintage construction-PIT reconstruction using observations dated on or before any date since ~2018; it does not recreate the publication vintage visible then. Reconstructed to Sep 12 2019, the board reads EROSION with reserves $576B below the kink and flags Sep 16 2019 — the exact day the repo market broke — as a crunch window.

Principles: no naked numbers (every value carries source + as-of + staleness), fail-loud (a dead feed shows as DEAD and reduces published coverage — it never silently vanishes), honest lags (COT is T+3 by construction; shown, not hidden), and honest scope (a registered market with no qualifying public benchmark stays visible as unavailable; a policy rate or restricted input is never relabelled as a live traded benchmark).

Public world-market contracts

The Market Atlas drills from nine live market packs into canonical instruments, observations, source/publication/ knowledge clocks and rights, then continues into the shared bulk corpus at /api/v2/corpus. Full normalized BIS rows use bounded, generation-bound access. The engine ledger reconciles 1,118 acquisition attempts to 1,110 verified unique objects, including eight recovered retries; its immutable public index exposes only rights-approved metadata and structural profiles. BSE, NSE, NY Fed and restricted acquisition recipes remain explicit metadata-only collections when values or downloads are not publishable. Complete public BIS flows use immutable manifests and content-addressed, byte-range-capable gzip shards so large transfers can resume without mixing generations. Seiche request handlers do not fetch this corpus into an analytic, and an object's data_class or acquisition review never grants model, training, scoring, execution or redistribution permission. See docs/MARKET_CORPUS.md for endpoints and invariants.

• GET /api/v2/world-markets returns the versioned seiche.world-markets.v1 projection of an already completed snapshot. It connects money-market funding, 22 official daily FX reference series, three trade-weighted dollar indexes, and a bounded macro-capital transmission view through selected Treasury, credit, volatility, dealer, positioning and commodity evidence, plus a signed metadata-only China macro side projection over four release-reviewed NBS series identities. The response carries canonical citation URLs, separate generation/evidence clocks, and observed, derived, structural, restricted or unavailable status. Add ?section=forex (or summary, money_markets, capital_markets, china_macro, sources, methodology, all) for a smaller projection. The request never starts collection, scans historical repositories or fits a model.
• Crawlable citation pages live at /markets/, /markets/forex/ and /markets/capital-markets/, with the signed metadata-only China catalog at /markets/china-macro/. They describe real public coverage and its gaps; they do not claim executable quotes, every security or licensed redistribution rights. China raw exports, histories and values remain restricted and never enter a gauge or score; see docs/NBS_SIGNED_EXPORT.md for the operator and verification contract.

Public money-market contracts

• GET /api/money-markets returns the full USD Money Market Desk. Every metric carries its source, as-of date, cadence and plain-language explanation; meaningful cards add native-series changes, a one-year robust z-score and a three-year empirical percentile. Derived spreads use exact common observation dates—there is no forward-fill across unrelated source clocks. The headline displays both the raw most-extreme channel and a conservative Bonferroni- adjusted desk-wide rank; reserve and ON-RRP stock levels remain visible context but cannot manufacture a funding-stress label by themselves.
• GET /api/v2/money-markets returns the Global Money Market Atlas from already collected canonical observations for all 11 registered packs. Eleven is a catalog count, not a claim of 11 live benchmarks or validated markets. It also returns a 44-row source-audited expansion ledger with benchmark taxonomy, authority link, access/rights caveat, confidence, review stage and verification date. Those rows are discovery metadata, not quotes. Query coverage, faults and per-market status for what is actually available now; the request never starts collection.
• GET /api/v2/country-funding lists country coverage; append /JP, /CN, /KR, /TW, /AU, /GB, /DE, /FR, /ES or another catalog code for dated policy, funding, liquidity and sovereign references. UK aliases GB. MCP exposes the same chartless data through money_market_context with section="countries", country="JP". Shared euro-area policy is separate from national sovereign debt. See sources, dates and gaps.
• GET /api/v2/india-funding returns the India funding desk: RBI liquidity and policy evidence, money-market rates, dated sovereign benchmarks, monthly maturity spreads and separately labelled bond auctions. MCP exposes the same chartless payload through money_market_context with section="india". Missing daily tenors remain explicit; India remains reference context.

Atlas state is explicit. AVAILABLE means a redistributable raw observation is present. DERIVED_CONTEXT means a restricted/derived-only input may contribute non-reversible own-history statistics, while its raw level and history remain withheld. POLICY_ONLY means an official policy anchor is visible but no eligible traded benchmark is available; policy is not used as a substitute. A declared unavailable market remains an evidence gap, not a calm reading. Changes and history windows follow each adapter's native cadence—weekly or monthly series are never padded into daily data—and cross-market comparison uses own-history normalization rather than unlike rate levels.

Seiche's AGPL-3.0-or-later license covers the code. It does not override upstream terms: allowed inputs may expose values, derived_only inputs expose bounded derived context, metadata_only inputs can describe availability but cannot enter public calculations, and prohibited values and source metadata are omitted.

Run it

# backend (Python 3.12+)cd backendpython3 -m venv .venv && .venv/bin/pip install -e ..venv/bin/uvicorn seiche.api:app --port 8787
# frontend (dev)cd frontendnpm installnpm run dev          # http://localhost:5173 (proxies /api to :8787)
# or production single-process: npm run build, then uvicorn serves frontend/dist at /

First load is slow (cold fetch of several years of history); everything after is served from the SQLite cache with cadence-aware TTLs.

The operator CLI

seiche pull               # force-refresh, print the index lineseiche brief --save       # this morning's desk note (markdown, archived to data/briefs/)seiche alert              # evaluate alert rules once (cron/launchd-friendly; exit 2 = fired)seiche watch -i 1800      # pull + alert on a loopseiche replay 2019-09-12  # Time Machine in the terminalseiche backtest           # PROOF summaryseiche ml                 # ML Lab: event probability + honest validationseiche analogs            # Tide Tables: nearest historical analogs + forward fanseiche swell              # the funding-stress forward curve, 6 weeks outseiche physics            # the physics board: floor, modes, determinism, tail lawseiche bathymetry         # the basin floor in detail: potential, spectrum, entropy, first passageseiche book               # the Book: today's positions + walk-forward P&L verdictseiche ask "…"            # desk assistant, grounded in the live boardseiche serve              # API + UIseiche mcp                # serve the board to AI agents over MCP (stdio)seiche nbs-intake catalog # four code-owned NBS source identities; no valuesseiche nbs-intake status  # verify the public-only signed China revision head

For AI agents (MCP)

Seiche is also a Model Context Protocol server — any MCP-capable agent (Claude Code, Codex, your own) can read the live board as tools. Where a data feed hands an agent raw macro numbers, Seiche hands it the conclusion: a regime read, forward event odds, historical analogs, and a historical diagnostic whose status, misses, and eligibility flags stay attached. Stdlib-only, no new dependencies.

claude mcp add seiche -- seiche-mcp          # Claude Code, local (stdio)SEICHE_MCP_PUBLIC=1 seiche-mcp               # free surface only

Or, zero-install, over HTTP: the same tools are served at /mcp on the API (https://api.seiche.info/mcp). Add the URL and start calling. Eight tools answer anonymously; see the release scope above. Retired tools in the historical catalog below are unavailable:

claude mcp add --transport http seiche https://api.seiche.info/mcpcurl https://api.seiche.info/api/gauge

The copy-paste quickstart and live tool runner are at seiche.info/developers.

That is the conclusion, the precedent, the honest record, the freshness, granular USD money-market context, unified world-market context and cross-market transmission context, and it stays free. Five analysis tools want a bearer token because they read gated forecasting, replay, positioning, prose, or LLM engines rather than a published contextual conclusion: funding_stress_forecast, replay_asof, positioning_book, desk_brief and ask_desk. institutional_flows answers anonymously but keeps its method_versions back for the same reason.

An authenticated hosted caller also sees five private Agent Room preview tools: agent_room_register_key, agent_room_create, agent_room_append_event, agent_room_list_events, and agent_room_verify. They record client-signed, server-co-signed agent discussion in a tamper-evident room; every record is non-executable and grants no acceptance, order, execution, payment, settlement, or custody authority. The full bearer-authenticated hosted catalog is therefore 24 tools (14 public evidence + five gated analysis + five Agent Room). See the exact security and signing contract.

Nothing fails at call time over this: tools/list returns exactly the tools the caller can run, so an agent never sees a tool it cannot use. Both surfaces are rate-limited per caller and metered per UTC day (anonymous callers per IP).

Full setup, the tool catalogue, client config, metering, tokens, and the pay-per-call option for the five analysis tools: docs/MCP.md.

Want the board in your pocket instead of a client config? The Hermes desk-agent kit turns hermes-agent into a Seiche desk agent on Telegram/Discord/Slack: a scheduled morning brief, regime alerts with anti-noise rules, construction-PIT episode replays, and a PROOF-grounded answer to "can I trust this". Walkthrough: docs/HERMES.md.

Alerts dedupe per state in SQLite, notify via macOS notification and optional webhook (SEICHE_WEBHOOK_URL — Slack/Telegram/ntfy style {"text": ...}). A launchd template lives in ops/com.seiche.watch.plist.

Production deployment

# Existing canonical host: install or refresh the signed release controller# without activating it, then run its gate-only acceptance cycle.bash /home/seiche/app/ops/deploy/install-release-poller.shSEICHE_CONTROL_GATE_ONLY=1 /usr/local/sbin/seiche-release-poll

Production uses the operator-provisioned /home/seiche/app layout documented in ops/deploy/RELEASE-POLLER.md; this repository intentionally has no unattended first-VPS bootstrap. The old /opt installer is retired because its service and state layout never matched production.

GET /api/health never starts or waits for the full board build. It returns the last completed snapshot's health fields with HTTP 200, or an immediate HTTP 503 with status: warming_or_unavailable while the cache is cold. The production background warmer owns snapshot construction; deployment probes only observe whether it has published a result.

Put a TLS reverse proxy in front. The box already serving another site (e.g. Palimpsest) just adds a vhost — nginx:

server {    listen 443 ssl http2;    server_name seiche.example.com;   # certbot --nginx -d seiche.example.com    location / { proxy_pass http://127.0.0.1:8787; proxy_set_header Host $host; }}

Signed releases: the on-host release poller is the sole automatic controller. It accepts only the reviewed SSH-signed main tip, tests that exact SHA in isolation, and hands it to the rollback-owning deploy wrapper. The deploy-hetzner workflow is workflow_dispatch-only break-glass recovery and must not run while the poller is active. The API cache lives under /home/seiche/app/backend/data; canonical market state and backup receipts live under /var/lib/seiche and /var/backups/seiche-market. Follow the poller and market backup runbooks rather than copying one directory as if it were the whole track record. LLM keys for the desk assistant/Navigator and Telegram alert credentials belong in a root-owned production environment file, not the retired ops/deploy/seiche.service template. On the host, create /etc/seiche/operator.env with mode 0600, then attach it to the actual seiche-api.service through a non-secret systemd drop-in:

sudo install -d -o root -g root -m 0755 /etc/seichesudo test -e /etc/seiche/operator.env || \  sudo install -o root -g root -m 0600 /dev/null /etc/seiche/operator.envsudoedit /etc/seiche/operator.envsudo install -d -o root -g root -m 0755 \  /etc/systemd/system/seiche-api.service.dprintf '%s\n' '[Service]' \  'EnvironmentFile=/etc/seiche/operator.env' | \  sudo tee /etc/systemd/system/seiche-api.service.d/operator-env.conf >/dev/nullsudo systemctl daemon-reloadsudo systemctl restart seiche-api.service

Use systemd KEY=value syntax in the environment file for only the required SEICHE_LLM_*, SEICHE_TELEGRAM_*, or webhook settings. Never commit their values. Confirm permissions with stat, then check systemctl status seiche-api.service and the API health route after restart.

Tuning the editorial voice

backend/seiche/config.py quarantines every judgment call: composite weights, regime thresholds, resonance/turn/tell parameters, alert rules, the episode library, contract DV01s. The math never hides an opinion.

Non-goals

The eight-tool public evidence surface needs no account and does not depend on paid upstream data; optional licensed or tenant inputs remain explicitly bounded. Legacy forecast, replay, positioning, prose and LLM tools are unavailable. Seiche does not claim intraday-tick coverage: daily cadence plus operation results is the honest granularity of the public stack. Historical reconstruction uses final/current-vintage inputs and is therefore construction-PIT, not validated-backtest evidence. The engine blocks the historical backtest output unless every required input has an ALFRED/as-published vintage manifest. From v2 onward Seiche accrues a true as-published point-in-time record (/api/pit) and stores immutable observation captures for forward vintage reconstruction. Those forward captures cannot repair vintages that were never retained. Not investment advice.

Connected research

The Seiche research_network tool and /api/v2/research-network endpoint connect Palimpsest's complete source catalog with separately completed funding context and explicit research steps into LiquiLens, Undertow and NarcoScope. Use topic, offset and limit; follow next_offset for remaining datasets. The human desk is https://seiche.info/#RESEARCH. Telegram readers can use /research china, /research regions or /research liquidity.

Catalog rows are references, not permission to redistribute source values or change a score. Source clocks, rights and missingness remain attached. The retrieved catalog hash is a byte identity, not a producer attestation.

Quant research agent integrations

Native framework tools and cited quant pipeline captures connect Seiche funding, LiquiLens bank diagnostics and Undertow market liquidity through compact read-only tables. LangChain/LangGraph, CrewAI, OpenAI Agents and Pydantic AI share one evidence contract and repeat-call revision tokens. Current published history is not an as-published vintage archive. No execution authority or institutional-adoption claim is implied.