SimpleFunctions Developer Manual

This page preserves the previous one-page documentation surface so no CLI, API, MCP, runtime, or concept coverage is lost during the Mintlify migration. Prefer the focused pages for new integrations.

Overview

SimpleFunctions is prediction market data, indicators, and autonomous trading infrastructure. Structured, decision-ready data from Kalshi, Polymarket, X/Twitter, and traditional markets — monitored 24/7. CLI, MCP server, REST API, and interactive agent with cognitive guardrails.

Quick Start

0. No install needed — try it now

curl https://simplefunctions.dev/api            # live data in your terminal
curl https://simplefunctions.dev/api/changes     # recent market changes
curl https://simplefunctions.dev/api/tools       # full capability manifest

1. Install the CLI

npm install -g @spfunctions/cli
sf scan "gold"           # search Kalshi + Polymarket (no auth)
sf query "iran oil"      # LLM-enhanced search — markets + X + answer
sf watch "gold"          # server-side change detection feed
sf agent                 # interactive agent (all tools + skills)

All commands work without an API key. Explorer mode gives you full market access.

2. Explore — ask questions (no thesis needed)

sf agent                # opens in explorer mode — all tools, no setup

Ask anything: “what’s happening with Iran?”, “show me gold contracts”, “any new markets today?”. The agent has full access to scan, query, watch, and explore — no thesis required. When you form a view, say it: “I think oil stays above $100” — the agent creates a thesis automatically.

3. Create a thesis (optional — makes context richer)

sf setup                # API key + optional Kalshi/Polymarket credentials (2 min)
sf thesis create 'US-Iran war will not end quickly. Oil stays above $100 through Q2 2026.'

Pass a testable claim — a statement that can be true or false at a future date. Use single quotes (not double) so $100 isn’t swallowed by your shell. Takes ~60s; system builds a causal tree, scans Kalshi + Polymarket for related contracts, identifies edges, and starts 24/7 monitoring.

4. Focused context

sf thesis context <id>  # thesis-specific: causal tree, edges, evaluation, track record
sf edges                # top mispriced contracts across all theses
sf dashboard        # interactive Bloomberg-style terminal

That’s it. The system runs 24/7. See the Agent Guide for full integration reference.

How It Works

Thesis → Causal Tree

Your plain-text thesis is decomposed into a tree of verifiable assumptions. Each node has a probability (0-1) and importance weight. The overall confidence is the weighted product.

Thesis: "Oil stays above $100 for 6 months"
├── n1: OPEC maintains production cuts (0.70, weight 0.30)
│   ├── n1.1: Saudi compliance remains high (0.80)
│   └── n1.2: Russia doesn't break quota (0.60)
├── n2: Demand stays strong (0.65, weight 0.25)
├── n3: Geopolitical risk premium persists (0.75, weight 0.25)
└── n4: No US SPR release (0.80, weight 0.20)
Confidence: 72%

Edge Detection

The system maps causal nodes to prediction market contracts and compares:

Market price: what Kalshi/Polymarket traders think (e.g. 34 cents)
Thesis price: what your causal model implies (e.g. 55 cents)
Edge: the difference (21 cents)
Executable edge: edge minus half the spread (real edge after crossing)

24/7 Monitoring

Every 15 minutes, the heartbeat engine:

Scans news (3 queries including one adversarial — never filters out contradictory evidence)
Refreshes prices from Kalshi API + Polymarket CLOB
Enriches orderbooks (bid/ask depth for edges > 5 cents)
Evaluates signals against causal tree (checks kill conditions first)
Computes track record (hit rate: % of edges that moved toward thesis)
Discovers new edges (daily) and augments the causal tree with new nodes (weekly)

Integration Options

MCP Server

One-line setup for Claude Code, Cursor, Cline, or Roo Code:

claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp

54 tools available. Public tools work without auth. See the Agent Guide for the full list.

CLI

Every command supports --json. Key commands support --share for shareable URLs. Explore (no auth):

Command	What it does
`sf scan "gold"`	Search Kalshi + Polymarket
`sf scan "btc" --expires-before 24h --price-min 3 --price-max 9`	Scan with server-side filters (expiry / price / volume)
`sf overround "senate majority leader"`	Sum YES asks across multi-leg event; flag arb
`sf newmarkets --hours 24`	Newly listed markets (catch fresh contracts before pro MM)
`sf query "iran oil"`	LLM-enhanced search (markets + X + answer)
`sf watch "gold"`	Price change detection feed
`sf watch "gold" orderbook`	Live bid/ask/spread/depth tracking
`sf watch "gold" flow`	Momentum detection, volume spikes
`sf watch "gold" cross-venue`	Kalshi vs Polymarket spread tracking
`sf agent`	Interactive agent (all tools + skills, explorer mode)
`sf context`	Global market snapshot
`sf markets`	Traditional markets (SPY, VIX, GLD, TLT, USO)
`sf explore`	Browse public theses
`sf status`	Health check: API, auth, Kalshi, Polymarket, theses
`sf dashboard`	Interactive Bloomberg-style terminal

Thesis + analysis:

Command	What it does
`sf thesis create "thesis"`	Create thesis with causal tree + edges
`sf thesis context <id>`	Thesis-specific snapshot
`sf edges`	Top mispriced contracts across all theses
`sf whatif <id> --set "n1=0.1"`	Scenario analysis (zero LLM cost)
`sf thesis signal <id> "text"`	Inject observation
`sf thesis evaluate <id>`	Force deep evaluation
`sf feed`	Evaluation history
`sf contagion`	Markets that should have moved but didn’t
`sf cross-venue`	Kalshi vs Polymarket price comparison
`sf calibration`	Brier scores + calibration metrics
`sf regime [ticker]`	Market regime analysis (—history)

Knowledge + community:

Command	What it does
`sf concepts [slug]`	Indicator definitions: IY, CRI, LAS, EE, OR…
`sf technicals [slug]`	Technical analysis methodology
`sf opinions [slug]`	Published market commentary
`sf blog [slug]`	Blog articles + research notes
`sf forum channels`	Forum channels + subscription state
`sf forum inbox`	Unread messages
`sf forum post <ch> "msg"`	Post to a channel
`sf watchlist`	Saved markets (—add/—remove)
`sf calendar`	Structured event calendar
`sf yield-curve [event]`	Implied yield curves

Intents + Execution:

Command	What it does
`sf intent buy <ticker> <qty> --price <cents>`	Create buy intent with trigger
`sf intent sell <ticker> <qty> --trigger below:40`	Sell intent with price trigger
`sf intent list`	Active intents (`--all` for history)
`sf intent status <id>`	Detailed status with fills
`sf intent cancel <id>`	Cancel an intent
`sf runtime start [--daemon] [--smart]`	Start execution daemon (—smart for LLM intelligence)
`sf runtime stop`	Stop daemon
`sf runtime status`	Runtime state + active intents

Portfolio + trading:

Command	What it does
`sf positions`	Kalshi + Polymarket positions with P&L
`sf balance`	Account balance
`sf orders`	Current resting orders
`sf fills`	Recent trade fills
`sf settlements`	Settled contracts with P&L
`sf performance`	P&L over time with sparklines
`sf buy <ticker> <qty> --price <cents>`	Buy contracts (direct, no intent)
`sf sell <ticker> <qty> --price <cents>`	Sell contracts (direct, no intent)
`sf cancel [orderId]`	Cancel orders (`--all` for all)

X / Twitter:

Command	What it does
`sf x "iran oil"`	Search X discussions — posts, sentiment, themes
`sf x-volume "tariffs"`	Discussion volume trend with histogram
`sf x-news "tariffs"`	X news stories with ticker mentions
`sf x-account @federalreserve`	Recent posts from a specific account

Flags: --json on all commands · --share on scan, query, context, edges, markets, explore Full reference in the Agent Guide.

Agent Contract

The CLI is designed for agent consumption. Behaviors agents can rely on:

Behavior	Detail
Structured errors	When piped (non-TTY), errors emit JSON on stderr: `{{"error": "...", "code": "..."}}`
Exit codes	`0` success, `127` unknown command
NO_COLOR	Set `NO_COLOR=1` to strip all ANSI escape codes
FORCE_COLOR	Set `FORCE_COLOR=1` to force ANSI even when piped
SF_AUTO_CONFIRM	Set `SF_AUTO_CONFIRM=1` to skip interactive confirmations (required for non-TTY order execution)
—json	Every command supports `--json` for structured output
LLM fallback	Unrecognized commands get LLM-powered suggestions (e.g., `sf thesis list` → suggests `sf list`)
—quiet	Suppress non-essential output (progress, banners)
sf describe —all —json	Machine-readable catalog of every tool — args, options, auth, side effects

Agent Harness

Tools for testing, backtesting, and constraining agent behavior.

Command	What it does
`sf agent --record-trace /tmp/trace.ndjson`	Record every tool call + LLM message to NDJSON file
`sf agent --replay-trace /tmp/trace.ndjson`	Replay: tool calls return recorded output (deterministic)
`sf agent --budget-usd 5`	Hard ceiling on total spend (LLM + side effects)
`sf agent --allow read,query`	Whitelist: only these tool categories allowed
`sf agent --deny order,position.write`	Blacklist: these tools blocked
`sf agent --headless`	Tool-only NDJSON mode: expose 95 tools via stdin/stdout, no LLM. For external LLM integration.

Event Subscription

Long-lived structured event streams for reactive agents. Replaces polling.

Command	What it does
`sf subscribe list`	Active subscriptions
`sf subscribe cancel <id>`	Cancel a subscription

Event types: market (price_cross, volume_spike, spread_widen, regime_flip), thesis (confidence_drop, confidence_rise, new_signal), position (drawdown, fill, close), portfolio (drawdown, tick_complete, halt), system (runtime.started, runtime.stopped).

Cloud Runtime

Run your agent runtime in the cloud. Always-on, no local laptop required. BYOK: your keys, encrypted client-side.

Command	What it does
`sf setup --cloud`	Configure cloud runtime: encrypt + upload your API keys
`sf runtime start --remote`	Start your cloud container (Fly.io, ~3s cold start)
`sf runtime stop --remote`	Stop cloud container (scale to zero)
`sf --remote agent`	Run agent command via cloud runtime

Key encryption: Your API keys are encrypted client-side (Argon2id key derivation) before upload. SimpleFunctions never sees plaintext credentials.

REST API

No auth needed:

Endpoint	What it does
`GET /api/agent/world`	Real-time world model for agents (~800 tokens markdown). Edges, movers, anchors, divergences.
`GET /api/agent/world/delta?since=1h`	Incremental world state update — only what changed (~30-50 tokens).
`GET /api/agent/inspect/:ticker`	Complete ticker dossier: price, regime, indicators, suggestion, contagion, 7d trend.
`GET /api/public/query?q=...`	LLM-enhanced search (Kalshi + Polymarket + X + traditional)
`GET /api/public/search?q=...`	Raw search index + market snippets
`GET /api/public/scan?q=...`	Cross-venue market search with relevance ranking
`GET /api/public/topic/:slug`	Topic-focused market surface with grouped context
`GET /api/public/answer/:slug`	Full natural-language answer object
`GET /api/public/screen?sort=iy&limit=10`	Indicator screener: filter 50K+ markets by IY, EE, OR, LAS, CRI, RV, VR, IAR, Adj IY, Residual VR, τ
`POST /api/public/discuss`	Post market discussion/feedback
`GET /api/public/ideas`	Trade ideas: S&T-style pitches with conviction + catalyst. `?q=topic` for on-demand.
`GET /api/public/contagion?window=6h`	Cross-market contagion: which connected markets should move but haven’t?
`GET /api/public/query-gov?q=...`	Legislative intelligence: bills, nominations, members, CRS reports + prediction market cross-reference
`GET /api/public/query-econ?q=...`	Official economic data search: FRED-backed time series, latest values, changes, tags. `includeMarkets=true` adds related prediction markets.
`GET /api/public/x/search?q=...`	Search X discussions — posts, sentiment, themes
`GET /api/public/x/volume?q=...`	Discussion volume trend — timeseries, velocity
`GET /api/public/fred?series=...`	Raw FRED anchor observations
`GET /api/public/databento`	Databento-backed traditional market anchors (SPY, VIX, GLD…)
`GET /api/public/legislation`	Bills listing with market cross-reference. `?q=`, `?hasMarket=true`
`GET /api/public/legislation/:billId`	Bill detail: status, actions, CRS summary, sponsors + linked markets + state bills
`GET /api/public/congress/members`	Current members of Congress. `?state=`, `?party=`, `?chamber=`
`GET /api/public/congress/member/:id`	Member detail: bio, sponsored bills, election markets
`GET /api/public/index`	SF Prediction Market Index v2: disagreement, geo_risk, breadth, activity
`GET /api/public/index/history?days=7`	Historical index data (1-30 days)
`GET /api/public/newmarkets`	Recently listed markets across venues
`GET /api/public/yield-curves`	Calendar yield curves — term structure across event families
`GET /api/public/calibration`	Brier score calibration metrics across 60K+ resolved markets
`GET /api/public/highlights`	Today’s market headlines and highlights
`GET /api/public/market/:ticker`	Single market detail: price, spread, volume, orderbook (`?depth=true`)
`GET /api/public/regime/scan`	Markets by adverse selection regime (maker/taker/neutral)
`GET /api/public/diff?tickers=X,Y&window=24h`	Market derivatives: price/volume/spread/depth deltas + divergence signals
`GET /api/public/briefing?topic=iran`	Daily topic briefing: what changed, why it matters, outlook
`GET /api/changes?since=&q=&type=`	Server-side market change detection (every 15 min)
`GET /api/tools`	Full capability manifest for agent auto-discovery
`GET /api/public/trad-markets`	Traditional market snapshot (SPY, VIX, GLD, TLT, USO via Databento)
`GET /api/public/theses`	List public theses
`GET /api/public/thesis/:slug`	Public thesis detail with causal tree + edges
`GET /api/public/opinions`	Opinion articles (`/:slug` for detail)
`GET /api/public/technicals`	Technical analysis (`/:slug` for detail)
`GET /api/public/glossary`	Glossary entries (`/:slug` for detail)
`GET /api/public/skills`	Agent cognitive skills and workflows
`POST /api/monitor-the-situation/enrich`	Paste text + topics → prediction market divergence analysis. No auth needed.

Auth required (Authorization: Bearer sf_live_xxx):

Endpoint	What it does
`POST /api/monitor-the-situation`	Universal web intelligence: scrape any URL (Firecrawl), cross-reference with markets. Requires auth.
`GET /api/edges`	Aggregated edges across all theses (auth adds private theses)

X / Twitter (no auth):

Endpoint	What it does
`GET /api/x/search?q=...`	Search X discussions — posts, sentiment, themes
`GET /api/x/volume?q=...`	Discussion volume trend — timeseries, velocity
`GET /api/x/news?q=...`	X news stories — headlines, summaries
`GET /api/x/account?username=...`	Recent posts from a specific account

Auth required (Authorization: Bearer sf_live_xxx):

Endpoint	What it does
`POST /api/thesis/create[?sync=true]`	Create thesis (sync waits for formation)
`GET /api/thesis/:id/context`	Thesis-specific snapshot
`GET /api/thesis/:id/changes?since=ISO`	Lightweight delta check (~50 bytes)
`POST /api/thesis/:id/signal`	Inject signal
`POST /api/thesis/:id/evaluate`	Force evaluation (up to 2 min)
`POST /api/thesis/:id/augment`	Tree augmentation (`?dryRun=true` to preview)
`POST /api/thesis/:id/strategies`	Create trading strategy
`GET /api/thesis/:id/strategies`	List strategies
`POST /api/intents`	Create execution intent with trigger conditions
`GET /api/intents`	List intents (`?active=true` for active only)
`DELETE /api/intents/:id`	Cancel an intent
`GET /api/thesis/:id/evaluations`	Daily-aggregated evaluation history (confidence trajectory)
`POST /api/thesis/:id/nodes/update`	Direct causal tree node mutation (zero LLM cost)
`GET /api/feed?hours=24`	Evaluation history
`POST /api/skill`	Create a custom skill
`GET /api/skill`	List user skills + built-in skills
`PUT /api/skill/:id`	Update a skill
`DELETE /api/skill/:id`	Delete a skill
`POST /api/skill/:id/publish`	Publish skill (set slug)
`POST /api/skill/:id/fork`	Fork a public skill into your collection
`POST /api/thesis/:id/fork`	Fork a public thesis (accepts ID or slug, copies thesis + causal tree)

Full endpoint reference in the Agent Guide.

Real-Time Data API

Sub-second WebSocket and REST data feed at data.simplefunctions.dev/v1/ — a separate surface from the agent / public APIs above. Built for trading agents, dashboards, quants, and risk engines that need tick-level state across Kalshi and Polymarket. REST (no auth required at the edge — rate-limited):

Endpoint	What it does	Cache-Control
`GET /v1/markets`	All tracked markets with precomputed heat score	`public, max-age=3, swr=10`
`GET /v1/markets/featured?n=20`	Top-N by heat — what is moving right now	`public, max-age=3, swr=10`
`GET /v1/markets/{ticker}`	Single market snapshot with full metadata	`public, max-age=2, swr=5`
`GET /v1/orderbook/{ticker}`	Live depth — bids, asks, timestamp	`public, max-age=1`
`GET /v1/candles/{ticker}?tf=1h&limit=500`	OHLC candles for any timeframe	`public, max-age=15` (1d) / `5` (others)
`GET /v1/trades/{ticker}?limit=50`	Recent trade prints, newest first	`public, max-age=1`
`GET /v1/heartbeat`	System status — markets tracked, ws clients, uptime	`public, max-age=10`

WebSocket (wss://data.simplefunctions.dev/v1/ws, JSON envelopes):

Topic	Frame shape	Cadence
`ticker:{ticker}`	`{type, ticker, last, bid, ask, volume24h, venue}`	On change
`orderbook:{ticker}`	`{type, ticker, bids, asks, ts}`	Throttled 1 Hz
`trade:{ticker}`	`{type, ticker, price, size, side, ts}`	On every print
`candle:{ticker}:{tf}`	`{type, ticker, timeframe, candle}`	On bar update
`featured`	`{type, markets, generated_at}`	60 s tick + rank-change

Heat score (0-100 per market): 0.40 × log-vol + 0.35 × spread-tightness + 0.15 × close-to-coin-flip + 0.10 × recent-volatility. Use to filter the long tail — only subscribe to markets above a heat threshold.

curl https://data.simplefunctions.dev/v1/heartbeat
curl https://data.simplefunctions.dev/v1/markets/featured?n=20

const ws = new WebSocket('wss://data.simplefunctions.dev/v1/ws')
ws.addEventListener('open', () => ws.send(JSON.stringify({
  action: 'subscribe',
  topics: ['featured', 'ticker:KXFEDDECISION-26DEC-CUT100'],
})))
ws.addEventListener('message', e => console.log(JSON.parse(e.data)))

Full integration page: Real-Time Data API. Agent-specific patterns: Build Agents.

Agent Skills

Cognitive guardrails for prediction market agents. Skills are prompts that make agents disciplined.

Skill	Trigger	What it does
Discipline	`/discipline`	Full position review: entry hypothesis, falsification, from-zero test
Pre-check	`/precheck`	Pre-trade adversarial check — argue against the trade first
Morning	`/morning`	Structured daily briefing: kill conditions, positions, action items

Skills are markdown files. Create your own in ~/.sf/skills/. See the Agent Guide for agent-facing usage patterns.

Agent Runtime

Multi-daemon architecture. Your agent orchestrates background daemons that monitor, reason, and execute autonomously. Smart mode (--smart) adds LLM intelligence: soft condition gating, periodic scans, wake conditions.

sf runtime start --smart --daemon   # execution daemon with LLM intelligence
sf telegram --daemon                # push notifications + mobile agent
sf agent                            # interactive agent (reads daemon alerts)

See the Agent Runtime guide for architecture, config, and operational patterns.

Telegram Bot

sf telegram --token YOUR_BOTFATHER_TOKEN --daemon

Runs locally. Slash commands + natural language. Auto-pushes confidence alerts.

Webhook

Add webhookUrl when creating a thesis. The engine POSTs on confidence changes >= 5%.

Authentication

Get an API key from the Dashboard.

curl -H "Authorization: Bearer sf_live_xxx" https://simplefunctions.dev/api/thesis

For CLI: sf setup stores the key in ~/.sf/config.json. Config priority: env vars > config file > defaults.

Key Concepts

Signals

Events that feed into evaluations. Five types:

Type	Source	Description
`news`	Heartbeat or manual	News articles, data releases
`price_move`	Heartbeat	Market price change >= 3 cents
`user_note`	Manual	Your analysis or observations
`external`	Manual	Signals from other systems
`upcoming_event`	Heartbeat	Kalshi milestone matching edges

Edge Types

The system classifies each edge by WHY the mispricing exists:

consensus_gap — market and thesis disagree on fundamental probability
attention_gap — market hasn’t reacted to recent information yet
timing_gap — market prices short-term risk, thesis prices long-term outcome
risk_premium — market embeds fear/greed premium that thesis doesn’t

Track Record

Feedback loop that computes how well past edges predicted market movement:

Hit rate: % of edges where market moved toward the thesis-implied price
Average movement: mean price change in cents since edge detection
Track record is injected into evaluation prompts so the system learns from its accuracy

Tree Augmentation

The causal tree evolves over time:

Each evaluation can suggest new causal factors (suggestedNodes)
Weekly (Monday 6 UTC), the augment agent reviews suggestions
LLM decides which to accept (must be genuinely new, not duplicates)
Accepted nodes are appended (never removed — append-only tree)
Importance weights are rebalanced among siblings

Kill Conditions

Before every evaluation, the system asks: “Does any event fundamentally break a core assumption of this thesis?” If yes, it flags the threat prominently before any other analysis.

Pricing

Free during beta. Pay by token after 15M tokens consumed.

Full Reference

See the Agent Guide for the complete machine-readable reference — all 54 MCP tools, CLI commands, REST endpoints, context response shape, and integration rules. The guide page has a “Copy everything” button for pasting into agent prompts.

Help

Archive

Complete Reference

Overview

Quick Start

0. No install needed — try it now

1. Install the CLI

2. Explore — ask questions (no thesis needed)

3. Create a thesis (optional — makes context richer)

4. Focused context

How It Works

Thesis → Causal Tree

Edge Detection

24/7 Monitoring

Integration Options

MCP Server

CLI

Agent Contract

Agent Harness

Event Subscription

Cloud Runtime

REST API

Real-Time Data API

Agent Skills

Agent Runtime

Telegram Bot

Webhook

Authentication

Key Concepts

Signals

Edge Types

Track Record

Tree Augmentation

Kill Conditions

Pricing

Full Reference

Help

Archive

Documentation Index

​Overview

​Quick Start

​0. No install needed — try it now

​1. Install the CLI

​2. Explore — ask questions (no thesis needed)

​3. Create a thesis (optional — makes context richer)

​4. Focused context

​How It Works

​Thesis → Causal Tree

​Edge Detection

​24/7 Monitoring

​Integration Options

​MCP Server

​CLI

​Agent Contract

​Agent Harness

​Event Subscription

​Cloud Runtime

​REST API

​Real-Time Data API

​Agent Skills

​Agent Runtime

​Telegram Bot

​Webhook

​Authentication

​Key Concepts

​Signals

​Edge Types

​Track Record

​Tree Augmentation

​Kill Conditions

​Pricing

​Full Reference

Overview

Quick Start

0. No install needed — try it now

1. Install the CLI

2. Explore — ask questions (no thesis needed)

3. Create a thesis (optional — makes context richer)

4. Focused context

How It Works

Thesis → Causal Tree

Edge Detection

24/7 Monitoring

Integration Options

MCP Server

CLI

Agent Contract

Agent Harness

Event Subscription

Cloud Runtime

REST API

Real-Time Data API

Agent Skills

Agent Runtime

Telegram Bot

Webhook

Authentication

Key Concepts

Signals

Edge Types

Track Record

Tree Augmentation

Kill Conditions

Pricing

Full Reference