Thesis engine for prediction market agents. Scan Kalshi + Polymarket, detect edges, monitor autonomously.

curl -fsSL https://simplefunctions.dev/install.sh | sh

Or with npm directly:

npm install -g @spfunctions/cli
sf setup

sf setup walks you through API key configuration with real-time validation. Get your key at simplefunctions.dev/dashboard/keys.

# No API key needed — try right now
sf scan "recession 2026"
sf schedule
sf explore

# With API key
sf create "Oil stays above $100 through 2026"
sf context <id> --json
sf agent

You express a macro thesis. The engine decomposes it into a causal tree of testable sub-claims, scans Kalshi and Polymarket for contracts where market prices diverge from thesis-implied prices (edges), and monitors everything autonomously every 15 minutes.

Thesis → Causal Tree → Market Scan → Edges
                                       ↓
Heartbeat (15 min): News + Prices + Milestones → Updated Confidence
                                                   ↓
                                       Webhook / Delta API / Feed

Requires sf setup --enable-trading. All orders have a 3-second countdown.

sf agent                  # continue last session
sf agent <id> --new       # fresh session for specific thesis
sf agent --plain          # plain text mode (pipe-friendly)

Natural language interface with 15+ tools. Analyzes edges, suggests trades, monitors positions. Slash commands: /tree, /edges, /pos, /eval, /buy, /sell, /cancel, /switch.

Connect any MCP-compatible client — Claude Code, Cursor, Cline, Roo Code.

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

15 tools: get_context, list_theses, inject_signal, trigger_evaluation, create_thesis, what_if, scan_markets, get_milestones, get_forecast, get_settlements, get_balance, get_orders, get_fills, get_schedule, explore_public.

Your agent only needs three operations:

# 1. Read — get current thesis state
sf context <id> --json

# 2. Write — inject observations
sf signal <id> "breaking: Hormuz blockade confirmed" --type news

# 3. React — trigger analysis when something big happens
sf evaluate <id>

The heartbeat engine handles news scanning, price monitoring, and routine evaluation automatically. For efficient polling, use the delta API:

curl "https://simplefunctions.dev/api/thesis/<id>/changes?since=<ISO timestamp>" \
  -H "Authorization: Bearer sf_live_xxx"
# Nothing changed: {"changed": false} — 50 bytes

Base URL: https://simplefunctions.dev

Auth: Authorization: Bearer sf_live_xxx

• Website
• Documentation
• Agent Guide
• API Keys
• Public Theses

MIT