Polytrader vs
SimpleFunctions.

Both products connect to Polymarket data. The structural difference is scope and surface: Polytrader wraps Polymarket with social-sentiment signals and automated strategies in a product-oriented interface. SimpleFunctions normalises Kalshi and Polymarket on the same API surface, adds computed indicators (implied yield, cliff risk, liquidity score), a causal thesis system, an autonomous Portfolio Autopilot, and a 56-tool MCP server. If your workflow is Polymarket-only with community signals, Polytrader is designed for that; if you need cross-venue agent infrastructure, SF is the match.

POST /api/thesis/create takes any natural-language claim — 'The Fed cuts rates by 50bps before December' — and decomposes it into a causal tree of testable sub-claims. Each sub-claim is priced against live Kalshi and Polymarket contracts. An evaluation heartbeat then runs automatically: news scan, price refresh, milestone check, LLM evaluation, confidence update. New evidence is injectable via /api/thesis/{id}/signal, and public theses are forkable. Polytrader offers AI-driven analysis framed around Polymarket market categories; a structured multi-venue causal decomposition with auto-evaluation is not documented.

No. SF does not natively source or process social or community sentiment signals. Polytrader's social-sentiment tracking is a genuine product differentiator for traders who weight community data in their Polymarket workflow. SF's thesis system accepts injected signals via /api/thesis/{id}/signal, so you can feed in external sentiment scores, but SF does not collect that data itself. If community sentiment is a primary signal for your strategy, Polytrader is the more purpose-built product.

SF's Portfolio Autopilot is a 1M-context LLM trading agent that draws from 13 data sources and gates every execution through a 7-step risk cascade — kill switch, position limits, drawdown gate, regime check, and more — before placing a trade on Kalshi or Polymarket. Polytrader also offers automated strategies, but their architecture and risk controls are not documented in public materials. The key structural difference is that SF's autopilot spans both venues and integrates with the thesis system; Polytrader's automation is built around Polymarket with sentiment signals as a native input.

Yes. SF normalises contracts from both Kalshi and Polymarket on the same API surface, with 48K+ active contracts indexed. Cross-venue matched pairs are available at /api/public/cross-venue/pairs?preset=arb for arbitrage scanning. Polytrader's documented scope is Polymarket; Kalshi coverage is not described in their public materials.

SimpleFunctions ships a 56-tool MCP server at https://simplefunctions.dev/api/mcp/mcp. Add it to Claude Code with one line: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. Tools cover market data, orderbook depth, thesis management, Portfolio Autopilot, computed indicators, and cross-venue scanning. Any MCP-compatible client — Claude Code, Cursor, custom agents — can consume these tools without additional integration work. Polytrader does not document an MCP server in public materials.

SF publishes live Brier scores at /api/calibration, broken down by venue, category, and price bucket — Kalshi 0.20, Polymarket 0.12 on T-24h prices, computed over the past 90 days. You can verify these with a single curl call; the data is computed live, not cached from a marketing page. This lets any user independently audit SF's calibration baseline. Polytrader does not publish equivalent calibration metrics in its public documentation.