Dome vs
SimpleFunctions.

Dome was acquired by Polymarket on 2026-02-19 and its standalone API service is in scheduled wind-down as the team integrates into Polymarket's own infrastructure. Developers who built on Dome are evaluating migration paths; SimpleFunctions is a frequently cited alternative because it covers the same Kalshi and Polymarket venues with a maintained, agent-first API and no acquisition risk. Common search queries following the announcement include 'dome alternative' and 'polymarket api after dome'.

Yes. SF's public REST API covers the same Kalshi and Polymarket venues that Dome normalised. Most read-path endpoints require no authentication, so replacing the data layer is low-friction. The SF CLI (npm i -g @spfunctions/cli) and 56-tool MCP server give you additional surfaces beyond what Dome offered. Migration involves pointing market-fetch calls at /api/public/markets and updating field names to SF's schema — see the code samples on this page for a direct comparison.

You POST a sentence to /api/thesis/create. SF decomposes it into a causal tree of testable sub-claims, propagates probability estimates down the tree, and scans Kalshi and Polymarket for contracts that map to each node. An evaluation heartbeat then runs on a schedule: news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject external signals at any point via /api/thesis/{id}/signal. Public theses are forkable by other users. No current prediction market data product offers an equivalent.

Yes. Add it in one line: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. This gives any MCP-compatible client — Claude Code, Cursor, or a custom agent — access to 56 tools covering market search, orderbook depth, thesis creation, trade ideas, world snapshot, and calibration data. Dome did not publish an MCP server. The SF MCP server requires no API key for read-path tools.

Portfolio Autopilot is SF's autonomous trading agent. It runs a 1M-context LLM over 13 data sources — including calibration scores, regime labels, and cross-venue pricing — and gates every potential trade through a 7-layer risk cascade: kill switch, position limits, drawdown gate, regime check, and more. Dome's product was scoped to data delivery, not autonomous execution or risk management. Autopilot is the SF capability furthest from anything Dome offered.

SF pre-computes six indicators across 48K+ active contracts: IY (implied yield), CRI (cliff risk index), LAS (liquidity availability score), EE (event overround), τ-days (time to settlement), and a regime label classifying the adverse-selection environment. These are available at /screen and via the API — no client-side computation needed. Dome delivered raw prices and volumes; computed signals were not part of its offering, so users had to derive them independently.

SF's /api/calibration endpoint returns live Brier scores by venue, category, and price bucket, computed from SF's own predictions against resolved outcomes in the past 90 days. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price. This is a public, self-auditing endpoint — you can verify it with a single curl call. Dome did not publish accuracy or calibration metrics, and most prediction market data providers do not audit their own forecasting quality publicly.