Alternative · Cross-venue terminal
Prediction Hunt vs
SimpleFunctions.
Same cross-venue foundation — Kalshi, Polymarket, and arbitrage detection. Prediction Hunt is a human-readable dashboard for monitoring spreads and smart-matched pairs across exchanges, refreshed every five minutes. SimpleFunctions ships the agent layer above it: causal-tree thesis system, autonomous trading, calibrated world model, computed indicators across 48K+ contracts, and a 56-tool MCP server that plugs into any agent runtime.
Verified 2026-04 · public sources only · live SF data from /calibration
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
You are building agents, autonomous trading systems, or research pipelines that need more than a refreshed comparison table — calibrated probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation cycles, regime classification across the full 48K-contract universe, computed indicators (implied yield, cliff risk, liquidity availability score), and a 56-tool MCP server that drops into Claude Code or Cursor in one line.
Choose Prediction Hunt if
You want a fast, human-readable dashboard for scanning cross-venue spreads across Kalshi, Polymarket, and PredictIt. Prediction Hunt's product is built specifically for that workflow, and its PredictIt coverage spans a venue that SF does not currently index.
Same Kalshi + Polymarket coverage, plus PredictIt on Prediction Hunt's side. Prediction Hunt is a comparison dashboard; SimpleFunctions ships the agent layer above it.
At a glance
Three things that
actually differ.
Everything Prediction Hunt gives you — cross-venue normalised prices, arbitrage pair detection, and smart matching across exchanges — SimpleFunctions also gives you, on the same Kalshi and Polymarket feeds.
On top of that, SF ships a causal-tree thesis system, Portfolio Autopilot (1M-context LLM, 7-gate risk cascade), and 56 MCP tools that no current PM comparison dashboard exposes.
SF also publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Prediction Hunt does not publish calibration or accuracy data.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket, 48K+ active contracts normalised and indexed.
Prediction HuntKalshi, Polymarket, and PredictIt — three-exchange coverage including PredictIt, which SF does not currently index.
SimpleFunctionsNormalised prices and smart-matched pairs available at /api/public/cross-venue/pairs, updated continuously.
Prediction HuntCross-exchange price comparison with a five-minute data refresh cadence.
SimpleFunctionsLive arbitrage pairs at /api/public/cross-venue/pairs?preset=arb with computed spread per pair.
Prediction HuntSmart matching and spread detection across Kalshi, Polymarket, and PredictIt.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimate.
Prediction HuntNot documented in publicly available materials.
SimpleFunctionsIY (implied yield), CRI (cliff risk index), LAS (liquidity availability score), EE (event overround), τ-days, and regime label pre-computed across 48K+ contracts at /screen.
Prediction HuntRaw price and spread comparison; no documented derived or computed metrics.
SimpleFunctionsLive Brier scores at /api/calibration segmented by venue, category, and price bucket — publicly verifiable with curl.
Prediction HuntNot published.
SimpleFunctionsPOST /api/thesis/create decomposes any natural-language thesis into a causal tree of sub-claims, links nodes to tradeable contracts, and runs a news-scan + LLM evaluation heartbeat automatically.
Prediction HuntNot in scope — product focus is cross-venue price comparison, not thesis modelling.
SimpleFunctionsPortfolio Autopilot uses a 1M-context LLM, 13 data sources, and a 7-gate risk cascade (kill switch, position limits, drawdown gate, regime check) before execution.
Prediction HuntNot in scope — Prediction Hunt is a comparison dashboard with no execution layer.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, and any MCP client.
Prediction HuntNo MCP server published.
SimpleFunctionsPublic REST, MCP, and CLI reads require no authentication; pay-per-token only on thesis and intent execution, free up to 15M tokens.
Prediction HuntNot publicly documented at time of verification.
Methodology
Verified 2026-04 from public sources only — Prediction Hunt's documentation, public website, and publicly observable behaviour. We never claim non-public information about Prediction Hunt's internals. SimpleFunctions claims on this page are computed live from /api/calibration, /api/public/cross-venue/pairs, and /api/public/markets — you can re-verify them yourself with curl.
Use cases
Same data, different
best fit per scenario.
Scenario 01
Building an AI agent that continuously monitors prediction market opportunities and takes positions autonomously.
SimpleFunctions · best fit
SF's 56-tool MCP server gives the agent structured access to prices, orderbook depth, trade ideas, and cross-venue pairs. Portfolio Autopilot handles execution through a 7-gate risk cascade, keeping a human-in-the-loop kill switch available at all times.
Prediction Hunt
Prediction Hunt has no agent interface or execution layer. It is a human dashboard refreshed every five minutes, not a programmatic API surface.
Scenario 02
Quickly scanning for live arbitrage spreads across Kalshi, Polymarket, and PredictIt in a browser tab.
SimpleFunctions
SF covers Kalshi and Polymarket cross-venue pairs at /api/public/cross-venue/pairs but does not currently index PredictIt markets, leaving a gap in three-exchange coverage.
Prediction Hunt · best fit
Prediction Hunt is built exactly for this workflow. Its smart matching covers all three exchanges and the five-minute refresh is tuned for a human monitoring session rather than programmatic polling.
Scenario 03
Decomposing a macroeconomic thesis into testable sub-claims and tracking which contracts are mispriced relative to the causal model.
SimpleFunctions · best fit
POST /api/thesis/create accepts a natural-language sentence, decomposes it into a causal tree, links each node to live Kalshi and Polymarket contracts, and runs an auto-evaluation heartbeat (news scan, price refresh, LLM confidence update) on a schedule.
Prediction Hunt
Prediction Hunt surfaces price spreads between contracts but has no thesis decomposition or causal modelling layer.
Scenario 04
Querying live prediction market data from within a Claude Code or Cursor session while writing research code.
SimpleFunctions · best fit
One command — claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp — exposes 56 tools covering prices, orderbook, arbitrage pairs, trade ideas, thesis management, and calibration scores directly inside the IDE.
Prediction Hunt
Prediction Hunt has no published MCP server or IDE integration.
Live data
The SimpleFunctions claims on this page are not marketing copy. Brier scores, market counts, and cross-venue pair counts are computed live from /calibration, /screen, and /api/public/cross-venue/pairs. All public, all free, all CC-BY-4.0.
FAQ
What is SimpleFunctions' causal thesis system, and how is it different from arbitrage detection?+
SimpleFunctions' thesis system takes a natural-language claim and automatically decomposes it into a causal tree of testable sub-claims. Each node is linked to tradeable contracts on Kalshi and Polymarket, and an evaluation heartbeat runs news scans, price refreshes, milestone checks, and LLM evaluations on a schedule. Prediction Hunt detects price spreads between existing contracts. The thesis system is a higher-order layer: it reasons about what drives probability, not just where prices diverge across exchanges.
Does SimpleFunctions cover PredictIt like Prediction Hunt does?+
At time of writing, SimpleFunctions' normalised contract universe covers Kalshi and Polymarket. Prediction Hunt additionally covers PredictIt, which makes it the better choice if PredictIt positions are part of your workflow. SF exposes cross-venue pairs at /api/public/cross-venue/pairs and computed indicators across the Kalshi and Polymarket universe, but does not currently index PredictIt markets.
How does SimpleFunctions' Portfolio Autopilot work?+
Portfolio Autopilot is SF's autonomous trading layer. It feeds a 1M-context LLM with 13 data sources — price feeds, news scans, thesis signals, calibration history — and passes every candidate trade through a 7-gate risk cascade before execution. Gates include a kill switch, position limits, drawdown gate, and regime check. Prediction Hunt has no execution layer; it surfaces comparison data for human decision-making. Autopilot is designed for automated pipelines, not a human checking a dashboard.
How do I add SimpleFunctions to Claude Code or Cursor via MCP?+
Run claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp in any terminal with Claude Code installed. No API key is required for read-only tools. The server exposes 56 tools covering price queries, thesis management, cross-venue pairs, trade ideas, orderbook depth, calibration scores, and the world-state snapshot. Prediction Hunt has no published MCP interface. Once added, you can prompt the agent to find arbitrage opportunities, evaluate a thesis, or pull live contract prices without leaving the editor.
What computed indicators does SimpleFunctions provide that Prediction Hunt does not?+
Across 48K+ active contracts SF pre-computes: IY (implied yield — annualised return on a binary position), CRI (cliff risk index — probability of sharp late movement), LAS (liquidity availability score), EE (event overround — excess probability), and τ-days (time to settlement). Contracts are also regime-labelled for adverse-selection classification. These are available pre-computed at /screen. Prediction Hunt surfaces raw prices and spreads; derived signals are not documented in its public materials.
How can I verify SimpleFunctions' accuracy claims?+
GET /api/calibration returns SF's own Brier scores segmented by venue, category, and price bucket. The current values — Kalshi 0.20, Polymarket 0.12 on T-24h price, computed over the past 90 days — are derived live from resolved contracts. You can re-verify the numbers yourself with curl at any time. Prediction Hunt does not publish calibration or accuracy data for its price feed.
Can I use Prediction Hunt and SimpleFunctions together?+
Yes. Prediction Hunt's five-minute-refresh dashboard gives a browser-friendly view of cross-venue spreads including PredictIt. SimpleFunctions adds the programmatic layer: MCP tools, thesis management, autopilot, and live indicators. They serve different surfaces — Prediction Hunt is a human UI, SimpleFunctions is an agent API. If your workflow spans both human monitoring across all three exchanges and automated execution on Kalshi and Polymarket, using both is reasonable.
Start for free.
Public endpoints are free for normal usage and rate-limited for reliability. Authenticated endpoints are free up to 15M tokens, then pay per token. No credit card to start.