Alternative · AI agent
Fere AI vs
SimpleFunctions.
Fere AI is a consumer crypto AI assistant that surfaces Polymarket prediction markets alongside memecoins and DeFi yield farming for retail discovery. SimpleFunctions is built for developers and agent runtimes: a causal-tree thesis system that decomposes any claim into testable sub-claims with automatic evaluation cycles, an autonomous Portfolio Autopilot with a 7-gate risk cascade, calibrated world model across 48K+ active prediction market contracts, and a 56-tool MCP server ready for Claude Code, Cursor, or any MCP client. Same upstream Polymarket feed in one area; entirely different product surface and intended user.
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 consumer-facing market discovery — calibrated probabilities with public Brier scores, causal-tree thesis modelling that decomposes a sentence into a testable sub-claim tree with automatic evaluation cycles, regime classification across the full 48K-contract universe, computed indicators (implied yield, cliff risk, liquidity availability score), cross-venue arbitrage pair matching, and a 56-tool MCP server that integrates with Claude Code or Cursor in one line.
Choose Fere AI if
You want a crypto-native AI assistant that handles the full DeFi stack — memecoins, yield farming, and multi-chain agent actions — with Polymarket prediction markets as one discovery surface among many. Fere AI is built for that consumer workflow; its product surface is crypto-wide, not prediction-market-deep.
Fere AI is a consumer crypto AI covering DeFi and Polymarket discovery; SimpleFunctions is an agent-first prediction market stack with thesis system, autopilot, and MCP.
At a glance
Three things that
actually differ.
Everything Fere AI gives you — Polymarket prediction market discovery surfaced through an AI agent — SimpleFunctions also gives you, on the same Polymarket feed plus Kalshi, across 48K+ active contracts indexed in real time.
On top of that, SF ships a causal-tree thesis system, an autonomous trading agent (Portfolio Autopilot, 1M-context LLM, 7-gate risk cascade), and 56 MCP tools that no current prediction market product exposes.
SF also publishes live Brier scores for itself at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Most competitors claim accuracy; we let you check ours.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed with cross-venue matched pairs.
Fere AIPolymarket prediction-market discovery alongside crypto assets (per public product description).
SimpleFunctionsPrediction markets only — Kalshi and Polymarket; no memecoin or yield farming coverage.
Fere AIMemecoins, yield farming, and multi-chain DeFi agents alongside Polymarket discovery — this is Fere AI's primary product surface.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true — bid/ask ladder, spread, and slippage estimate.
Fere AINot documented as a public machine-consumable endpoint.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label pre-computed across 48K contracts at /screen.
Fere AIDerived indicators not published; discovery is consumer-facing rather than quantitative.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket; Kalshi 0.20, Polymarket 0.12 on T-24h price.
Fere AINot published.
SimpleFunctionsPOST /api/thesis/create decomposes any natural-language thesis into a causal tree, propagates probabilities, scans Kalshi + Polymarket for tradeable edges, and runs auto-evaluation cycles.
Fere AINot in scope; market surfacing is discovery-oriented rather than structured thesis decomposition.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade (kill switch, position limits, drawdown gate, regime check) before any execution.
Fere AIAutonomous prediction market execution with risk gates is not described in the public product surface.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, any MCP client.
Fere AINo public MCP server documented.
SimpleFunctionsPublic REST API, 60+ CLI commands (npm i -g @spfunctions/cli), and MCP server — all machine-consumable, reads require no auth.
Fere AIConsumer app interface; no public REST API documented for programmatic access.
SimpleFunctionsFree public REST + MCP + CLI for reads; pay-per-token only on thesis/intent execution above 15M tokens.
Fere AIPricing not publicly documented in available sources.
Methodology
Verified 2026-04 from public sources only — Fere AI's documentation, public website, and publicly observable behaviour. We never claim non-public information about Fere AI'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 needs structured, machine-consumable prediction market data with calibrated probability signals.
SimpleFunctions · best fit
SF's public REST API, 56-tool MCP server, and /api/agent/world endpoint are designed for agent consumption. Calibration data, computed indicators, and cross-venue arbitrage pairs are all machine-readable with no authentication required for read operations.
Fere AI
Fere AI is a consumer AI assistant rather than an API product; it surfaces Polymarket for human-facing discovery rather than providing structured, programmatic endpoints for agent pipelines.
Scenario 02
Exploring memecoins, yield farming opportunities, and multi-chain DeFi strategies with prediction markets as one signal among many.
SimpleFunctions
SF covers prediction markets only — Kalshi and Polymarket. It does not track memecoins, yield farming, or multi-chain DeFi activity. This is outside SF's scope.
Fere AI · best fit
This is Fere AI's primary product surface. Its multi-agent architecture is designed for exactly this crypto-native, cross-asset discovery workflow. Fere AI is the better fit here.
Scenario 03
Decomposing a geopolitical or macroeconomic thesis into tradeable prediction market edges on Kalshi and Polymarket.
SimpleFunctions · best fit
SF's causal thesis system takes a natural-language claim, decomposes it into a tree of testable sub-claims, propagates probabilities, and scans both venues for matching contracts. Signal injection and auto-evaluation cycles keep the thesis live as events develop.
Fere AI
Fere AI surfaces Polymarket markets for discovery but does not expose a structured thesis decomposition or causal probability propagation system.
Scenario 04
Running autonomous, risk-gated trades on prediction markets without manual order placement.
SimpleFunctions · best fit
Portfolio Autopilot ingests 13 data sources into a 1M-context LLM and runs a 7-gate risk cascade before placing any order. It is purpose-built for autonomous prediction market execution on Kalshi and Polymarket.
Fere AI
Fere AI's agent capabilities focus on crypto DeFi actions. Autonomous, risk-gated prediction market execution with drawdown gates and regime checks is not described in its public product surface.
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 and how is it different from Fere AI?+
SimpleFunctions is an API, CLI, and MCP server built for developers and AI agents working on prediction markets (Kalshi and Polymarket). It exposes calibrated probability data, computed indicators, a causal thesis system, and autonomous trading across 48K+ active contracts. Fere AI is a consumer crypto AI assistant that includes Polymarket as one discovery surface alongside memecoins and DeFi yield farming. They serve different audiences: SF is infrastructure for builders and agent pipelines; Fere AI is an end-user product for crypto exploration.
How does SimpleFunctions' causal thesis system work?+
You POST a natural-language claim to /api/thesis/create. SF decomposes it into a causal tree of testable sub-claims, assigns initial probabilities to each node by scanning Kalshi and Polymarket for matching contracts, and launches an evaluation heartbeat. The heartbeat runs on a schedule: news scan → price refresh → milestone check → LLM evaluation → confidence update. You can inject new signals at any time via /api/thesis/{id}/signal. Public theses are forkable. No other prediction market product exposes this architecture.
How does SimpleFunctions' Portfolio Autopilot work?+
Portfolio Autopilot is SF's autonomous trading agent for prediction markets. It ingests 13 data sources into a 1M-context LLM and runs a 7-gate risk cascade before executing any trade — gates include a kill switch, position limits, drawdown gate, and regime check, among others. Every gate must clear before an order is placed. The system is purpose-built for Kalshi and Polymarket; it is not a general crypto trading bot and does not operate on memecoins or DeFi positions.
Can I use SimpleFunctions as an MCP tool in Claude Code or Cursor?+
Yes. Run claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. SF exposes 56 MCP tools covering market search, thesis creation, orderbook depth, calibration data, cross-venue pair matching, trade ideas, and more. The server requires no API key for read operations, so you can start querying prediction market data from any MCP-compatible client immediately without an account.
Does Fere AI have a public API I can call from my code?+
Based on publicly available information, Fere AI presents as a consumer AI assistant rather than a developer API product. No public REST API documentation has been observed. If you need machine-consumable endpoints for prediction market data — normalised prices, orderbook depth, computed indicators, calibration scores — SF's public REST API, CLI, and MCP server are available without authentication for read operations.
What calibration data does SimpleFunctions publish?+
SF publishes its own Brier scores at /api/calibration, broken down by venue, category, and price bucket. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price, computed over the past 90 days. This lets you independently verify SF's forecasting accuracy before building on top of it. The endpoint is public and can be queried with a simple curl call — no authentication required.
Which product is better for building a prediction market data pipeline?+
SimpleFunctions. SF provides a public REST API with cross-venue normalised prices, orderbook depth, computed indicators (implied yield, cliff risk index, liquidity availability score, event overround), cross-venue arbitrage pair matching, and a 56-tool MCP server. Fere AI is designed as a consumer AI assistant for crypto discovery and does not appear to offer a documented public API for programmatic prediction market data access.
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.