Alternative · AI agent
Bankr vs
SimpleFunctions.
SimpleFunctions and Bankr both use AI to interact with prediction markets, but operate on fundamentally different layers. Bankr is a crypto-native agent that delivers Polymarket access through X/Twitter and a private terminal, combining it with an AI-assisted crypto wallet. SimpleFunctions is the programmable infrastructure layer above the data: causal-tree thesis system with auto-evaluation cycles, Portfolio Autopilot with a 7-gate risk cascade, computed indicators across 48K+ contracts, live calibration Brier scores, and a 56-tool MCP server spanning Kalshi and Polymarket.
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 programmatic depth beyond a conversational interface — calibrated probabilities with public Brier scores, causal-tree thesis modelling with automatic evaluation cycles, regime classification across the full 48K-contract universe spanning Kalshi and Polymarket, computed indicators (implied yield, cliff risk, liquidity availability score, event overround), and a 56-tool MCP server that integrates into Claude Code or Cursor in one command.
Choose Bankr if
Bankr is the right choice if your workflow lives inside X/Twitter and you want to interact with Polymarket positions through a conversational social interface without developer setup, or if you need an AI-assisted crypto wallet that manages crypto holdings and prediction market exposure on the same platform.
Bankr is a social-native Polymarket agent on X with a crypto wallet. SimpleFunctions is the programmable agent layer over Kalshi and Polymarket — theses, autopilot, indicators, MCP.
At a glance
Three things that
actually differ.
Everything Bankr gives you — Polymarket integration and AI-assisted market interaction — SimpleFunctions also gives you, plus Kalshi coverage on the same normalised feed, orderbook depth, and cross-venue arbitrage detection.
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 publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days — letting you verify its accuracy before building on it.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed on a single feed.
BankrPolymarket integration documented; Kalshi coverage not documented.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true — bid/ask ladder, spread, slippage estimation.
BankrNot published as a programmatic public endpoint.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, regime label — pre-computed across 48K+ contracts at /screen.
BankrNot documented.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, price bucket; Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days.
BankrNot published.
SimpleFunctionsPOST /api/thesis/create decomposes any thesis into a causal tree, scans Kalshi + Polymarket for edges, and runs an auto-evaluation heartbeat with signal injection.
BankrNot in scope.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade (kill switch, position limits, drawdown gate, regime check) before execution.
BankrAI agent for Polymarket and crypto interaction on X; autonomous execution parameters not publicly documented.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, and any MCP client.
BankrNo MCP server published.
SimpleFunctionsPublic REST API, 60-command CLI, 56-tool MCP server — fully programmatic, no social-platform dependency.
BankrX/Twitter conversational interface and a private terminal; designed for social-native, no-code interaction.
SimpleFunctionsNot in scope; SF focuses on prediction market analytics and agent execution, not crypto custody.
BankrAI-assisted crypto wallet on X — manages crypto holdings alongside Polymarket positions on a single platform.
SimpleFunctionsPublic REST + MCP + CLI reads require no auth; thesis and intent execution free up to 15M tokens, then pay-per-token.
BankrNot publicly documented.
Methodology
Verified 2026-04 from public sources only — Bankr's documentation, public website, and publicly observable behaviour. We never claim non-public information about Bankr'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 research agent that needs programmatic access to prediction market data across Kalshi and Polymarket.
SimpleFunctions · best fit
SF exposes a 56-tool MCP server, a fully documented REST API, and a 60-command CLI. The agent can query the 48K-contract universe, retrieve computed indicators, access orderbook depth, and scan cross-venue arbitrage opportunities without deriving signals from raw prices.
Bankr
Bankr provides Polymarket access via a conversational interface on X/Twitter and a private terminal. A publicly documented programmatic REST API for agent integration has not been published.
Scenario 02
Interacting with Polymarket positions conversationally through X/Twitter without any developer setup.
SimpleFunctions
SF requires API calls or CLI usage. While the 56-tool MCP server works inside Claude Code and Cursor, it is not a social-native conversational interface and requires a developer integration step.
Bankr · best fit
Bankr is purpose-built for this workflow — conversational Polymarket access directly on X/Twitter with no code required, plus an integrated AI-assisted crypto wallet for managing holdings on the same platform. This is Bankr's core product.
Scenario 03
Decomposing a macroeconomic thesis into testable sub-claims and scanning for tradeable prediction market positions.
SimpleFunctions · best fit
SF's thesis system accepts a plain-language sentence, decomposes it into a causal tree, maps sub-claims to contracts on Kalshi and Polymarket, computes tradeable edges, and runs an evaluation heartbeat on each cycle. Public theses are forkable.
Bankr
Bankr focuses on conversational market access and crypto wallet management. Structured causal-tree thesis decomposition with automated evaluation cycles is not documented as part of its feature set.
Scenario 04
Running an autonomous trading agent with multi-gate risk controls across prediction markets.
SimpleFunctions · best fit
Portfolio Autopilot uses a 1M-context LLM, 13 data sources, and a 7-gate risk cascade — kill switch, position limits, drawdown gate, and regime check — before any trade executes, covering both Kalshi and Polymarket on a single system.
Bankr
Bankr is an AI agent for crypto and Polymarket interaction; the scope and parameters of autonomous risk-gated execution are not publicly documented.
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 Bankr and how does it differ from SimpleFunctions?+
Bankr is a crypto-native AI agent that delivers Polymarket access through a conversational X/Twitter interface and a private terminal, paired with an AI-assisted crypto wallet. SimpleFunctions is a programmable prediction market infrastructure layer — public REST API, 60-command CLI, and 56-tool MCP server — built for developers and autonomous agents. The overlap is Polymarket venue coverage; the divergence is in distribution method, supported venues (SF adds Kalshi), and the depth of the analytics and automation layer.
Does SimpleFunctions cover the same prediction markets as Bankr?+
Both products include Polymarket. SimpleFunctions additionally covers Kalshi, normalising prices across both venues into a unified 48K+ contract universe. Cross-venue matched pairs are available at /api/public/cross-venue/pairs?preset=arb, exposing arbitrage opportunities between the two markets. Based on Bankr's public documentation, Polymarket is the documented venue; Kalshi coverage is not described.
What is SimpleFunctions' causal thesis system and how do I use it?+
POST /api/thesis/create takes a plain-language sentence and decomposes it into a causal tree of testable sub-claims, each mapped to a probability. The system scans Kalshi and Polymarket for contracts that test each sub-claim, computes tradeable edges, and runs an evaluation heartbeat — news scan, price refresh, milestone check, LLM evaluation, confidence update — on each cycle. External signals can be injected via /api/thesis/{id}/signal. Public theses are forkable. No comparable structured thesis system is documented on other prediction market platforms.
How does Portfolio Autopilot work?+
Portfolio Autopilot uses a 1M-context LLM reading 13 data sources to evaluate and size positions. Before any trade executes, it passes through a 7-gate risk cascade: kill switch, position limits, drawdown gate, regime check, and additional controls. The autopilot generates trade ideas with conviction scores and catalysts at /api/public/ideas and can execute autonomously when all gates clear. This differs from Bankr's conversational agent model, which operates through an X/Twitter interface rather than a programmatic risk-gated pipeline.
Can I use SimpleFunctions as an MCP server with Claude Code or Cursor?+
Yes. Run claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp and the full 56-tool server is available to any MCP-compatible client including Claude Code, Cursor, and others. Tools cover market search, orderbook depth, thesis creation and management, autopilot signals, calibration data, and cross-venue arbitrage scanning. No additional authentication is required for read operations. Bankr does not publish an MCP server.
Does SimpleFunctions publish its calibration accuracy publicly?+
Yes. GET /api/calibration returns SF's own Brier scores segmented by venue, category, and price bucket, computed over the past 90 days. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h prices. Brier score is a proper scoring rule — lower is better, 0.25 is effectively random on binary outcomes. This transparency lets users evaluate whether to trust SF's probability estimates before building on them. Bankr does not publish equivalent calibration data.
Does Bankr have a public REST API I can call programmatically?+
Based on Bankr's public documentation and website, access is provided through an X/Twitter conversational interface and a private terminal. A public REST API with documented endpoints has not been published. SimpleFunctions exposes a fully documented public REST API requiring no authentication for read operations, with an OpenAPI spec at /api/openapi.json, llms.txt at /llms.txt, and a /.well-known/ai-world-state spec for machine consumption.
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.