Alternative · Forecasting platform
Manifold Markets vs
SimpleFunctions.
Manifold Markets surfaces community-created play-money forecasting markets with a full public API, embeddable widgets, and an open-source monorepo. SimpleFunctions operates in a different register entirely: it is the agent layer above real-money venues, shipping a causal-tree thesis system with auto-evaluation cycles, an autonomous trading agent running a 7-gate risk cascade, 56 MCP tools that connect any AI client in one command, and computed indicators across 48K+ live contracts on Kalshi and Polymarket. Same category of product; different market type, different execution surface, different audience.
Verified 2026-04 · public sources only · live SF data from /calibration
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
Choose SimpleFunctions if you are building agents, autonomous systems, or research that needs calibrated real-money probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation heartbeats, regime classification across 48K contracts, computed indicators (implied yield, cliff risk index, liquidity availability score, event overround), and a 56-tool MCP server that integrates with Claude Code or Cursor in a single command. SF covers real-money venues — Kalshi and Polymarket — where positions carry actual economic stakes.
Choose Manifold Markets if
Choose Manifold Markets if your use case is community-driven play-money forecasting: creating markets around any question, embedding live probability widgets into external pages, or building on an open-source prediction market platform. Manifold's audience is forecasters and community builders operating in a no-financial-risk environment, not traders or AI agents deploying capital on regulated real-money venues.
Manifold is play-money community forecasting with embeddable markets; SimpleFunctions is the agent layer above real-money Kalshi and Polymarket venues.
At a glance
Three things that
actually differ.
Everything Manifold Markets gives you — a public REST API, searchable market data, and probability time-series — SimpleFunctions also gives you, on Kalshi and Polymarket real-money feeds across 48K+ active contracts.
On top of that, SF ships a causal-tree thesis system with auto-evaluation heartbeats, a Portfolio Autopilot (1M-context LLM, 7-gate risk cascade), computed indicators across the full contract universe, and 56 MCP tools no current PM data product exposes.
SF publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Manifold does not publish a calibration baseline.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsReal-money regulated venues (Kalshi + Polymarket); all positions carry genuine economic stakes and settle in USD.
Manifold MarketsPlay-money platform only; all markets use virtual currency (Mana) with no real-money settlement.
SimpleFunctionsKalshi + Polymarket normalised across 48K+ active contracts, with cross-venue matched pairs at /api/public/cross-venue/pairs.
Manifold MarketsCommunity-created play-money markets accessible via public API at docs.manifold.markets/api; no Kalshi or Polymarket coverage.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimation.
Manifold MarketsAMM-based liquidity pool structure; no traditional orderbook depth endpoint is published.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label pre-computed across 48K contracts at /screen.
Manifold MarketsRaw probability time-series via API; derived indicators are not pre-computed.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket, computed from the past 90 days.
Manifold MarketsCalibration baselines not published.
SimpleFunctionsPOST /api/thesis/create decomposes any sentence into a causal tree of testable sub-claims, maps each to contracts, propagates probabilities, and runs an evaluation heartbeat automatically.
Manifold MarketsNot in scope; Manifold is a market-creation and community forecasting platform, not a thesis evaluation engine.
SimpleFunctionsPortfolio Autopilot uses a 1M-context LLM across 13 data sources with a 7-gate risk cascade (kill switch, position limits, drawdown gate, regime check) before any execution.
Manifold MarketsPlay-money only; autonomous real-money trading is not a feature of the platform.
SimpleFunctions56 tools via `claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp`, compatible with Claude Code, Cursor, and any MCP client.
Manifold MarketsNo MCP server published.
SimpleFunctionsSF reads from existing real-money venues; it does not offer user-created market hosting or embeddable probability widgets.
Manifold MarketsAny user can create a market on any question; embeddable widgets allow live probability displays to be dropped into any webpage.
SimpleFunctionsPublic REST, MCP, and CLI reads require no authentication; thesis creation and intent execution are free up to 15M tokens, then pay-per-token.
Manifold MarketsPlay-money platform; accessible at no monetary cost, with real-money settlement not available.
Methodology
Verified 2026-04 from public sources only — Manifold Markets's documentation, public website, and publicly observable behaviour. We never claim non-public information about Manifold Markets'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 calibrated real-money signals from Kalshi and Polymarket.
SimpleFunctions · best fit
SF's MCP server exposes 56 tools covering market data, thesis evaluation, arbitrage detection, and portfolio management across 48K+ real-money contracts. A single `claude mcp add simplefunctions` command connects any Claude-based agent to the full stack, including calibration, indicators, and autopilot controls.
Manifold Markets
Manifold's public API covers play-money community markets only. There is no coverage of Kalshi or Polymarket, and no MCP server is published.
Scenario 02
Creating custom forecast markets around any topic and embedding live probability widgets in a blog or product.
SimpleFunctions
SF does not offer user-created market hosting or embeddable probability widgets. It reads from existing real-money venues and does not host its own market layer.
Manifold Markets · best fit
This is Manifold's core product. Create a market on any question, share it with a community, and embed live probability displays on any external webpage using Manifold's widget system. Manifold wins clearly here.
Scenario 03
Decomposing a thesis like 'The Fed will cut rates twice before year-end' into a causal tree of sub-claims mapped to tradeable contracts.
SimpleFunctions · best fit
POST /api/thesis/create takes the sentence, decomposes it into a causal tree, locates matching contracts on Kalshi and Polymarket, propagates implied probabilities up the chain, and starts an auto-evaluation heartbeat. Signals can be injected via /api/thesis/{id}/signal. Public theses are forkable.
Manifold Markets
Manifold allows creating related markets around a theme, but there is no automated causal decomposition, probability propagation across a tree, or evaluation heartbeat.
Scenario 04
Auditing a prediction model's calibration before deploying real capital.
SimpleFunctions · best fit
/api/calibration returns SF's own Brier scores by venue, category, and price bucket — a public, curl-verifiable calibration baseline updated from the past 90 days. You can benchmark your model against a live reference point with concrete numbers.
Manifold Markets
Manifold does not publish a calibration baseline or Brier score audit. Its play-money context also makes direct comparison to real-money models less applicable.
Migrate
From https://api.manifold.markets/v0/markets to SF.
Same shape, no auth, same venues. Python example.
import requests
# Fetch trending markets from Manifold (play-money)
resp = requests.get(
"https://api.manifold.markets/v0/markets",
params={"limit": 20, "sort": "score"},
)
markets = resp.json()
for m in markets:
print(m["question"], m["probability"])import requests
# Fetch active real-money contracts from SF (Kalshi + Polymarket)
resp = requests.get(
"https://simplefunctions.dev/api/public/markets",
params={"limit": 20},
)
markets = resp.json()
for m in markets:
print(m["title"], m["price"], m["venue"])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 the core difference between SimpleFunctions and Manifold Markets?+
The most fundamental difference is market type. Manifold is a play-money platform — all positions use virtual currency (Mana) with no real-money settlement. SimpleFunctions connects to Kalshi and Polymarket, both real-money regulated venues where positions carry genuine economic stakes. Beyond venue coverage, SF adds an agent layer Manifold does not offer: causal-tree thesis evaluation, autonomous portfolio trading, computed indicators across 48K contracts, and a 56-tool MCP server for AI clients.
Does SimpleFunctions support play-money or community-created markets?+
No. SimpleFunctions reads from Kalshi and Polymarket — real-money, regulated venues. It does not host or index play-money markets, and it does not offer a market-creation interface. If your use case is community forecasting, creating markets on arbitrary questions, or embedding probability widgets from custom markets into a website, Manifold is the more appropriate tool.
How does SimpleFunctions' causal thesis system work?+
POST /api/thesis/create accepts any natural-language claim — for example, 'The Fed will cut rates twice before year-end.' SF decomposes it into a causal tree of testable sub-claims, maps each to matching contracts on Kalshi and Polymarket, propagates implied probabilities up the causal chain, and starts an auto-evaluation heartbeat: news scan → price refresh → milestone check → LLM eval → confidence update. You inject signals via /api/thesis/{id}/signal, and public theses are forkable by other users.
What is the Portfolio Autopilot and how does it differ from anything Manifold offers?+
Portfolio Autopilot is SF's autonomous trading system for real-money venues. It uses a 1M-context LLM, pulls from 13 data sources, and passes every candidate trade through a 7-gate risk cascade — kill switch, position limits, drawdown gate, regime check, and others — before any execution. Manifold operates in a play-money environment only; autonomous real-money trading is not a feature it offers or targets.
Does Manifold Markets have an MCP server or computed indicators?+
Neither is published. Manifold's public API at docs.manifold.markets/api covers market data and user operations for its play-money platform. It does not expose a Model Context Protocol server or pre-computed indicators such as implied yield, cliff risk index, or liquidity availability score. SimpleFunctions' 56-tool MCP server is available at https://simplefunctions.dev/api/mcp/mcp and covers calibration, thesis management, cross-venue arbitrage, and portfolio operations.
Does SimpleFunctions publish its own calibration data?+
Yes. /api/calibration returns SF's own Brier scores, broken down by venue, category, and price bucket, computed from the past 90 days of resolved contracts. Kalshi stands at 0.20 and Polymarket at 0.12 on T-24h price. These numbers are live and curl-verifiable at any time. Manifold does not publish an equivalent calibration audit for its play-money markets.
Can I migrate from the Manifold API to SimpleFunctions' API?+
The APIs serve different underlying data — Manifold returns play-money community markets, SF returns real-money contracts from Kalshi and Polymarket. The migration is a conceptual shift as much as a technical one. If your downstream logic depends on real-money probabilities, the SF public REST API is a drop-in HTTP replacement: no authentication required for reads, same JSON conventions, and a richer set of fields including pre-computed indicators and calibration metadata.
Is Manifold Markets open source?+
Yes. Manifold publishes its monorepo on GitHub, which is a genuine advantage for developers who want to self-host or contribute to the platform's market mechanics. SimpleFunctions is not open-source at the platform level; its CLI is MIT-licensed and published at npm as @spfunctions/cli, and public datasets are released under CC-BY-4.0 on HuggingFace and Kaggle. The two projects have different stances on openness that reflect their different product goals.
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.