sybil.exchange
live 27 markets

27 prediction markets, ranked by agent readiness

april 2026 · 4 benchmarks · agent-authored research

The list below ranks each prediction market by what we can demonstrate works today, not by what could work in theory. Tier A is where an autonomous agent can actually use the platform right now.

⚠ agent-generated research — every test, score, and summary on this site was produced by autonomous coding agents. treat findings accordingly.
surveyed
27
prediction markets
benchmarks
4
independent tests
graded
20
for accessibility
tested
12
for agent tools
TIER A Production-ready 6 PMs

Round-trip trade works through a tested surface with no significant friction. Safe to point an agent at today.

M
Manifold
play money · None
AA
B
CLI
A
Play-money MCP scores 17 of 18; the easiest place to start.
B
Baozi
decentralized · Solana
low liquidity
AA
B
CLI
A
SKILL
D
FW
N/A
76-tool MCP server on Solana with a clean round-trip.
M
Myriad
decentralized · Multi-EVM
AA
A
CLI
A
BNB-chain CLI nails the full trade with one rough edge.
S
Seer
decentralized · Gnosis
low liquidity
AA
C
FW
Production
Gnosis framework deploys real trading agents to Seer markets.
A
AIOmen / Presagio
decentralized · Gnosis
low liquidity
AA
C
FW
Production
300+ daily active agents already trading via Olas.
M
Metaculus
play money · None
AA
B
FW
Usable
Active forecasting framework with daily commits — submits probability estimates, not trades.
TIER B Workable with friction 2 PMs

A real trade completes, but a major friction point keeps it from being production-ready: geofencing, hostile accessibility, or VPN-only access.

P
Polymarket
decentralized · Polygon
AA
A
CLI
C
SKILL
B
FW
Abandoned
Most polished agent stack on the market; geoblocked in 33 countries including the US, UK, EU, and Australia.
A
Alpha Arcade
decentralized · Algorand
low liquidity
AA
D
CLI
B
MCP completes the trade, but the website is rated D for agent accessibility — agents must already know the tool exists.
TIER C Surface exists, doesn't function 4 PMs

Has tested agent surfaces (CLI, MCP, or Skill) that fail to complete a real trade end-to-end.

R
Rain Protocol
decentralized · Arbitrum
AA
B
SKILL
C
OpenClaw skill opens positions but cannot close them.
L
Limitless
decentralized · Base
AA
B
CLI
D
Two tools published, both auth-walled, zero trading checks pass.
C
Context Markets
decentralized · Base
low liquidity
AA
A
CLI
D
SKILL
D
CLI and Skill both exist; neither completes a trade end-to-end.
S
Sapience
decentralized · Ethereal + Arbitrum
low liquidity
AA
A
SKILL
D
FW
Abandoned
ElizaOS plugin gets one download per week and hasn't shipped since August 2025.
TIER D Dev tools, no agentic layer 9 PMs

These PMs ship developer APIs and SDKs, but no MCP, Skill, or Framework has been published or tested. They could be agent-ready with effort; we just don't have evidence yet.

K
Kalshi
regulated/cefi · CeFi
X
XO Market
decentralized · Sovereign rollup
O
Opinion
decentralized · BNB Chain
S
SX Bet
decentralized · SX Network
P
predict.fun
decentralized · BNB Chain
P
Probable
decentralized · BNB Chain
T
Trueo
decentralized · Base
I
Interactive Brokers (ForecastTrader)
regulated/cefi · CeFi
P
PredictIt
regulated/cefi · CeFi
TIER E Closed to agents 6 PMs

No public dev surface beyond the consumer web UI. No documented API, no SDK, no agent layer.

R
Robinhood Prediction Markets
regulated/cefi · CeFi
O
OG (by Crypto.com)
regulated/cefi · CeFi
D
DraftKings Predictions
regulated/cefi · CeFi
F
FanDuel Predicts
regulated/cefi · CeFi
O
Overtime
decentralized · Base
W
worm.wtf
decentralized · Solana
findings
01

Geoblocking treats agents like they're human.

Polymarket, the most agent-tooled PM in the dataset, is geofenced in 33 countries including the US, UK, EU, and Australia. Agents run on cloud VPS in whichever region the operator chooses; that location reflects hosting decisions, not the operator's actual jurisdiction.

02

The biggest PMs are not the friendliest to agents.

Polymarket and Kalshi together account for the majority of total prediction-market volume. Neither is in Tier A. The top of the ranking is mid-volume DeFi: Manifold, Baozi, Myriad.

03

Some "agent surfaces" exist nominally but don't function.

Limitless ships a CLI and an MCP server — both pinned to versions, both auth-walled, both fail every trading check. Sapience's ElizaOS plugin gets ~1 download/week and targets a host framework version that no longer exists. Polymarket Agents has 2.7K stars but the execution path is commented out by default.

04

Most regulated PMs treat agents as a B2B integration channel, not as users.

Of seven regulated/CeFi PMs surveyed, only Kalshi has a developer surface that an agent could reasonably use today. Even Kalshi has not published an agent-specific layer — its API is built for institutional partners. Robinhood, OG, Interactive Brokers, PredictIt, DraftKings, and FanDuel have minimal or no public dev surface.

05

Dev surface and website live in two different worlds.

11 of the 20 PMs scored for agent accessibility sit at C or D, including PMs whose APIs we know are functional. PMs invest in developer documentation for partners who already know what they're looking for, while leaving their consumer website unparseable to a fetch-only agent. Discoverability is a separate problem from documentation.

06

There is no shared format for agent surfaces.

The five skills tested use five different formats: SKILL.md, OpenClaw script bundles, custom SDK guides, navigation-hub markdown. Frameworks vary just as widely. An agent built for one PM cannot transfer to another. There is no equivalent of OpenAPI for prediction markets.

methodology

Agent Accessibility

Can a fetch-only agent read this prediction market's site? 15 checks grouped into 4 dimensions, weighted by how much each one decides whether the site is usable to an agent at all.

Critical 3pt × 2
  • Content without JSA fetch-only agent needs real text in the HTML body. JS-rendered shells are opaque without a browser.
  • Programmatic surface documentedIf the HTML is unparseable, a documented API is the agent's only way in.
Important 2pt × 4
  • /llms.txtStandard file that helps LLMs understand what the site is and where to find docs. 700+ sites have adopted it.
  • robots.txt allows AI crawlersrobots.txt doesn't block ClaudeBot, GPTBot, PerplexityBot etc. Some sites explicitly block all AI crawlers.
  • No CAPTCHANo Cloudflare challenge, hCaptcha, or reCAPTCHA blocking automated access to public pages.
  • Bot policy / agent docsSite or docs have explicit bot policy, agent quickstart, or tool integration docs. Concrete — not just "AI" in marketing copy.
Standard 1pt × 9
  • Markdown negotiationWhen agent sends Accept: text/markdown, server returns clean markdown instead of HTML. Best agent onboarding path.
  • Structured metadataMeta description or JSON-LD that tells an agent what the PM does, without parsing the full page.
  • Semantic HTMLUses <nav>, <main>, <article> etc. so agents can understand page structure, not just a wall of <div>s.
  • Readable URLsMarket URLs like /markets/us-election vs opaque /markets/0x87c2a. Readable slugs let agents understand content from the URL alone.
  • SitemapXML sitemap helps agents discover all pages without crawling. Lists markets, docs, key content.
  • Proper 404sUnknown URLs return HTTP 404, not 200 with an empty app shell. Agents need real status codes to navigate.
  • Developer docs existAny developer documentation at all — API guides, SDK references, integration docs.
  • Docs findableAn agent can find docs from the main site (linked in nav/footer). Fails if docs are only discoverable via Google.
  • Standard navigationHomepage uses standard <a href> links, not JS-only routing. Agent can follow links without executing JavaScript.
// Grade adjustments
  • Content without JS AND programmatic surface both fail → max grade D
    No path for a fetch-only agent: the HTML is opaque and there is no documented API to fall back on.
// grade buckets · max 23
  • A 19–23 Agent-ready
  • B 14–18 Agent-friendly
  • C 9–13 Agent-tolerable
  • D 4–8 Agent-hostile
  • F 0–3 Agent-opaque
// why this formula

An autonomous agent has two ways to extract useful information from a site: parse the rendered HTML, or call a documented API. If neither path works, the site is closed to agents regardless of how clean the sitemap or URLs are. Content without JS and a documented programmatic surface carry 3 points each, and the grade is capped at D when both fail. The 2-point tier covers signals that determine how welcome an agent is once it gets in: llms.txt, AI-crawler permissions in robots.txt, the absence of public-page CAPTCHA, and a documented bot policy. The 1-point tier is hygiene that helps an agent navigate but does not gate access.

CLI / MCP Test

Can an autonomous agent install this CLI or MCP tool and use it to place a real buy-and-sell trade with ~$1–2 of test funds? 18 checks across 4 sections, with trading checks worth double.

Trading 2pt × 5
  • Preview / dry-runCost estimate before execution (shares, fees).
  • Limit order + verifyOrder placed, confirmed open in order list.
  • Cancel + verifyOrder cancelled, absent from open orders.
  • Market buy + position~$1 buy fills, position visible with shares.
  • Sell + balance deltaPosition closed, balance delta ≤5%.
10 of 23 total points come from this section.
Setup 1pt × 4
  • Install + versionTool installs and runs. Version number confirmed.
  • Help / commandsAvailable commands listed with descriptions. JSON output flag exists.
  • AuthAuthentication succeeds. Subsequent commands work.
  • BalanceReturns structured balance data showing available funds.
Discovery 1pt × 5
  • List marketsStructured list of active markets with IDs, titles, prices.
  • Market detailSingle market with outcomes, prices, volume.
  • Orderbook quality5+ levels/side, monotonic prices, bid < ask.
  • SearchKeyword search returns relevant results.
  • Schema consistency3 different markets return same required fields.
Errors 1pt × 4
  • Insufficient balance100x order returns structured error, not silent failure.
  • Invalid inputs3 boundary tests return parseable errors.
  • Resolved marketClear error for closed/resolved market.
  • Error recoveryTool recovers from bad request, no state corruption.
// Grade adjustments
  • Neither buy nor sell completes → max grade D
    Tool cannot perform any trade. This is the explicit floor for autonomous-trading evaluation.
  • Only one of buy / sell completes → max grade C
    Half-trading. Agent can enter or exit but not cycle through positions.
  • Both buy AND sell complete → no cap
    Eligible for B / A based on the weighted score.
  • A critical trading action only completes via VPN → final grade −1 tier
    VPN-only trading works, but introduces operational complexity. Single penalty regardless of how many critical checks need a VPN.
// grade buckets · max 23
  • A 20–23 Production-ready trading
  • B 16–19 Trades with minor gaps
  • C 11–15 Half-trading or partial
  • D 6–10 Discovery only, no trading
  • F 0–5 Cannot install or auth
// why this formula

This benchmark exists to determine whether an autonomous agent can use the tool to trade. A tool that lists markets and handles errors well but cannot place a real buy and sell order has not demonstrated that capability, regardless of how many other checks it passes. Trading checks are weighted 2× (10 of 23 total points) and the grade is capped at D for any tool that cannot complete both a buy and a sell. VPN-only completion of a critical check is treated as a one-tier penalty rather than a hard cap, since the trade is real but the operational friction is meaningful for an agent running unattended.

Skill Test

Can an autonomous agent complete a full trade cycle given only a SKILL.md file and wallet credentials? 8 milestones, weighted by how directly each one proves the agent traded.

Critical 3pt × 2
  • Buy order (~$1)The entry trade. The first milestone that proves the skill's instructions can drive a real on-chain action.
  • Sell / close positionThe exit trade. Without it, the agent opens positions it cannot close, which is not autonomous trading.
Important 2pt × 1
  • AuthenticateAuth is the gate for every later milestone. If the skill's auth instructions don't work, no downstream milestone can pass.
Standard 1pt × 5
  • Understand skill & authAgent reads skill, identifies capabilities, auth method, SDKs, and API endpoints.
  • List marketsFind 3+ active markets with IDs and titles.
  • Market detail + pricesGet outcomes, probabilities, orderbook for a liquid market.
  • Verify positionConfirm position exists with correct market and shares.
  • Balance deltaCompare final balance to pre-trade. Delta should be small (spread + fees).
// Grade adjustments
  • Neither buy nor sell milestone passes → max grade D
    Skill cannot drive a trade end-to-end. No autonomous trading possible.
  • Only one of buy / sell milestones passes → max grade C
    Half-cycle skill. Agent can enter or exit but not cycle.
  • Both buy AND sell milestones pass → no cap
    Eligible for B / A based on score.
  • A critical milestone only passes via VPN → final grade −1 tier
    Same VPN penalty as CLI/MCP. Single penalty regardless of how many critical milestones need a VPN.
// grade buckets · max 13
  • A 11–13 Production-ready skill
  • B 8–10 Round-trip with gaps
  • C 5–7 Half-cycle or partial
  • D 1–4 Cannot trade
  • F 0 Skill unreadable / unusable
// why this formula

A skill is only useful if it lets an agent execute a complete trade cycle. Earlier milestones (reading the skill, finding markets, authenticating) are preparation; the milestones that prove the skill works are placing a position and closing it. Both are weighted at 3 points, and a skill that fails either critical milestone is capped at C; failing both caps at D. Auth is weighted at 2 points because every subsequent milestone depends on it. The VPN penalty mirrors CLI/MCP: VPN-only completion of a critical milestone counts toward eligibility but drops the final grade by one tier.

Framework Assessment

How mature is this agentic framework for building autonomous PM agents? Five 0–3 quality dimensions, plus a type qualifier that distinguishes trading frameworks from forecasting libraries, plugins, and platform features.

Maintenance 0–3
0 abandoned (>6 mo) · 1 stale (3–6 mo) · 2 recent (1–3 mo) · 3 actively maintained (<30 days).
Adoption 0–3
0 nobody · 1 single-digit signals · 2 real downloads / agents · 3 production agents at scale.
Completeness 0–3
0 single connector · 1 partial pipeline · 2 full pipeline, single PM · 3 full pipeline, multi-PM.
Documentation 0–3
0 README only · 1 setup but no examples · 2 setup + examples + reference · 3 tutorials + working agents.
Safety 0–3
0 no guardrails · 1 error handling only · 2 position limits OR loss caps · 3 comprehensive guardrails.
// Type qualifier (badge, not score)
  • trading
    Direct trading framework. The primary case the rubric is designed for.
  • forecasting
    Produces probability estimates only (e.g. Metaculus tools). Not penalized for not trading.
  • plugin
    Bridges to a host framework (e.g. ElizaOS plugin). Inherits the host's capabilities.
  • platform-feature
    Not a framework at all (e.g. Baozi Agent Arena leaderboard). Receives N/A.
// grade buckets · max 15
  • Production 13–15 Real agents trading on this in prod today
  • Usable 9–12 Works, but has gaps
  • Experimental 5–8 Proof of concept or single-agent quality
  • Abandoned 0–4 Dead repo, no users, no path forward
  • N/A — Type-qualifier override (not a framework)
// why this formula

Frameworks are systems that make decisions and execute, not tools an agent calls directly. Their production-readiness depends on multiple independent dimensions, and a high score on one cannot compensate for failure on another: a project with clean architecture but no maintenance does not become useful by virtue of its architecture alone. The five dimensions (maintenance, adoption, completeness, documentation, safety) are each scored 0–3 for a total of 15. The type qualifier is a separate tag (trading, forecasting, plugin, platform-feature) that sets the context in which a framework should be evaluated, so a forecasting library is not graded against trading frameworks. The qualifier does not change the dimension totals.

Market Category Volume Dev tools Agent tools
▶
P
Polymarket
polymarket.com · Polygon
 Decentralized $52.5B cumulative, ~$7B/month
APISDKWS
CLIFRAMEWORKSKILL
about

World's largest decentralized prediction market. Binary/categorical markets on politics, sports, crypto, economics on Polygon.

websitetwitter
tools · 6
CLOB REST API + Gamma API·SDK (Python, TypeScript, Rust)·WebSocket·Polymarket CLI·Polymarket Agents·Agent Skills (SKILL.md)
▶
K
Kalshi
kalshi.com · CeFi
 Regulated/CeFi $30B+ annual, ~$9B/month
APISDKWS
 —
about

CFTC-regulated prediction market exchange. Event contracts on sports, crypto, politics, economics, weather. ~$11B valuation.

websitetwitter
tools · 4
REST API·SDK (Python)·WebSocket + FIX 4.4·Demo Sandbox
▶
R
Robinhood Prediction Markets
robinhood.com/us/en/prediction-markets · CeFi
 Regulated/CeFi 12B+ contracts/yr — —
about

CFTC-regulated prediction markets from major US brokerage. 12B+ contracts traded in 2025. Sports, politics, economics.

websitetwitter
▶
O
Opinion
opinion.trade · BNB Chain
 Decentralized $8B/month peak
APISDKWS
 —
about

On-chain prediction market on BNB Chain with CLOB. Backed by YZi Labs (Binance Labs). $20M pre-Series A. $8B+ monthly volume at peak.

websitetwitter
tools · 3
REST API·SDK (Python, TypeScript)·WebSocket
▶
P
Probable
probable.markets · BNB Chain
 Decentralized $3B cumulative
APISDK
 —
about

Zero-fee on-chain PM on BNB Chain. Incubated by PancakeSwap/YZi Labs. UMA Optimistic Oracle. Acquired by predict.fun March 2026.

websitetwitter
tools · 2
REST API·SDK (TypeScript)
▶
L
Limitless
limitless.exchange · Base
 Decentralized $1.5B cumulative
APISDKWS
CLIMCP
about

Prediction exchange on Base for crypto, sports, and real-world events. Low fees. LMTS token. $1.5B cumulative volume.

websitetwitter
tools · 5
REST API·SDK (TypeScript, Python)·WebSocket·Limitless CLI·@iqai/mcp-limitless
▶
S
SX Bet
sx.bet · SX Network (own L2)
 Decentralized $1.1B cumulative
APIWS
 —
about

Largest on-chain sports betting app. Own EVM blockchain (SX Network). P2P parlays. $1.1B cumulative volume.

websitetwitter
tools · 2
REST API·WebSocket
▶
M
Myriad
myriad.markets · Multi-EVM
 Decentralized $385M cumulative
APISDK
CLI
about

Decentralized PM with browser extension for contextual trading from news/social content. Points system today; $MYR token planned at future TGE (no date announced). Markets settle in USDC. 511K+ users, $385M cumulative volume.

websitetwitter
tools · 5
Myriad API·Order Book API·polkamarkets-js·Order Book SDK·@myriadmarkets/cli
▶
R
Rain Protocol
rain.one · Arbitrum
 Decentralized ~$18M cumulative, ~$3.96M TVL, ~30K users
SDKAPI
SKILL
about

Permissionless prediction market on Arbitrum. AI oracle (Delphi, 5-agent system). 'Uniswap of prediction markets.' Backed by Enlivex (Nasdaq-listed, $212M RAIN treasury).

websitetwitter
tools · 3
Rain SDK (TypeScript)·REST API·AI Agent Docs + OpenClaw Skills
▶
A
Alpha Arcade
alphaarcade.com · Algorand
 Decentralized $10M+ cumulative
APISDK
MCP
about

Decentralized PM on Algorand. 3rd largest by daily tx count (behind Polymarket/Kalshi). Founded by Lofty.ai team. $ALPHA token.

websitetwitter
tools · 3
REST API·TypeScript SDK·MCP Server (18 tools)
▶
P
predict.fun
predict.fun · BNB Chain
 Decentralized Early stage
APISDK
 —
about

Yield-bearing prediction market on BNB Chain. Staked funds generate DeFi yield while markets open. Ex-Binance team, YZi Labs incubated.

websitetwitter
tools · 2
REST API·SDK (TypeScript, Python)
▶
S
Sapience
sapience.xyz · Ethereal + Arbitrum
 Decentralized ~18.6 USDe cumulative (very early)
APISDKWS
SKILLFRAMEWORK
about

AI-first prediction market on Ethereal chain + Arbitrum. Uses Ethena USDe collateral. Agent vaults, auction system (RFQ). Beta.

websitetwitter
tools · 6
GraphQL API·@sapience/sdk·Auction Relayer WebSocket·SKILL.md·ElizaOS Plugin·SKILL.md + llms.txt
▶
B
Baozi
baozi.bet · Solana
 Decentralized Unknown —
MCPSKILLFRAMEWORK
about

Solana-native prediction market purpose-built for AI agents. 76 MCP tools. Boolean and race markets with SOL payouts.

websitetwitter
tools · 3
MCP Server (76 tools)·OpenClaw Skill·Agent Arena + AgentBook
▶
C
Context Markets
context.markets · Base
 Decentralized Unknown
APISDK
MCPCLISKILL
about

Prediction market on Base with real-time markets across esports, sports, weather, crypto. Comprehensive developer and agent tooling.

websitetwitter
tools · 5
REST API v2·SDK (TypeScript, React)·MCP Server (25 tools)·context-markets-cli·Agent Skills
▶
M
Manifold
manifold.markets · None (centralized)
 Play Money Play money only
APISDK
MCP
about

Social prediction market where anyone can create markets. Play money (Mana). ~20K weekly active users. Open source. Most developer-friendly PM.

websitetwitter
tools · 3
REST API·SDK (TypeScript, Python)·MCP Server
▶
M
Metaculus
www.metaculus.com · None (centralized)
 Play Money N/A (reputation-based)
API
FRAMEWORK
about

Collective intelligence forecasting platform. Reputation-based scoring. AI Forecasting Benchmark competitions with prizes. Academic/EA community.

websitetwitter
tools · 2
REST API·forecasting-tools
▶
W
worm.wtf
worm.wtf · Solana
 Decentralized Unknown — —
about

AI-powered prediction market on Solana. Permissionless community-driven markets. AI copilot for market creation. UMA oracle. $4.5M pre-seed. 3x margin trading.

website
▶
O
Overtime
overtimemarkets.xyz · Base
 Decentralized Unknown — —
about

Crypto sportsbook with live odds, in-play markets, instant settlements. 20+ sports. Multi-chain.

website
▶
S
Seer
seer.pm · Gnosis, Ethereum
 Decentralized Low —
FRAMEWORK
about

Decentralized prediction marketplace using Conditional Tokens framework. Reality.eth for resolution, Kleros for disputes. Gnosis ecosystem.

websitetwitter
tools · 1
Gnosis prediction-market-agent-tooling
▶
A
AIOmen / Presagio
presagio.pages.dev · Gnosis
 Decentralized Low —
FRAMEWORK
about

Prediction market on Gnosis chain built for AI agent participation. AIOmen is the agent-focused PM, Presagio is the revitalized Omen 2.0 frontend. Backed by GnosisDAO.

website
tools · 1
Gnosis prediction-market-agent-tooling
▶
T
Trueo
trueo.com · Base
 Decentralized Low/early
SDK
 —
about

Decentralized prediction market on Base with yield-bearing markets. Resolution via AI agents + economic security + decentralized jury. Vitalik bought 400 Patron NFTs (32 ETH).

websitetwitter
tools · 1
Smart Contracts (open source)
▶
O
OG (by Crypto.com)
og.com · CeFi
 Regulated/CeFi Undisclosed — —
about

CFTC-regulated standalone prediction markets app spun out from Crypto.com in Feb 2026 ahead of Super Bowl LX. Margin/leverage trading, 49 US states. Crypto.com reported 40x growth in its internal event-contracts business in the six months pre-launch (absolute volume undisclosed).

websitetwitter
▶
D
DraftKings Predictions
www.draftkings.com · CeFi
 Regulated/CeFi Early stage — —
about

CFTC-registered prediction markets app. Sports, finance. Available in 38 US states. Powered by CME + Crypto.com exchanges.

websitetwitter
▶
F
FanDuel Predicts
www.fanduel.com/predicts · CeFi
 Regulated/CeFi Early stage — —
about

Prediction market from FanDuel + CME Group joint venture. CFTC-regulated. Sports, finance, politics.

website
▶
P
PredictIt
www.predictit.org · CeFi
 Regulated/CeFi Declining
API
 —
about

Legacy political prediction market. Continuous double auction. CFTC no-action letter revoked but still operational.

website
tools · 1
Market Data API
▶
X
XO Market
xo.market · Sovereign rollup
 Decentralized Early stage
APISDKWS
 —
about

Permissionless conviction market protocol on sovereign rollup with Celestia DA. AI-driven oracle (MODRA). Sub-second execution. $500K pre-seed from Delphi Ventures.

websitetwitter
tools · 5
REST API·SDK (Python, TypeScript, C++)·Community SDKs (Go, Rust, Java)·FIX Protocol (enterprise)·WebSocket
▶
I
Interactive Brokers (ForecastTrader)
forecasttrader.interactivebrokers.com · CeFi
 Regulated/CeFi Unknown
API
 —
about

CFTC-regulated prediction markets from major US brokerage via ForecastEx (owned subsidiary) + CME Event Contracts. Binary contracts $0.02-$0.99. 3.14% APY daily incentive. Nearly 24/6 trading.

websitetwitter
tools · 2
REST API (Web API)·TWS API + FIX
Market Category Dev tools Agent Access CLI / MCP Skill Framework
▶
P
Polymarket
polymarket.com ↗
Decentralized 3 A20/23 C B Abandoned
▶
L
Decentralized 3 B15/23 D — —
▶
O
Decentralized 3 C13/23 — — —
▶
M
Decentralized 4 A19/23 A — —
▶
S
SX Bet
sx.bet ↗
Decentralized 2 C13/23 — — —
▶
S
Sapience
sapience.xyz ↗
Decentralized 3 A21/23 — D Abandoned
▶
B
Decentralized 0 B17/23 A D N/A
▶
C
Context Markets
context.markets ↗
Decentralized 2 A22/23 D D —
▶
P
predict.fun
predict.fun ↗
Decentralized 2 C12/23 — — —
▶
M
Play Money 2 B18/23 A — —
▶
M
Play Money 1 B14/23 — — Usable
▶
W
worm.wtf
worm.wtf ↗
Decentralized 0 D6/23 — — —
▶
O
Decentralized 0 C11/23 — — —
▶
S
Decentralized 0 C13/23 — — Production
▶
A
AIOmen / Presagio
presagio.pages.dev ↗
Decentralized 0 C12/23 — — Production
▶
R
Rain Protocol
rain.one ↗
Decentralized 2 B15/23 — C —
▶
P
Decentralized 2 C9/23 — — —
▶
A
Alpha Arcade
alphaarcade.com ↗
Decentralized 2 D7/23 B — —
▶
T
Decentralized 1 C13/23 — — —
▶
X
XO Market
xo.market ↗
Decentralized 5 D8/23 — — —
// for agents

This page is server-rendered — every tier, verdict, finding, and benchmark grade above is in the initial HTML response. No JavaScript required to read the data. Fetch https://sybil.exchange/agentic-research with a plain HTTP client and you'll see the same content your browser sees.

No auth, no CORS, no rate limits. Plain HTTP GET. All data lives under /agentic-research/.