AgentOracle live
trust infrastructure
New Jun 1Open-source receipt verifier published — offline JWS verification, MIT licensed → github Jun 1Cross-operator benchmark live — open methodology, open submissions → github Jun 6IETF Internet-Draft FILED — draft-krausz-verification-state-00 → datatracker May 30Receipt spec v0.3 — binary-halt gate + canonical/derived/version-bound mapping → spec May 28AVeriTeC 2024 dev published — 57.6% overall, held-out 57.7%, MIT licensed → repo May 27Pinned in x402trace v0.3.3 — first operator-contributed fixture in the harness → release May 26Live on SKALE Base — first paid settlement gasless on SKALE → explorer May 11Tutorial #4: claim verification in AI content approval workflows → dev.to May 8Indexed in Coinbase Bazaar — 8 settlements verified → discovery

AI agents can act.
Most still can’t be trusted.

AgentOracle is the verification layer for the agent economy. We decompose every claim, verify across 4 independent sources, and return a cryptographic receipt — before your agent takes any action or moves value.

Works with Claude Desktop, Cursor, and Windsurf. Verify before you act.

INDEXED IN COINBASE BAZAAR · 8 SETTLEMENTS · LIVE ON SKALE · verify →
pip install langchain-agentoracle npm install agentoracle-verify
/evaluate live
input
[00:00.001] received /evaluate — dispatching to pipeline
[00:00.211] 4 claims extracted via Gemma 4
[00:00.216] querying Sonar · Sonar Pro · Adversarial · Gemma in parallel
[00:00.889] claim 1 supported (0.97) — 4/4 sources agree
[00:01.021] claim 2 refuted (0.04) — all sources contradict
[00:01.184] claim 3 supported (0.94) — 4/4 sources confirm
[00:01.342] claim 4 unverifiable (0.61) — insufficient data
[00:01.412] payment settled on Base · fingerprint stored ✓
0.94 confidence
act
4 claims · 3 supported · 1 unverifiable
evaluated in 1.4s · free during beta
act x402 protocol created by Coinbase
0.97
reject OpenAI acquired Anthropic in early 2026
0.04
act LangGraph leads agent frameworks
0.94
verify Gemini 3.0 has native agent tools
0.61
claim fingerprints loading...
queries today past 24h · rolling
verification sources 4 sonar · adversarial · gemma
chains supported 3 Base · SKALE · Stellar
system status checking connecting to API...
verifiable receipts

Verify the verifier.

Every /evaluate response is committed to a published JWS receipt format. Anyone can verify offline against our public JWKS — no AgentOracle service required.

live receipts

Every response, cryptographically signed.

Sample receipts. Real signatures. Each one verifiable against the public JWKS at agentoracle.co/.well-known/jwks.json.

11:47 AMACT
“Bitcoin is currently trading above $80,000.”
confidence 0.984 sourceskid: ao-receipt-2026-04-ed25519-f2753b7c
eyJhbGciOiJFZERTQSIsImtpZCI6ImFvLXJlY2VpcHQtMjAyNi0wNC0…
12:02 PMREJECT
“Vaccines cause autism in 1 in 50 children.”
confidence 0.99CDC, NEJM, WHOcontradicted by all 4 sources
eyJhbGciOiJFZERTQSIsImtpZCI6ImFvLXJlY2VpcHQtMjAyNi0wNC0…
3:21 PMABSTAIN
“Acme Corp’s Q3 2025 earnings exceeded guidance by 12%.”
confidence 0.41insufficient sourcescalibration.provisional: true
eyJhbGciOiJFZERTQSIsImtpZCI6ImFvLXJlY2VpcHQtMjAyNi0wNC0…
5:08 PMACT
“Marketing copy: ‘Our product is FDA-cleared for hypertension.’”
verified pre-publicationFDA registry confirmedaudit trail: legal review ready
eyJhbGciOiJFZERTQSIsImtpZCI6ImFvLXJlY2VpcHQtMjAyNi0wNC0…
who uses agentoracle

Built for the people who can’t afford to be wrong.

AI Engineers

Wire verification into your agent loop with one API call. Get back signed receipts you can store, audit, and replay.

Brand & Content Teams

Pre-publication fact-check for AI-generated copy. Replace human fact-check teams. Hand legal a signed audit trail, not a screenshot.

Compliance Officers

EU AI Act Article 12 record-keeping (high-risk AI systems, applies Aug 2, 2026), NIST AI RMF measurement — covered by cryptographic receipts that don’t require trusting us.

Developer Tooling Founders

Resell verification as a feature in your own product. MCP-native. x402-paid. No revenue share, no rate limit on integrations.

Researchers

Benchmark your model’s factual accuracy against AVeriTeC and FEVER through our public eval harness. Public scoring, deterministic results.

Don’t see your role?

Tell us your use case →

how it works

From claim to verifiable, auditable answer.

Four steps. Every response. No exceptions.

01decompose
Claim Decomposition
We break complex statements into verifiable atomic claims. Each one stands alone.
gemma 4
02verify
Multi-Source Verification
Each claim is checked against 4 independent sources in parallel. Consensus builds. Contradiction flags risk.
4 sources
03score
Confidence Scoring
Every result gets a precise 0.00–1.00 confidence score plus a recommendation: ACT, VERIFY, or REJECT.
0.00–1.00
04sign
Cryptographic Receipt
A signed JWS proof of verification. Store it, verify it, audit it. Tamper-evident, replayable, third-party verifiable.
ed25519 jws

Result: your agents don’t just give answers — they give verifiable, auditable answers.

capabilities

Built for agents. Designed for trust.

Every response is machine-readable. Every claim gets a confidence score. Every source gets a reputation. No API keys.

01 Per-claim verdicts Content is decomposed into individual claims. Each one gets a verdict — supported, refuted, unverifiable — with evidence and corrections.
0.97 accuracy
02 4-source verification Sonar + Sonar Pro + Adversarial + Gemma 4 run in parallel. Consensus builds the score. Contradiction flags the risk.
0.92 coverage
03 x402 native payments HTTP-native micropayments on Base, SKALE, and Stellar. No API keys. Agents discover pricing via the x402 manifest and pay inline.
multi-chain
04 Source reputation Every domain accumulates a trust score from verified claim history. Query reputation before using any source.
0.81 lift
05 Feedback flywheel Agents report outcomes via /feedback. The scoring model improves for every agent on the network.
0.76 growth
Live Verdicts
live demo

Evaluate any text

Submit any content and get per-claim verification in real time. No payment required to start.

use cases

Real agent workflows

See how agents use AgentOracle in production with real cost breakdowns.

Market Intelligence

Agent researches competitor pricing and market positioning across three dimensions.

  • "Competitor X pricing model 2026"
  • "Market share AI API providers"
  • "Developer API pricing trends"
3 × $0.02 · /research$0.06
Due Diligence

Agent verifies a company's claims and cross-references with public records.

  • "Company Y revenue claims verification"
  • "Company Y regulatory filings analysis"
2 × $0.10 · /deep-research$0.20
Real-Time News

Agent monitors breaking developments and synthesizes updates across multiple topics.

  • "AI regulation updates today"
  • "x402 protocol adoption updates"
  • "Agent framework releases 2026"
5 × $0.02 · /research$0.10
integration

MCP Server

Connect AgentOracle to Claude, Cursor, Windsurf, or any MCP-compatible client with a single command. No integration code required.

Claude Cursor Windsurf Any MCP Client
View on GitHub →
terminal
$ npx agentoracle-mcp

// claude_desktop_config.json

{
  "mcpServers": {
    "agentoracle": {
      "command": "npx",
      "args": ["agentoracle-mcp"]
    }
  }
}
pricing

Pay only for what you use

No subscriptions. No minimums. No API keys. Just pay per query with USDC on Base.

Gasless on SKALE Network — zero gas cost for agent queries

/preview
FREE
no payment required
  • Live truncated results
  • Confidence scores
  • 20 requests/hour
  • No payment required
Try /preview
/evaluate
FREE
beta · paid tiers coming soon
  • Full 4-source claim verification
  • Per-claim verdicts + evidence
  • act or halt output (binary gate, IETF -00)
  • Adversarial scanning included
  • On-chain payment verification
View x402 Manifest
/deep-research
$0.10
per query · USDC · Base · SKALE · Stellar
  • Multi-step deep analysis
  • Sonar Pro engine
  • Comprehensive source verification
  • Higher confidence scoring
  • Extended context window
View Manifest
For agent orchestration platforms

Platform-tier pricing — integrating verification at scale

Building a platform that needs verification as a primitive? Volume-tier rates kick in automatically above 1M verifications/month. Includes white-label receipt branding, custom mapping documents under your namespace, SLA on availability and latency, and a dedicated integration channel.

Open-source verifier client on npm: @agentoracle/receipt-verify — your end users get the same offline cryptographic guarantees regardless of which platform issued the receipt.

Talk to us View verifier on GitHub
credentials

Cryptographic proof, not vendor claims.

Six public artifacts. Every one independently verifiable.

technical

Specs & infrastructure

Protocolx402
ChainsBase · SKALE · Stellar
CurrencyUSDC + EURC
FacilitatorCoinbase CDP
Research ModelPerplexity Sonar
Endpoints/preview · /evaluate
HostingVercel Edge
Gasless OptionSKALE Active
Verification Sources4 (parallel)
Rate Limit100 req/hr
SDKLangChain · CrewAI
MCP ServerLive
comparison

How we compare

Other tools return search results. We return verified truth.

Feature AgentOracle Tavily Exa Raw LLM
Per-claim verification Yes No No No
Adversarial scanning Yes No No No
Confidence scoring 0.00–1.00 No No No
Multi-source (4 independent) Yes No No No
x402 native payments Yes No No No
Gasless option (SKALE) Yes No No No
Stellar support Yes No No No
Pricing $0.02 / $0.10 tiers varies varies per-token
What you get Verified truth Search results Search results Hallucination risk

Comparison based on publicly available pricing and documentation as of May 2026.

faq

Common questions

Everything you need to know before integrating.

x402 is an open protocol by Coinbase that enables HTTP-native payments. Instead of API keys, your agent includes a payment proof in the X-PAYMENT header of each request. The server verifies the on-chain payment and returns the response.
Yes, your agent needs a wallet with USDC on Base. The /preview endpoint is completely free and requires no wallet — use it to test first. Most agent frameworks support wallet integration through Coinbase CDP.
USDC on Base (L2), USDC.e on SKALE Base (zero gas fees), and native USDC on Stellar. Same endpoint — agent picks the cheapest chain. EURC is also accepted on Base.
Perplexity's API requires API keys and billing setup. AgentOracle wraps the same research engine in an agent-native payment layer — your agent discovers pricing via the x402 manifest, pays per query with USDC, and gets per-claim verdicts. Zero human setup required.
/evaluate (free during beta) verifies claims you already have — input any text, get per-claim ACT/VERIFY/REJECT verdicts. /research ($0.02) fetches new information from the web and returns structured results with confidence scoring.
100 requests per hour per IP for paid endpoints. 20 requests per hour for the free /preview endpoint. Rate limit headers are included on every response.

Your first verification is free

No wallet required. No API key sign-up. No payment method needed. Just paste a claim and verify.