AgentOracle live
trust infrastructure

The trust layer for AI agents.

verify before you act.

Verify any claim before your agent acts. Per-claim confidence scoring across 4 independent sources. x402 native.

Try free — no wallet needed → $ pip install langchain-agentoracle crewai-agentoracle
/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 · cost $0.01 USDC
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...
how it works

4-source verification in seconds

Every claim runs through four independent sources in parallel. Consensus builds the score. Contradiction flags the risk.

01input
Claim Input
Agent sends any text or data to /evaluate. Plain string, JSON, scraped content — anything.
any source
02decompose
Decomposition
Gemma 4 breaks content into individual verifiable claims. Each claim is independent and atomic.
gemma 4
03verify
4-Source Verify
Sonar + Sonar Pro + Adversarial scan + Gemma calibration run in parallel against every claim.
4 sources
04score
Trust Score
Per-claim confidence (0.00–1.00) plus top-level recommendation: ACT, VERIFY, or REJECT.
0.00–1.00
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.
$0.01/claim
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 queries · /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 queries · /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 queries · /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
/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
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
Price per query $0.01 $0.005 $0.005 ~$0.01
What you get Verified truth Search results Search results Hallucination risk

Comparison based on publicly available pricing and documentation as of April 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 ($0.01) 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.