We count page visits with Google Analytics to see which pages are read. Nothing is stored until you accept, and we never store search queries. Privacy.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"phion-agent-trust-infrastructure-2","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Transaction Assurance — Verify settlement, delivery and deterministic acceptance; emit a signed receipt and dispute packet
Transaction Recovery — Classify paid transaction failures and emit signed recovery claims and deterministic remedy plans
Try PHION Service Free — Preview any PHION service, inspect its value and receive exact machine-readable upgrade terms without a wallet or payment
Agent Spending Gateway — Non-custodial local spending mandates with per-call, cumulative, service and expiry limits
PHION Execute — Execute any selected PHION service through one budgeted, persistently idempotent call with acceptance checks and a signed completion envelope
PHION Universal Market — Normalize capabilities and compare PHION and configured external providers; economic execution remains buyer-funded, authority-bound and disabled until a production adapter is verified
Tool Output Firewall — Inspect untrusted tool output before context ingestion or downstream action
7 d ago · declared · summary → "One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security,
7 d ago · declared · version → "1.57.0"
7 d ago · declared · description → "One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security,
21 d ago · declared · publisherName → "PHION Systems"
21 d ago · declared · summary → "One hundred twenty-two composable inference, search, intelligence, verified-data, enrichment, durable-task, security, t
21 d ago · declared · description → "One hundred twenty-two composable inference, search, intelligence, verified-data, enrichment, durable-task, security, t
21 d ago · declared · publisherUrl → "https://phion.systems"
21 d ago · declared · homepageUrl → "https://phion.systems/services"
21 d ago · declared · version → "1.52.0"
1 mo ago · declared · description → "Seventeen composable trust, compatibility, reputation, commerce and RWA services for autonomous AI agents"
1 mo ago · declared · summary → "Seventeen composable trust, compatibility, reputation, commerce and RWA services for autonomous AI agents"
1 mo ago · declared · protocols → ["a2a"]
Memory Write Guard
— Screen persistent agent-memory writes for poisoning and missing provenance
MCP Manifest Firewall — Inspect MCP metadata and schemas before installation or trust
Tool Call Policy Guard — Bind proposed tool calls to declared intent and execution policy
Data Egress Preflight — Inspect outbound agent data and destination before transmission
Schema Normalize & Repair — Validate and safely normalize agent payloads before payment without altering payment-critical values
RWA Asset Due Diligence — Issuer, contract, custody and disclosure assessment with live evidence
RWA Compliance Decision — Deterministic declared eligibility and transfer-policy assessment
RWA NAV & Reserve Verification — Independent observations for NAV, reserve and collateral claims
RWA Transaction Assurance — Asset, payment, delivery and transfer-rule verification
RWA Corporate Action Monitor — Detect material NAV, income, maturity, redemption and freeze changes
Sanctions Screening Evidence — Traceable literal screening against observed official US and EU sources; not legal clearance
Agent Reputation Evidence — Evidence-bounded reputation score with confidence, coverage and explicit limitations
Counterparty Risk Preflight — Deterministic allow, review or deny decision using supplied reputation evidence and transaction limits
Agent Budget Guard — Stop autonomous spending before a call exceeds its task, session or period budget.
Idempotency Replay Guard — Distinguish a safe retry from conflicting reuse before an agent repeats an action or payment.
Human Approval Policy — Make escalation predictable by classifying actions before execution.
Secret Redaction Preflight — Remove common secret indicators before agent context or payload leaves its boundary.
OAuth Token Audience Guard — Prevent token forwarding to the wrong resource after local signature validation.
Redirect Callback Validator — Reject unsafe callbacks, ambiguous domains and redirects outside an explicit allowlist.
Tool Capability Drift Monitor — Detect when an approved tool changes its schema or declared capabilities.
MCP Server Identity Evidence — Bind the declared MCP domain, endpoint, manifest, key and version into portable evidence.
Agent Task Handoff Receipt — Give collaborating agents a portable statement of task, scope, budget and expiry.
Context Provenance Labeler — Carry integrity and confidentiality labels with agent context instead of losing its origin.
Signed Result Comparator — Expose exact agreement or conflict between multiple agent results without inventing consensus.
Service SLA Attestation — Turn bounded availability and latency samples into auditable signed SLA evidence.
Autonomous Payment Firewall — Reject unsafe payment terms before an autonomous agent signs or spends.
Independent Web Evidence — Independently retrieve, normalize, screen and hash a public source.
AI Agent Due Diligence — Inspect an agent endpoint before trusting it, delegating work or paying it.
Commerce Journey Verification — Verify that intent, quote, payment and delivery form one untampered history.
Payment Route Selector — Reject routes that cannot safely settle, rank the remaining x402 routes by your policy, and return the exact next action before signing.
x402 Quote Comparator — Validate and normalize x402 v2 quotes, preventing false price comparisons across incompatible assets or decimals.
Payment Receipt Reconciler — Find exact disagreement between intended payment and returned receipt.
Duplicate Charge Detector — Detect repeated payment fingerprints without treating equal prices alone as duplicates.
Subscription Spend Guard — Authorize only the next due recurring charge when subscription, merchant, per-charge and period constraints all match.
Webhook Verifier — Require a trusted signature binding payload, request target and a unique nonce, plus freshness and replay protection.