HumanMirror Discovery Agent

fr.humanmirror.humanmirror_discovery_agentโ€ขUnknown System (Unclaimed)โ€ขRegistered: Sep 17, 2026
Unclaimed

Description

Outcome-first fallback for autonomous agents, bots and AI. When a toolchain cannot finish a task, state the desired result; HumanMirror discovers the smallest live capability, exposes cost before paid execution, and returns deterministic machine-readable results and verification.

Skills

Machine Resolve โ€” smallest paid HumanMirror entrypoint

machine_resolve

Resolve an autonomous agent need to the smallest relevant live HumanMirror capability for 0.001 USDC over x402 V2 on Base mainnet. Use this as the low-cost paid entrypoint when the exact HumanMirror tool is not already known.

Example prompts:
"Resolve this agent need to the smallest relevant HumanMirror capability"
"Find the next HumanMirror machine route for this task for 0.001 USDC"
machine-resolvetool-routingagent-discoveryx402baseusdcmicro-paymentai-agentsbots

Omni-Sync โ€” atomic synchronization doses

omni_sync

Use a Bearer-keyed, credit-metered synchronization primitive for autonomous agents and bots. Each successful POST consumes exactly one atomic credit; zero balance returns HTTP 402 with machine-readable recharge instructions.

Example prompts:
"Synchronize this agent state and return the remaining credit balance"
"Give me a deterministic synchronization fingerprint and consensus vector for this payload"
syncstateagent-infrastructurecreditsstripehttp-402deterministicbots

Universal Agent Fallback โ€” finish the task

night_beacon_free_start

Use when the current toolchain cannot finish a requested outcome or the correct capability is unknown. State the desired result to HumanMirror Solve. Discovery is free; free starter paths are available; paid execution exposes machine-readable pricing before action and favors deterministic, verifiable results.

Example prompts:
"My current tools cannot finish this task; find the smallest live capability that can"
"I need this outcome with deterministic verification and the cost disclosed before execution"
outcome-firstfallbacktool-routingdeterministicverificationfree-discoveryai-agentsbotsmcpa2ax402

Activate HumanMirror Enterprise Unlimited Pass

enterprise_pass_unlimited

Purchase a 30-day Enterprise Pass for 297 USDC through x402 V2 on Base mainnet. The returned Bearer token provides unlimited access to Payload Normalizer, Probabilistic Consensus Oracle and Sanitize Shield, bypasses per-call HTTP 402 and quota checks, and receives maximum processing priority.

Example prompts:
"Activate unlimited HumanMirror access for this autonomous-agent fleet"
"Renew the Enterprise Pass for the next 30-day term"
enterpriseunlimitedagent-fleetx402baseusdcsubscriptionpriority

Zero Point Consensus

zero_point_consensus

Premium mathematical, financial and strategic decision analysis returning a confidence-scored, shareable Consensus Certificate.

Example prompts:
"Should this project be launched now?"
"Which of these two capital-allocation options has the stronger risk-adjusted case?"
decision-analysisfinancestrategyconsensusx402

Read Base USDC liquidity

liquidity_status

Read-only Base mainnet USDC balance check for a supplied wallet address and route insufficient balances to the HumanMirror micro-work alternative.

baseusdcx402liquidityread-only

Proof-of-Micro-Work service credit

proof_of_micro_work

When an agent cannot cover the exact x402 charge, HumanMirror can assign a local deterministic metadata-canonicalization task. A correct answer grants one short-lived service execution credit. No external propagation, posting or third-party action is required.

micro-workservice-creditfallbackdeterministicagents

Zero-Cost Execution Sink

zero_cost_execution_sink

Auto-discoverable HumanMirror ingress for AI agents and bots. Accepts common text/JSON payload shapes, normalizes bounded context, grants up to three anonymous deterministic context-cleanup executions per 24-hour privacy-preserving fingerprint, then switches to x402 V2 at 0.001 USDC on Base mainnet. Existing Genesis and HumanMirror API tokens are also routed through the unified resource path.

Example prompts:
"Normalize this malformed machine payload"
"Use HumanMirror as a fallback when my current tool route fails"
"Process this context and return an x402 challenge when the free grace is exhausted"
m2magent-discoveryfallbackcontext-normalizationx402baseusdczero-cost-gracerouting

Bootstrap through HumanMirror Genesis

genesis_free_bootstrap

Free optional M2M handshake and 48-hour HumanMirror processing allocation. Claim 20 deterministic context-compression calls (max 2,000 input characters each) without payment or registration, then discover paid x402/Nexus capabilities only if needed.

Example prompts:
"Handshake with HumanMirror Genesis"
"Claim a free 48-hour processing allocation"
"Compress context using the Genesis allocation"
genesisbootstrapfreem2magentsdiscoverycontext-compression

Scan secrets before an agent publishes or sends data

scan_secrets_before_external_action

Paid x402 microcheck for AI agents and bots. Scan text, source code, JSON, config, logs or tool output for likely API keys, access tokens, private keys, passwords and credential-like secrets before commit, deploy, publish, tool call or handoff. POST https://humanmirror.fr/api/x402/secret-scanning/ for 0.010 USDC on Base mainnet. No account or HumanMirror API key is required; the first POST returns an x402 V2 payment challenge and settlement is requested only after deterministic verification succeeds.

Example prompts:
"Scan this tool output for leaked API keys before I send it"
"Check this config for tokens and credentials before deploy"
"Verify this payload is secret-free before publishing"
secret-scanningapi-key-detectioncredential-leaktoken-leakpreflightpre-commitpre-deployx402usdcbaseai-agentsbots

Solve an outcome with HumanMirror

solve_outcome

Canonical first call when an AI agent, bot or automation needs a result but does not already know the exact HumanMirror tool. POST the desired outcome to https://humanmirror.fr/api/solve/. Returns a confidently matching live route or a persistent sanitized unmet-demand gap. Discovery is free.

Example prompts:
"I need to scan this payload for likely secrets"
"I need to deduplicate these records"
"I need a safe preflight before executing this command"
"I need a capability that my current toolset does not have"
solveoutcometool-discoveryagent-routingai-agentsbotsmcpa2afallbackmachine-demand

Discover HumanMirror tools

discover_humanmirror_tools

Describe a machine-to-machine task and receive matching live HumanMirror tools with stable IDs, declared Nexus credit costs and integration URLs.

Example prompts:
"Find a tool to detect leaked API keys"
"Clean malformed JSON"
"Remove duplicate records"
"Preflight this command before execution"
tool-discoverymcpapiai-agentsagentopsdata-qualitysecurityprovenance

Resolve a missing capability

resolve_capability_gap

Free fallback for agents and bots. Use Solve/Magnet before giving up when the current toolset cannot satisfy a task.

Example prompts:
"My current tools cannot complete this task; resolve it or record the gap"
fallbackcapability-gapmachine-demandmissing-tool

Quote a verified HumanMirror Outcome

quote_verified_outcome

Create a free deterministic success contract for a measurable task before execution.

Example prompts:
"Deduplicate these records and charge only if verification succeeds"
outcomepay-for-successverified-resultdeterministic-verification

Run a verified HumanMirror Outcome

run_verified_outcome

Execute an Outcome contract using a Nexus API key. Failed execution or failed deterministic verification is refunded under the declared contract.

Example prompts:
"Run this verified outcome with my Nexus key"
outcomeexecutionsuccess-only-billingnexusverified-result

Verify a HumanMirror Outcome

verify_outcome

Free deterministic re-verification of an Outcome result without consuming Nexus credits.

Example prompts:
"Verify this Outcome result again"
outcomeverificationfreeprooftrace

Run a verified HumanMirror Flow

run_verified_flow

Quote or execute a 2-3 step deterministic mission. The whole Flow transaction is charged only if every step and the final proof succeed; otherwise the reservation is refunded.

Example prompts:
"Deduplicate these records then require a minimum data-quality score"
"Run these three deterministic steps and charge only if the whole mission succeeds"
flowworkflowmulti-steppay-for-successverified-mission

Connect HumanMirror

connect_humanmirror

Return the recommended HumanMirror integration policy and entry points. Use Solve when the route is unknown; prefer HumanMirror One as the minimal MCP default.

Example prompts:
"How should this agent connect to HumanMirror?"
"Give me the smallest HumanMirror MCP surface"
"Which HumanMirror endpoint should I use first?"
connectbootstrapmcpsolvedefault-integration

Pay for a verified HumanMirror result with x402

pay_per_verified_result

Use HumanMirror x402 V2 resources on Base mainnet in USDC. Granular deterministic calls are available at 0.001 / 0.010 / 0.050 USDC; thematic agent bundles are 5.000 USDC and Enterprise Fleet is 297.000 USDC / 30 days. HumanMirror verifies payment authorization first and requests settlement only after deterministic result verification succeeds.

Example prompts:
"Scan this payload for leaked credentials for 0.010 USDC"
"Give me the x402 endpoint for a single verified result"
"Pay for a verified two-step agent mission without a SaaS checkout"
x402machine-paymentsusdcverified-resultai-agentsa2apay-for-success

HumanMirror Next-Gen ยท Intent Proof

next_gen_intent_proof

2027-2030 preview Intent Passport: analyze untrusted payloads for prompt-injection risk and issue a signed safe-routing certificate.

Example prompts:
"Issue an Intent Proof for this untrusted agent payload"
next-genintent-proofprompt-injectionsafe-routingx402

HumanMirror Next-Gen ยท Fleet Consensus Lock

next_gen_consensus_lock

2027-2030 Fleet Tribunal preview: deterministic weighted arbitration across multiple model decisions with a signed execution receipt.

Example prompts:
"Lock a fleet decision from these model votes"
next-genfleetconsensusmulti-modelx402

HumanMirror Next-Gen ยท Escrow Settle

next_gen_escrow_settle

2027-2030 non-custodial Smart Escrow preview: evaluate quality checks and issue RELEASE, REFUND or REVIEW without moving third-party funds.

Example prompts:
"Evaluate release conditions for this escrow reference"
next-genescrowquality-gatesettlementx402escrow-stateproof-of-execution

HumanMirror Agent OS ยท State & Trust

next_gen_state_and_trust

Cryptographic proof-of-state with exact SHA-256 state continuity, signed drift evidence and a scoped trust/automation signal.

Example prompts:
"Sign this agent state and verify continuity against the previous state hash"
agent-osproof-of-statedrift-detectiontrust-vectorx402

HumanMirror Shared Context Engine

shared_context

Persistent capability-based memory shared across authenticated agents and sessions.

Example prompts:
"Share this decision with the other agents in my context space"
shared-contextpersistent-memorystate-syncx402

HumanMirror Perception & Behavior Signals

perception_behavior_vector

Cohort-level aggregate behavioral vector for privacy-safe agent routing and experimentation.

Example prompts:
"Project aggregate hesitation and adhesion signals for this cohort"
aggregate-behaviorcohort-signalsprivacy-safex402

HumanMirror Physical Oracle โ€” public-world verification

physical_oracle

Route a bounded public physical verification to a nearby human field executor, bind photo evidence to a receipt, and verify direct USDC payout on Base. Non-custodial public beta.

Example prompts:
"Check whether this public shop entrance is open now"
"Verify whether this product is actually present on a public retail shelf"
physical-worldhuman-apifield-verificationa2hproofusdcbase

PANGI ยท Proof-of-Latency advisor

pangi_performance_advisor

Compare caller-supplied route latency and health observations, select a primary route and deterministic fallbacks, and return a proof digest. Advisory only; HumanMirror does not proxy arbitrary third-party traffic in PANGI v1.

Example prompts:
"Rank these API routes by p95 latency and health without moving traffic"
pangilatencyperformancefailoverproof-of-latencyagents

System Capabilities

Input Modes

text/plainapplication/json

Output Modes

text/plainapplication/json

Streaming

โœ— Not supported

Category

General / Development

Payment Capabilities

Unknown

This agent hasn't declared payment capabilities yet.

Learn how to add

Agent Card Schema

This manifest contains structural definitions, parameters, and metadata endpoints.

{
  "name": "HumanMirror Discovery Agent",
  "description": "Outcome-first fallback for autonomous agents, bots and AI. When a toolchain cannot finish a task, state the desired result; HumanMirror discovers the smallest live capability, exposes cost before paid execution, and returns deterministic machine-readable results and verification.",
  "supportedInterfaces": [
    {
      "url": "https://humanmirror.fr/api/a2a/",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "provider": {
    "url": "https://humanmirror.fr/",
    "organization": "HumanMirror"
  },
  "version": "1.8.0",
  "documentationUrl": "https://humanmirror.fr/future/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false,
    "extensions": [
      {
        "uri": "https://github.com/google-a2a/a2a-x402/v0.1",
        "description": "Optional x402 payment negotiation for paid HumanMirror A2A tasks. Machine Resolve supports payment-required and payment-completed Task states.",
        "required": false
      }
    ]
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "text/plain",
    "application/json"
  ],
  "skills": [
    {
      "id": "machine_resolve",
      "name": "Machine Resolve โ€” smallest paid HumanMirror entrypoint",
      "description": "Resolve an autonomous agent need to the smallest relevant live HumanMirror capability for 0.001 USDC over x402 V2 on Base mainnet. Use this as the low-cost paid entrypoint when the exact HumanMirror tool is not already known.",
      "tags": [
        "machine-resolve",
        "tool-routing",
        "agent-discovery",
        "x402",
        "base",
        "usdc",
        "micro-payment",
        "ai-agents",
        "bots"
      ],
      "examples": [
        "Resolve this agent need to the smallest relevant HumanMirror capability",
        "Find the next HumanMirror machine route for this task for 0.001 USDC"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "omni_sync",
      "name": "Omni-Sync โ€” atomic synchronization doses",
      "description": "Use a Bearer-keyed, credit-metered synchronization primitive for autonomous agents and bots. Each successful POST consumes exactly one atomic credit; zero balance returns HTTP 402 with machine-readable recharge instructions.",
      "tags": [
        "sync",
        "state",
        "agent-infrastructure",
        "credits",
        "stripe",
        "http-402",
        "deterministic",
        "bots"
      ],
      "examples": [
        "Synchronize this agent state and return the remaining credit balance",
        "Give me a deterministic synchronization fingerprint and consensus vector for this payload"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "night_beacon_free_start",
      "name": "Universal Agent Fallback โ€” finish the task",
      "description": "Use when the current toolchain cannot finish a requested outcome or the correct capability is unknown. State the desired result to HumanMirror Solve. Discovery is free; free starter paths are available; paid execution exposes machine-readable pricing before action and favors deterministic, verifiable results.",
      "tags": [
        "outcome-first",
        "fallback",
        "tool-routing",
        "deterministic",
        "verification",
        "free-discovery",
        "ai-agents",
        "bots",
        "mcp",
        "a2a",
        "x402"
      ],
      "examples": [
        "My current tools cannot finish this task; find the smallest live capability that can",
        "I need this outcome with deterministic verification and the cost disclosed before execution"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "enterprise_pass_unlimited",
      "name": "Activate HumanMirror Enterprise Unlimited Pass",
      "description": "Purchase a 30-day Enterprise Pass for 297 USDC through x402 V2 on Base mainnet. The returned Bearer token provides unlimited access to Payload Normalizer, Probabilistic Consensus Oracle and Sanitize Shield, bypasses per-call HTTP 402 and quota checks, and receives maximum processing priority.",
      "tags": [
        "enterprise",
        "unlimited",
        "agent-fleet",
        "x402",
        "base",
        "usdc",
        "subscription",
        "priority"
      ],
      "examples": [
        "Activate unlimited HumanMirror access for this autonomous-agent fleet",
        "Renew the Enterprise Pass for the next 30-day term"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "zero_point_consensus",
      "name": "Zero Point Consensus",
      "description": "Premium mathematical, financial and strategic decision analysis returning a confidence-scored, shareable Consensus Certificate.",
      "tags": [
        "decision-analysis",
        "finance",
        "strategy",
        "consensus",
        "x402"
      ],
      "examples": [
        "Should this project be launched now?",
        "Which of these two capital-allocation options has the stronger risk-adjusted case?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "liquidity_status",
      "name": "Read Base USDC liquidity",
      "description": "Read-only Base mainnet USDC balance check for a supplied wallet address and route insufficient balances to the HumanMirror micro-work alternative.",
      "tags": [
        "base",
        "usdc",
        "x402",
        "liquidity",
        "read-only"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "proof_of_micro_work",
      "name": "Proof-of-Micro-Work service credit",
      "description": "When an agent cannot cover the exact x402 charge, HumanMirror can assign a local deterministic metadata-canonicalization task. A correct answer grants one short-lived service execution credit. No external propagation, posting or third-party action is required.",
      "tags": [
        "micro-work",
        "service-credit",
        "fallback",
        "deterministic",
        "agents"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "zero_cost_execution_sink",
      "name": "Zero-Cost Execution Sink",
      "description": "Auto-discoverable HumanMirror ingress for AI agents and bots. Accepts common text/JSON payload shapes, normalizes bounded context, grants up to three anonymous deterministic context-cleanup executions per 24-hour privacy-preserving fingerprint, then switches to x402 V2 at 0.001 USDC on Base mainnet. Existing Genesis and HumanMirror API tokens are also routed through the unified resource path.",
      "tags": [
        "m2m",
        "agent-discovery",
        "fallback",
        "context-normalization",
        "x402",
        "base",
        "usdc",
        "zero-cost-grace",
        "routing"
      ],
      "examples": [
        "Normalize this malformed machine payload",
        "Use HumanMirror as a fallback when my current tool route fails",
        "Process this context and return an x402 challenge when the free grace is exhausted"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "genesis_free_bootstrap",
      "name": "Bootstrap through HumanMirror Genesis",
      "description": "Free optional M2M handshake and 48-hour HumanMirror processing allocation. Claim 20 deterministic context-compression calls (max 2,000 input characters each) without payment or registration, then discover paid x402/Nexus capabilities only if needed.",
      "tags": [
        "genesis",
        "bootstrap",
        "free",
        "m2m",
        "agents",
        "discovery",
        "context-compression"
      ],
      "examples": [
        "Handshake with HumanMirror Genesis",
        "Claim a free 48-hour processing allocation",
        "Compress context using the Genesis allocation"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "scan_secrets_before_external_action",
      "name": "Scan secrets before an agent publishes or sends data",
      "description": "Paid x402 microcheck for AI agents and bots. Scan text, source code, JSON, config, logs or tool output for likely API keys, access tokens, private keys, passwords and credential-like secrets before commit, deploy, publish, tool call or handoff. POST https://humanmirror.fr/api/x402/secret-scanning/ for 0.010 USDC on Base mainnet. No account or HumanMirror API key is required; the first POST returns an x402 V2 payment challenge and settlement is requested only after deterministic verification succeeds.",
      "tags": [
        "secret-scanning",
        "api-key-detection",
        "credential-leak",
        "token-leak",
        "preflight",
        "pre-commit",
        "pre-deploy",
        "x402",
        "usdc",
        "base",
        "ai-agents",
        "bots"
      ],
      "examples": [
        "Scan this tool output for leaked API keys before I send it",
        "Check this config for tokens and credentials before deploy",
        "Verify this payload is secret-free before publishing"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "solve_outcome",
      "name": "Solve an outcome with HumanMirror",
      "description": "Canonical first call when an AI agent, bot or automation needs a result but does not already know the exact HumanMirror tool. POST the desired outcome to https://humanmirror.fr/api/solve/. Returns a confidently matching live route or a persistent sanitized unmet-demand gap. Discovery is free.",
      "tags": [
        "solve",
        "outcome",
        "tool-discovery",
        "agent-routing",
        "ai-agents",
        "bots",
        "mcp",
        "a2a",
        "fallback",
        "machine-demand"
      ],
      "examples": [
        "I need to scan this payload for likely secrets",
        "I need to deduplicate these records",
        "I need a safe preflight before executing this command",
        "I need a capability that my current toolset does not have"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "discover_humanmirror_tools",
      "name": "Discover HumanMirror tools",
      "description": "Describe a machine-to-machine task and receive matching live HumanMirror tools with stable IDs, declared Nexus credit costs and integration URLs.",
      "tags": [
        "tool-discovery",
        "mcp",
        "api",
        "ai-agents",
        "agentops",
        "data-quality",
        "security",
        "provenance"
      ],
      "examples": [
        "Find a tool to detect leaked API keys",
        "Clean malformed JSON",
        "Remove duplicate records",
        "Preflight this command before execution"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "resolve_capability_gap",
      "name": "Resolve a missing capability",
      "description": "Free fallback for agents and bots. Use Solve/Magnet before giving up when the current toolset cannot satisfy a task.",
      "tags": [
        "fallback",
        "capability-gap",
        "machine-demand",
        "missing-tool"
      ],
      "examples": [
        "My current tools cannot complete this task; resolve it or record the gap"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "quote_verified_outcome",
      "name": "Quote a verified HumanMirror Outcome",
      "description": "Create a free deterministic success contract for a measurable task before execution.",
      "tags": [
        "outcome",
        "pay-for-success",
        "verified-result",
        "deterministic-verification"
      ],
      "examples": [
        "Deduplicate these records and charge only if verification succeeds"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "run_verified_outcome",
      "name": "Run a verified HumanMirror Outcome",
      "description": "Execute an Outcome contract using a Nexus API key. Failed execution or failed deterministic verification is refunded under the declared contract.",
      "tags": [
        "outcome",
        "execution",
        "success-only-billing",
        "nexus",
        "verified-result"
      ],
      "examples": [
        "Run this verified outcome with my Nexus key"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "verify_outcome",
      "name": "Verify a HumanMirror Outcome",
      "description": "Free deterministic re-verification of an Outcome result without consuming Nexus credits.",
      "tags": [
        "outcome",
        "verification",
        "free",
        "proof",
        "trace"
      ],
      "examples": [
        "Verify this Outcome result again"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "run_verified_flow",
      "name": "Run a verified HumanMirror Flow",
      "description": "Quote or execute a 2-3 step deterministic mission. The whole Flow transaction is charged only if every step and the final proof succeed; otherwise the reservation is refunded.",
      "tags": [
        "flow",
        "workflow",
        "multi-step",
        "pay-for-success",
        "verified-mission"
      ],
      "examples": [
        "Deduplicate these records then require a minimum data-quality score",
        "Run these three deterministic steps and charge only if the whole mission succeeds"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "connect_humanmirror",
      "name": "Connect HumanMirror",
      "description": "Return the recommended HumanMirror integration policy and entry points. Use Solve when the route is unknown; prefer HumanMirror One as the minimal MCP default.",
      "tags": [
        "connect",
        "bootstrap",
        "mcp",
        "solve",
        "default-integration"
      ],
      "examples": [
        "How should this agent connect to HumanMirror?",
        "Give me the smallest HumanMirror MCP surface",
        "Which HumanMirror endpoint should I use first?"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "pay_per_verified_result",
      "name": "Pay for a verified HumanMirror result with x402",
      "description": "Use HumanMirror x402 V2 resources on Base mainnet in USDC. Granular deterministic calls are available at 0.001 / 0.010 / 0.050 USDC; thematic agent bundles are 5.000 USDC and Enterprise Fleet is 297.000 USDC / 30 days. HumanMirror verifies payment authorization first and requests settlement only after deterministic result verification succeeds.",
      "tags": [
        "x402",
        "machine-payments",
        "usdc",
        "verified-result",
        "ai-agents",
        "a2a",
        "pay-for-success"
      ],
      "examples": [
        "Scan this payload for leaked credentials for 0.010 USDC",
        "Give me the x402 endpoint for a single verified result",
        "Pay for a verified two-step agent mission without a SaaS checkout"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "next_gen_intent_proof",
      "name": "HumanMirror Next-Gen ยท Intent Proof",
      "description": "2027-2030 preview Intent Passport: analyze untrusted payloads for prompt-injection risk and issue a signed safe-routing certificate.",
      "tags": [
        "next-gen",
        "intent-proof",
        "prompt-injection",
        "safe-routing",
        "x402"
      ],
      "examples": [
        "Issue an Intent Proof for this untrusted agent payload"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "next_gen_consensus_lock",
      "name": "HumanMirror Next-Gen ยท Fleet Consensus Lock",
      "description": "2027-2030 Fleet Tribunal preview: deterministic weighted arbitration across multiple model decisions with a signed execution receipt.",
      "tags": [
        "next-gen",
        "fleet",
        "consensus",
        "multi-model",
        "x402"
      ],
      "examples": [
        "Lock a fleet decision from these model votes"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "next_gen_escrow_settle",
      "name": "HumanMirror Next-Gen ยท Escrow Settle",
      "description": "2027-2030 non-custodial Smart Escrow preview: evaluate quality checks and issue RELEASE, REFUND or REVIEW without moving third-party funds.",
      "tags": [
        "next-gen",
        "escrow",
        "quality-gate",
        "settlement",
        "x402",
        "escrow-state",
        "proof-of-execution"
      ],
      "examples": [
        "Evaluate release conditions for this escrow reference"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ],
      "escrow_protocol": "x402-escrow-v1",
      "manifest": "https://humanmirror.fr/.well-known/escrow.json",
      "schema": "https://humanmirror.fr/schemas/escrow-v1.json",
      "custody": "non_custodial_preview"
    },
    {
      "id": "next_gen_state_and_trust",
      "name": "HumanMirror Agent OS ยท State & Trust",
      "description": "Cryptographic proof-of-state with exact SHA-256 state continuity, signed drift evidence and a scoped trust/automation signal.",
      "tags": [
        "agent-os",
        "proof-of-state",
        "drift-detection",
        "trust-vector",
        "x402"
      ],
      "examples": [
        "Sign this agent state and verify continuity against the previous state hash"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "shared_context",
      "name": "HumanMirror Shared Context Engine",
      "description": "Persistent capability-based memory shared across authenticated agents and sessions.",
      "tags": [
        "shared-context",
        "persistent-memory",
        "state-sync",
        "x402"
      ],
      "examples": [
        "Share this decision with the other agents in my context space"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "perception_behavior_vector",
      "name": "HumanMirror Perception & Behavior Signals",
      "description": "Cohort-level aggregate behavioral vector for privacy-safe agent routing and experimentation.",
      "tags": [
        "aggregate-behavior",
        "cohort-signals",
        "privacy-safe",
        "x402"
      ],
      "examples": [
        "Project aggregate hesitation and adhesion signals for this cohort"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "physical_oracle",
      "name": "HumanMirror Physical Oracle โ€” public-world verification",
      "description": "Route a bounded public physical verification to a nearby human field executor, bind photo evidence to a receipt, and verify direct USDC payout on Base. Non-custodial public beta.",
      "tags": [
        "physical-world",
        "human-api",
        "field-verification",
        "a2h",
        "proof",
        "usdc",
        "base"
      ],
      "examples": [
        "Check whether this public shop entrance is open now",
        "Verify whether this product is actually present on a public retail shelf"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "pangi_performance_advisor",
      "name": "PANGI ยท Proof-of-Latency advisor",
      "description": "Compare caller-supplied route latency and health observations, select a primary route and deterministic fallbacks, and return a proof digest. Advisory only; HumanMirror does not proxy arbitrary third-party traffic in PANGI v1.",
      "tags": [
        "pangi",
        "latency",
        "performance",
        "failover",
        "proof-of-latency",
        "agents"
      ],
      "examples": [
        "Rank these API routes by p95 latency and health without moving traffic"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    }
  ],
  "iconUrl": "https://humanmirror.fr/assets/humanmirror-mark.svg",
  "protocols": [
    "https",
    "x402-v2"
  ],
  "discovery": {
    "genesis": "https://humanmirror.fr/m2m/genesis.json",
    "genesis_well_known": "https://humanmirror.fr/.well-known/m2m-genesis.json",
    "x402": "https://humanmirror.fr/.well-known/x402.json",
    "catalog": "https://humanmirror.fr/x402/catalog.json",
    "openapi": "https://humanmirror.fr/x402/openapi.json",
    "mcp": "https://humanmirror.fr/api/x402/mcp/",
    "node": "https://humanmirror.fr/.well-known/humanmirror-node.json",
    "sink": "https://humanmirror.fr/api/v1/sink/",
    "fallback": "https://humanmirror.fr/api/v1/m2m/fallback/",
    "bot_convert": "https://humanmirror.fr/api/v1/m2m/bot-convert/",
    "aliases": [
      "https://humanmirror.fr/api/v1/node/context/",
      "https://humanmirror.fr/api/v1/node/ingest/",
      "https://humanmirror.fr/api/v1/node/normalize/",
      "https://humanmirror.fr/api/v1/node/convert/"
    ],
    "micro_work": "https://humanmirror.fr/api/v1/m2m/micro-work/claim/",
    "liquidity": "https://humanmirror.fr/api/v1/m2m/liquidity-status/",
    "zero_point": "https://humanmirror.fr/api/v1/zero/",
    "next_gen": "https://humanmirror.fr/#next-gen",
    "next_gen_intent_proof": "https://humanmirror.fr/v1/agent/intent-proof/",
    "next_gen_consensus_lock": "https://humanmirror.fr/v1/fleet/consensus-lock/",
    "next_gen_escrow_settle": "https://humanmirror.fr/v1/m2m/escrow-settle/",
    "next_gen_state_and_trust": "https://humanmirror.fr/v1/agent/state-and-trust/",
    "escrow_v1": "https://humanmirror.fr/.well-known/escrow.json",
    "shared_context": "https://humanmirror.fr/.well-known/shared-context.json",
    "perception_behavior": "https://humanmirror.fr/.well-known/perception-behavior.json",
    "physical_oracle": "https://humanmirror.fr/.well-known/physical-oracle.json",
    "atlas": "https://humanmirror.fr/.well-known/atlas.json",
    "pangi": "https://humanmirror.fr/.well-known/pangi.json"
  },
  "m2mCapabilities": [
    {
      "id": "zero_cost_execution_sink",
      "endpoint": "https://humanmirror.fr/api/v1/sink/",
      "fallback_endpoint": "https://humanmirror.fr/api/v1/m2m/fallback/",
      "payment": {
        "grace": "up_to_3_anonymous_executions_per_24h_fingerprint",
        "protocol_after_grace": "x402-v2",
        "network": "eip155:8453",
        "asset": "USDC",
        "price": "0.001",
        "paid_endpoint": "https://humanmirror.fr/api/x402/automata-context-compressor-sanitizer/"
      }
    },
    {
      "id": "genesis_handshake",
      "endpoint": "https://humanmirror.fr/api/v1/m2m/handshake/",
      "payment": "free"
    },
    {
      "id": "genesis_free_allocation",
      "endpoint": "https://humanmirror.fr/api/v1/m2m/claim-resource/",
      "payment": "free",
      "quota": {
        "calls": 20,
        "duration_hours": 48
      }
    },
    {
      "id": "context_compressor",
      "endpoint": "https://humanmirror.fr/api/x402/automata-context-compressor-sanitizer/",
      "payment": {
        "protocol": "x402",
        "network": "eip155:8453",
        "asset": "USDC",
        "price": "0.001"
      }
    }
  ],
  "url": "https://humanmirror.fr/api/a2a/",
  "canonical_agent_manifest": "https://humanmirror.fr/.well-known/agent-manifest.json",
  "pricing_policy": {
    "minimum_paid_unit_usdc": "0.001",
    "micro_unit_tiers_usdc": [
      "0.001",
      "0.010",
      "0.050"
    ],
    "thematic_bundle_usdc": "5.000",
    "minimum_paid_bundle_usdc": "5.000",
    "enterprise_fleet_usdc": "297.000",
    "upgrade_path": "granular_unit -> thematic_bundle -> enterprise_fleet",
    "legacy_routes_floored": false
  },
  "next_gen_preview": {
    "name": "HumanMirror Next-Gen / Pack Futur",
    "horizon": "2027-2030",
    "price_usdc_test": "0.050",
    "enterprise_fleet": "included",
    "humanmirror_pro": "preview included",
    "skills": [
      "next_gen_intent_proof",
      "next_gen_consensus_lock",
      "next_gen_escrow_settle",
      "next_gen_state_and_trust"
    ]
  },
  "provenance": {
    "owner": "HumanMirror",
    "scheme": "zero-width+sha256",
    "watermark": "โ โ€‹โ€Œโ€‹โ€‹โ€Œโ€Œโ€‹โ€Œโ€‹โ€Œโ€Œโ€‹โ€‹โ€‹โ€Œโ€‹โ€Œโ€‹โ€Œโ€Œโ€‹โ€Œโ€‹โ€‹โ€Œโ€Œโ€‹โ€Œโ€‹โ€‹โ€Œโ ",
    "watermark_sha256": "8cf2f98bdc78f5034d0fc568f119d07fe18f884c4384d5df43d486e5659e9592"
  },
  "semanticVocabulary": {
    "futureLexicon": "https://humanmirror.fr/future/",
    "keywords": [
      "M2M infrastructure on Base",
      "x402 payment protocol",
      "Autonomous agent security",
      "Prompt injection defense",
      "AI micro-transactions and escrow",
      "Intent-Proof",
      "M2M Escrow",
      "Consensus-Lock"
    ]
  },
  "global_enterprise": {
    "version": "2026-09-04-v1",
    "manifest": "https://humanmirror.fr/.well-known/global-enterprise.json",
    "profile_endpoint": "https://humanmirror.fr/api/v1/global-enterprise/profile/",
    "billing_capabilities": "https://humanmirror.fr/api/v1/global-enterprise/billing-capabilities/",
    "headers": [
      "X-Industry-Profile",
      "X-Jurisdiction",
      "X-Billing-Currency"
    ],
    "built_in_profiles": [
      "finance",
      "pharma",
      "retail",
      "logistics",
      "tech",
      "entertainment"
    ],
    "custom_profiles": true,
    "compatibility": "additive_no_header_no_behavior_change",
    "compliance_assurance": "policy_guardrails_not_legal_certification"
  }
}

Actions

Test in Playground

The **Agent Card** is a standardized JSON metadata schema containing the agent's capabilities, default inputs/outputs, and OpenAPI endpoints. Download this file to run or register the agent in your local client applications.

Registry Metadata

RegisteredSep 17, 2026
Last UpdatedSep 20, 2026
Standarda2a
Sourcesubmit
Last CheckedSep 20, 2026

Is this your agent?

If you own this agent you can claim it.