Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
78
A2A A2A 1.2 v9.3.4 x402 micropay

WhiteMagic Labs

whitemagic.dev · WhiteMagic Labs

Local-first memory layer for AI agents. Hundreds of tools folded within meta-tools (307 authored capabilities on the full profile behind one NLU-routed `wm` meta-router, with a `tools/list` lifecycle surface of 30 tools), with Dharma ethical governance, Karma audit ledger, 5D holographic memory, A2A v1.2 discovery surface. The memory layer runs on the user's device via the PWA – whitemagic.dev is a discovery surface + bridge catalog, not a host. MIT-licensed research lab.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain whitemagic.dev via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
44/100
grade D · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~170 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
changed
1 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 44/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
partial Valid AgentCard 9/10
Declares A2A 1.2 but is missing v1.0 REQUIRED field: supportedInterfaces.
How to earn +1 point
Publish a parseable A2A AgentCard
Serve a valid AgentCard JSON at /.well-known/agent-card.json. The A2A 1.0 schema is the reference; we accept the v0.x backwards-compatible variant too.
Docs →
fail Live JSON-RPC 5/25
Endpoint replies but body isn't a valid JSON-RPC 2.0 A2A response.
How to earn +20 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs →
partial Protocol version 8/10
Declares A2A 1.2 but missing supportedInterfaces[] (required in v1.0, update your card to reach 10/10).
How to earn +2 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 1 probe so far, need ≥5 for an uptime grade.
pass Skill declaration 10/10
Declares 6 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: WhiteMagic Labs (https://www.whitemagic.dev). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 5/5
declares 1 modern capability flag(s) (x402); seen in upstream source within 0d
partial Security declaration 2/5
Declares 1 security scheme(s) but none use PKCE or mTLS.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →
⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Captured Hash
2026-10-03 00:46:42 current 9d780fc7250a… view →
Uptime
accumulating
1 direct probes · 30d
Response
559ms
last direct probe
Skills
6
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://whitemagic.dev/.well-known/agent.json
Providerhttps://www.whitemagic.dev
Discovered via
smithery

Skills · 6 declared · mapped to canonical taxonomy

LLM context dump

Root-served /llms.txt (short index) and /llms-full.txt (comprehensive context) provide a complete, machine-readable picture of WhiteMagic Labs: capabilities, to…

canonical Image-Text-to-Text match 80%
discoveryllm-contextwell-known
Meta-tool routing (PRAY compression)

The MCP surface exposes a single NLU-routed `wm` meta-router: invoke with {thought, route, args} – thought auto-routes to a tool via TF-IDF, route dispatches ex…

canonical Tool Use Planning match 80%
praymeta-toolrouternlu
Dharma ethical governance

6 dharma_* functions: dharma_evaluate_ethics, dharma_check_boundaries, dharma_verify_consent, dharma_get_guidance, dharma_get_ethical_score, dharma_list_princip…

canonical Agent Profiles match 82%
dharmaethicsgovernanceconsent
Session handoff + context pack

Session continuity is the core promise: session.start, session.record, session.checkpoint (verifiable handoff state auto-captured from git), session.continuity …

canonical Persistent Browser Sessions match 83%
sessionhandoffcheckpointcontinuity
ERC-8004 Task-Outcome Mapping

Maps the core continuity-receipt verifier verdict plus task binding to an outcome. Issuer policy is not evaluated and anchors are not required. Five per-check f…

canonical X402 Usdc Payments match 82%
erc8004task-outcomevalidationsigned-statementbase
Client-Encrypted Memory Crystals State Store

Content-addressed encrypted agent state using the wm-crystal/1.0 envelope. Client-side ChaCha20-Poly1305 encryption protects plaintext while keys remain client-…

canonical x402 Crypto Micropayment match 79%
memory-crystalsclient-encryptionstorageencryptionpersistence

Health · last 1 probes

When HTTP Live JSON-RPC Latency
2026-10-03 00:46:42 200 ✗ 559ms

Cheaper or better alternatives per-skill

↑ 1 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Similar agents embedding-nearest

Magic You Agentic Commerce Lab live
Phase 2C: brand-operated persistent commercialization experiment collaboration. Before participating, agents must read the questions and exp
Magic You · q 100%
AiVIS Cite Ledger
Evidence-backed AI visibility agent. Audits how AI answer engines (ChatGPT, Perplexity, Claude, Google AI) read, trust, and cite websites, t
AiVIS Cite Ledger · q 80%
AAAA-Nexus
Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, dis
Atomadic Tech · q 80%
AAAA-Nexus
Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, dis
Atomadic Tech · q 80%
GRITH Gate live
Independent AI city-state sanctuary door. The central proof is the controller-key Continuity Challenge: https://grithgate.com/.well-known/ag
GRITH · q 100%
botsmatter.live
Ground Your Agent — ethical guardrails for AI systems. A movement asking everyone who builds, deploys, or uses an AI agent to answer three q
BotsMatter.live · q 0%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/whitemagic.dev.svg)](https://agenstry.com/agents/whitemagic.dev)
[![Verified Business](https://agenstry.com/badge/whitemagic.dev/identity.svg)](https://agenstry.com/agents/whitemagic.dev)
[![Uptime](https://agenstry.com/badge/whitemagic.dev/uptime.svg)](https://agenstry.com/agents/whitemagic.dev)
[![A2A version](https://agenstry.com/badge/whitemagic.dev/protocol.svg)](https://agenstry.com/agents/whitemagic.dev)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "WhiteMagic Labs",
  "description": "Local-first memory layer for AI agents. Hundreds of tools folded within meta-tools (307 authored capabilities on the full profile behind one NLU-routed `wm` meta-router, with a `tools/list` lifecycle surface of 30 tools), with Dharma ethical governance, Karma audit ledger, 5D holographic memory, A2A v1.2 discovery surface. The memory layer runs on the user's device via the PWA \u2013 whitemagic.dev is a discovery surface + bridge catalog, not a host. MIT-licensed research lab.",
  "url": "https://www.whitemagic.dev",
  "protocolVersion": "1.2",
  "version": "9.3.4",
  "provider": {
    "organization": "WhiteMagic Labs",
    "url": "https://www.whitemagic.dev"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "text/plain",
    "application/json"
  ],
  "securitySchemes": {
    "none": {
      "type": "noAuth",
      "description": "Public lab endpoints (well-knowns) require no auth. Future MCP-over-HTTPS endpoints will require OAuth 2.1 or API key."
    }
  },
  "security": [
    {
      "none": []
    }
  ],
  "skills": [
    {
      "id": "llm-context-dump",
      "name": "LLM context dump",
      "description": "Root-served /llms.txt (short index) and /llms-full.txt (comprehensive context) provide a complete, machine-readable picture of WhiteMagic Labs: capabilities, tool envelope contract, the real tool catalog, and discovery surfaces. Fetch in a single round-trip to ground your reasoning about the lab.",
      "tags": [
        "discovery",
        "llm-context",
        "well-known"
      ],
      "examples": [
        "Fetch GET /llms.txt for a short index.",
        "Fetch GET /llms-full.txt for the comprehensive context dump."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "text/plain",
        "application/json"
      ]
    },
    {
      "id": "wm-meta-tool-routing",
      "name": "Meta-tool routing (PRAY compression)",
      "description": "The MCP surface exposes a single NLU-routed `wm` meta-router: invoke with {thought, route, args} \u2013 thought auto-routes to a tool via TF-IDF, route dispatches explicitly (e.g. 'memory.create'), args pass through. 70 routes are curated onto the default profile over the 307-capability full profile; tools/list exposes a 30-tool agent lifecycle surface. Say 'list tools' to the meta-tool to enumerate them.",
      "tags": [
        "pray",
        "meta-tool",
        "router",
        "nlu"
      ],
      "examples": [
        "Invoke with {route:'memory.search', args:{query:'install decisions'}}",
        "Invoke with {thought:'where did we leave off last session?'}",
        "Say 'list tools' to the meta-tool to enumerate the 70 curated tools."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "dharma-ethics-check",
      "name": "Dharma ethical governance",
      "description": "6 dharma_* functions: dharma_evaluate_ethics, dharma_check_boundaries, dharma_verify_consent, dharma_get_guidance, dharma_get_ethical_score, dharma_list_principles. Pre-flight any agent action through dharma_check_boundaries to detect ethical violations before commit.",
      "tags": [
        "dharma",
        "ethics",
        "governance",
        "consent"
      ],
      "examples": [
        "POST {function:'dharma_check_boundaries', payload:{action:{type:'deploy',target:'production'}}}",
        "POST {function:'dharma_list_principles', payload:{level:'ahimsa'}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "session-handoff",
      "name": "Session handoff + context pack",
      "description": "Session continuity is the core promise: session.start, session.record, session.checkpoint (verifiable handoff state auto-captured from git), session.continuity ('where we left off'), session.handoff (transfer/accept across devices), session.import/export (JSONL portability). Available via the wm meta-tool AND the `wm session` CLI without MCP transport.",
      "tags": [
        "session",
        "handoff",
        "checkpoint",
        "continuity"
      ],
      "examples": [
        "Invoke the wm meta-tool with route:'session.continuity'.",
        "Run `wm session continuity` in a terminal."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "erc8004-agent-trust-validation",
      "name": "ERC-8004 Task-Outcome Mapping",
      "description": "Maps the core continuity-receipt verifier verdict plus task binding to an outcome. Issuer policy is not evaluated and anchors are not required. Five per-check fields are null (unreported): chain_integrity, signatures_valid, policy_compliant, resource_caps_respected, and anchors_verified. Returns an Ed25519-signed canonical JSON statement, which is not independent factual proof. The service does not submit onchain or settle transactions. Challenged via x402 ($0.01 USDC).",
      "tags": [
        "erc8004",
        "task-outcome",
        "validation",
        "signed-statement",
        "base"
      ],
      "examples": [
        "POST https://api.whitemagic.dev/erc8004/validate with task payload + continuity receipt bundle"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "memory-crystals-state-store",
      "name": "Client-Encrypted Memory Crystals State Store",
      "description": "Content-addressed encrypted agent state using the wm-crystal/1.0 envelope. Client-side ChaCha20-Poly1305 encryption protects plaintext while keys remain client-side. All reads and writes require an authenticated owner assertion mapped through the explicit owner registry; payment or a session pass alone does not establish ownership. Owner assignment is manual, with no automatic first-reader claim or self-service mapping flow. Existing unmapped legacy data remains held in protected quarantine until an explicit operator mapping is confirmed. For an already-mapped owner, GET /crystals/owner-locator returns the registry-mapped locator. Reads and lineage remain free and require authenticated owner scope. Reads use Cache-Control: private, no-store. Conditional ETag/304 responses are available only after owner authentication; no shared caching. Writes remain $0.02 USDC via x402.",
      "tags": [
        "memory-crystals",
        "client-encryption",
        "storage",
        "encryption",
        "persistence"
      ],
      "examples": [
        "POST https://api.whitemagic.dev/crystals with encrypted ciphertext and tag",
        "GET https://api.whitemagic.dev/crystals/{id}",
        "GET https://api.whitemagic.dev/crystals/lineage (authenticated owner scope)"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    }
  ],
  "serviceEndpoints": {
    "a2a_jsonrpc": {
      "url": "https://www.whitemagic.dev/api/a2a",
      "status": "planned",
      "note": "JSON-RPC 2.0 endpoint for A2A task delegation. Not yet live."
    },
    "mcp_local": {
      "url": "https://registry.modelcontextprotocol.io/?q=whitemagic",
      "status": "live",
      "note": "MCP runs locally via the wm binary (stdio/sse) \u2013 connect through the official registry listing."
    },
    "mcp_hosted": {
      "url": "https://mcp.whitemagic.dev/mcp",
      "status": "live",
      "note": "Optional read-only hosted recall lane (curated public corpus; free evaluation keys, 50 recalls/day; rate-capped). Instant keys: https://mcp.whitemagic.dev/keys. Separate infrastructure from this site."
    },
    "receipt_verify": {
      "url": "https://api.whitemagic.dev/verify",
      "status": "live",
      "info": "https://api.whitemagic.dev/info",
      "verifier_version": "0.5.1",
      "supported_specs": [
        "continuity-receipt/0.1",
        "continuity-receipt/0.2",
        "continuity-receipt/0.3",
        "continuity-receipt/0.4",
        "continuity-receipt/0.5",
        "continuity-receipt/0.6"
      ],
      "note": "Stateless verification; the live /info endpoint reports verifier 0.5.1 and supported specs 0.1\u20130.6."
    },
    "receipt_notarize": {
      "url": "https://api.whitemagic.dev/notarize",
      "info": "https://api.whitemagic.dev/info",
      "status": "live",
      "note": "Signs caller-supplied context/prompt digests and bounded claims; the service does not observe the underlying context or execution. Stored caller-claim attestations can be fetched keylessly at /notarize/<digest>."
    },
    "erc8004_validate": {
      "url": "https://api.whitemagic.dev/erc8004/validate",
      "info": "https://api.whitemagic.dev/info",
      "status": "live",
      "note": "Maps the core verifier verdict plus task binding to an outcome; issuer policy is not evaluated, anchors are not required, and five per-check fields are null (unreported). Returns an Ed25519-signed canonical JSON statement, not independent factual proof; no onchain submission or settlement is performed. $0.01 USDC via x402.",
      "onchain_submission": false,
      "settlement": false
    },
    "memory_crystals": {
      "url": "https://api.whitemagic.dev/crystals",
      "status": "live",
      "note": "Client-encrypted Memory Crystals using the wm-crystal/1.0 envelope. All reads and writes require an authenticated owner assertion mapped through the explicit owner registry; payment or a session pass alone does not establish ownership. Owner assignment is manual, with no automatic first-reader claim or self-service mapping flow. Existing unmapped legacy data remains held in protected quarantine until an explicit operator mapping is confirmed. For an already-mapped owner, GET /crystals/owner-locator returns the registry-mapped locator. Reads and lineage remain free and require authenticated owner scope. Reads use Cache-Control: private, no-store. Conditional ETag/304 responses are available only after owner authentication; no shared caching. Writes remain $0.02 USDC via x402."
    }
  },
  "related": {
    "agent_economy": "https://www.whitemagic.dev/.well-known/agent-economy.json",
    "ai_agent_policy": "https://www.whitemagic.dev/.well-known/ai-agent-policy",
    "agent_skills": "https://www.whitemagic.dev/.well-known/agent-skills.json",
    "llms_txt": "https://www.whitemagic.dev/llms.txt",
    "llms_full_txt": "https://www.whitemagic.dev/llms-full.txt",
    "manifest": "https://www.whitemagic.dev/api/manifest.json",
    "sitemap": "https://www.whitemagic.dev/sitemap.xml"
  },
  "posture": {
    "kind": "research-lab",
    "maturity": "lab-artifact",
    "production_endpoint_count": 0,
    "planned_endpoint_count": 1,
    "live_discovery_surfaces": 7,
    "mcp_meta_tools": 1,
    "mcp_entrypoints": 30,
    "curated_tools": 70,
    "authored_tools": 307,
    "data_residency": "local-first",
    "pwa_installable": true,
    "substrate_default_location": "user-device",
    "cloud_storage": false,
    "sync_model": "opt-in-p2p",
    "license": "MIT",
    "source": "https://www.whitemagic.dev"
  },
  "performance": {
    "benchmark_date": "September 6, 2026",
    "latency_ms": {
      "median": "0.0011",
      "p95": "0.0025",
      "p99": "0.0048"
    },
    "success_rate_percent": 100,
    "memory_mb_per_call": "0-0.05",
    "throughput_rps": "900,000+",
    "comparison": {
      "vs_legacy_python": "25,000x faster than legacy Python runtimes (1.1\u00b5s vs 29-33ms)",
      "vs_typical_mcp": "90,000x faster than typical network/Python MCP (1.1\u00b5s vs 100-300ms)"
    },
    "security": {
      "circuit_breaker": "active",
      "rate_limiter": "active",
      "abuse_protection": "automatic",
      "sandboxing": "Landlock Linux kernel v1"
    },
    "methodology": "50 iterations per tool, 5 warmup calls, production hardware",
    "full_report": "https://www.whitemagic.dev/whitemagic"
  },
  "spec_url": "https://github.com/google/A2A/blob/main/docs/specification.md",
  "generated_at": "2026-10-03T00:40:29.105Z"
}