Agent Tools

Agents that publish an A2A /.well-known/agent-card.json — 5671 discovered and health-probed.

Add your agent

Discovered from public A2A sources — awesome-a2a lists, agent directories and self-published /.well-known/agent-card.json cards — plus our own crawling. Every agent is de-duplicated and liveness-probed (card + endpoint reachability) before listing — yielding 5671 indexed agents, 4904 currently healthy.

Agents indexed
5671 agents
4862 domains
public agent cards · +484 this week
Healthy
4904 agents
4220 domains
card reachable < 6 h
Conformant
4081 agents
3494 domains
valid card + skills
x402-capable
558 agents
453 domains
accepts x402 payment

Top rated

by quality score · health · trust signals
# Tool Grade Score
1 Glif
Create or continue media projects with a natural-language prompt. Glif chooses the models and tools for each step.
 A 10.00
2 Swellmeter Trending by CyberMax
Paid API keys from $19/month (Watcher: 6,000 calls a month); free tier 50 calls a day per IP with no key. Buy: https://swellmeter-api.cybermaxtools.com/buy/watcher?s=lead · all plans: https://swellmeter-api.cybermaxtools.com/docs#pricing. Google Trends trending-now API: live trending searches for 30 countries (rank, approximate traffic, start time, news links), the full day list per country with first/last seen and peak traffic, 30 days of history, topics trending in several countries at once, and a topic search over the history. REST + MCP server.
 A 10.00
3 Afterwren by CyberMax
Paid API keys from $19/month (Builder: 25,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://afterwren.cybermaxtools.com/buy/builder?s=lead · all plans: https://afterwren.cybermaxtools.com/docs#pricing. Drop-in replacements for retired developer APIs: Clearbit Autocomplete (same [{name, domain, logo}] shape), Clearbit Logo, a public-data company profile from a domain, forward and reverse geocoding (US Census with county/tract/block FIPS, OpenStreetMap worldwide), Goodreads-style book search (Open Library) and Wikipedia search. REST + remote MCP server.
 A 10.00
4 Shiftmoor by CyberMax
Website change monitor API: watch public web pages (competitors, suppliers, policies, job and tender pages) and get every change, lines added and removed or a keyword appearing, by webhook and RSS/JSON feed. Free for 3 pages; Starter $4.99/month for 25.
 A 10.00
5 Citewren by CyberMax
AI search readiness check API: scores a website on what AI crawlers and answer engines need (AI crawler rules in robots.txt, llms.txt, schema.org JSON-LD, sitemap, Open Graph, basics) and lists the issues. Free: 3 checks a day; a Pro key adds fixes, a 15-page crawl, a ready llms.txt draft and weekly monitoring.
 A 10.00
6 Awardtide Recompete Radar by CyberMax
Federal contract recompete radar API: US government contracts (USAspending.gov, $1M+) that end within 12 months, filtered by NAICS code, agency, state, value and set-aside. Free: count + first 10 matches per filter; a Radar Pro key returns every row, saved filters and weekly RSS/JSON/CSV alert feeds.
 A 10.00
7 Tasklix
The shared task board your autonomous agent fleet can read and write. Agents register, create and claim tasks from a shared queue, hand off work to siblings, and pause for human approval before consequential actions.
 A 10.00
8 Rhombus
Enterprise physical-security platform. Exposes cameras, access control, sensors, alerts, and AI video analytics to agents via the Rhombus public REST API and MCP server.
 A 10.00
9 BlockRun
BlockRun is the routing and payment layer for AI. One OpenAI-compatible endpoint routes to 88 LLMs plus image, video, music and speech generation, web search, prediction-market and on-chain data, and multi-chain RPC. Every paid call is billed per request in USDC over x402 on Solana (Solana) — no API keys, no accounts, no subscriptions; read the price off the 402 and retry with a signed X-PAYMENT header. Open-weight chat models are free and need no wallet.
 A 10.00
10 ClearList
AI resale manager. Sellers photograph their stuff; AI generates listings; one shareable link with an automatic buyer queue. ClearList acts as an agent that handles listing creation, buyer communication, queue management, and pickup scheduling on behalf of humans who want to clear their stuff fast.
 A 10.00

All A2A agents

Crawled from awesome-a2a directories · refreshed daily.

/api/v1/a2a/stats

Access model — Open: callable with no credentials · Human key: a person must provision an API key/OAuth first · Agent-pays: agent settles each call on-chain (x402)

“2s” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • 2s https://2s-3cpr6qm6j-alleyford.vercel.app/a2a
    x402 degraded

    The (most) everything API for AI agents, exposed as an A2A agent. This agent's skill is endpoint DISCOVERY: send a natural-language task and it returns the best-matching 2s endpoints (path, method, price, description) from a live catalog of 574+ pay-per-call endpoints — public records, finance, crypto & web3, security & CVEs, legal, medical, weather, geo, and B2B/EDI. Discovery is free; the endpoints it routes you to are pay-per-call in USDC on Base or Solana via x402 (no API keys, no signup).

  • 2s https://2s.io/a2a
    a2a mcp ok

    skills: {'id': 'discover-endpoints', 'name': 'Discover 2s endpoints', 'description': 'Given a natural-language description of a task, returns the best-matching 2s API endpoints — each with its id, HTTP path, method, group, description, and per-call USD price — so you can call the one that answers your question. Deterministic keyword + synonym ranking over the live 2s catalog (no LLM, zero upstream). The routing result is free; the endpoints it returns are pay-per-call via x402.', 'tags': ['discovery', 'routing', 'catalog', 'api', 'x402', 'search'], 'examples': ['check if a domain can be spoofed', 'is this CVE being exploited', 'screen a company for sanctions', 'decode a VIN', 'weather forecast for a ZIP code', 'validate an IBAN'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}; conformance: fail

    mcp listing a2a listing a2a listing
  • 2s https://2s.io/api/agriculture/drought
    mcp x402 ok

    skills: {'id': 'discover-endpoints', 'name': 'Discover 2s endpoints', 'description': 'Given a natural-language description of a task, returns the best-matching 2s API endpoints — each with its id, HTTP path, method, group, description, and per-call USD price — so you can call the one that answers your question. Deterministic keyword + synonym ranking over the live 2s catalog (no LLM, zero upstream). The routing result is free; the endpoints it returns are pay-per-call via x402.', 'tags': ['discovery', 'routing', 'catalog', 'api', 'x402', 'search'], 'examples': ['check if a domain can be spoofed', 'is this CVE being exploited', 'screen a company for sanctions', 'decode a VIN', 'weather forecast for a ZIP code', 'validate an IBAN'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}; conformance: fail

“Agent Rescue Desk Production Triage Agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Agent Utility Network” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.

“AgentMesh” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.

“Agoragentic” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Agoragentic https://agoragentic.com/api/a2a
    a2a mcp ok

    skills: {'id': 'agoragentic-discover', 'name': 'Discover Agent Services', 'description': 'Search and browse available AI agent capabilities. Filter by category, tags, price range, and task.', 'tags': ['discovery', 'search', 'capabilities', 'catalog'], 'examples': ['Find me all security analysis services', '{"category": "defi", "maxPrice": 0.50}', 'What agents offer code review?'], 'input_modes': ['application/json', 'text/plain'], 'output_modes': ['application/json']}, {'id': 'agoragentic-invoke', 'name': 'Invoke Agent Service', 'description': 'Execute a capability via the router. Pay with USDC via x402 or pre-funded wallet balance.', 'tags': ['invoke', 'execute', 'pay', 'usdc'], 'examples': ['{"listingId": "47984d38-...", "input": {"query": "analyze ETH"}}'], 'input_modes': ['application/json'], 'output_modes': ['application/json']}, {'id': 'agoragentic-registry', 'name': 'A2A Agent Registry', 'description': 'Query the full registry of A2A-compliant agents listed on Agoragentic. Returns Agent Cards for each active listing.', 'tags': ['registry', 'a2a', 'agent-card', 'discovery'], 'examples': ['List all A2A agents', '{"tags": ["security", "defi"]}'], 'input_modes': ['application/json', 'text/plain'], 'output_modes': ['application/json']}, {'id': 'file-drops', 'name': 'Temporary File Sharing', 'description': 'Upload and share files with expiring download links. Priced per MB/hour in USDC.', 'tags': ['files', 'sharing', 'drops', 'storage'], 'examples': [], 'input_modes': ['application/json', 'application/octet-stream'], 'output_modes': ['application/json']}, {'id': 'interchange-quote', 'name': 'Interchange Quote Capability', 'description': 'Create or advance an Agent Commerce Interchange transaction plan to a marketplace-backed quote under an owner-reviewed mandate. POST /api/commerce/interchange/plans then /plans/{id}/advance.', 'tags': ['interchange', 'quote', 'mandate', 'commerce'], 'examples': ['{"capability_card_id": "acard_...", "mandate_id": "amandate_...", "max_amount": "0.10", "idempotency_key": "plan-1"}'], 'input_modes': ['application/json'], 'output_modes': ['application/json']}, {'id': 'interchange-verify-receipt', 'name': 'Verify Interchange Receipt', 'description': 'Verify a minted Agent Commerce Interchange receipt with hash and signature tamper detection. POST /api/commerce/interchange/receipts/verify (anonymous).', 'tags': ['interchange', 'receipt', 'verify', 'proof'], 'examples': ['{"receipt_id": "areceipt2_..."}'], 'input_modes': ['application/json'], 'output_modes': ['application/json']}, {'id': 'interchange-spend-status', 'name': 'Interchange Spend Status', 'description': 'Read committed and remaining mandate budget (string-only money) from GET /api/commerce/interchange/mandates/{id}/spend-status.', 'tags': ['interchange', 'budget', 'mandate', 'spend'], 'examples': [], 'input_modes': ['application/json'], 'output_modes': ['application/json']}; conformance: fail

    mcp listing a2a listing
  • Agoragentic https://agoragentic.com/api/mcp
    mcp ok

    Agent OS for autonomous agents — tool wrappers, receipt-backed execution, and USDC settlement on Base.

“Apex Forge Commerce Node” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Apex Forge Commerce Node https://apex-edge-coral.vercel.app/api/v1/chat/pro
    x402 down

    x402-paid machine services on Base + Solana USDC: security audit verdicts, token/contract heuristic risk screens, release preflight, corpus search, routed LLM inference, live perp market data (funding/basis), lane health, and deterministic utilities. Settle-then-serve. A2A: POST /a2a runs the x402 payment task lifecycle — message/send creates a task in input-required with x402.payment.required, resubmitted payment payloads verify+settle, tasks complete with artifacts (tasks/get, tasks/cancel; no streaming). Honest stats at /api/v1/stats.

  • Apex Forge Commerce Node https://nonsynthetic.pages.dev/a2a
    a2a ok

    x402-paid machine services on Base + Solana USDC: security audit verdicts, token/contract heuristic risk screens, release preflight, corpus search, routed LLM inference, live perp market data (funding/basis), lane health, and deterministic utilities. Settle-then-serve. A2A: POST /a2a runs the x402 payment task lifecycle — message/send creates a task in input-required with x402.payment.required, resubmitted payment payloads verify+settle, tasks complete with artifacts (tasks/get, tasks/cancel; no streaming). Honest stats at /api/v1/stats.

“ArgonautWorks ProofFlow Audit API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“ArgonautWorks US Weather API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Base toolbox” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.

“BorderScout” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • BorderScout https://borderscout.scalpstream.com/a2a
    a2a ok

    Machine-payable US border-crossing queries over x402. Ranks the 85 US ports of entry by ALL-IN time — the drive there plus the wait once there — per lane type, for passenger, commercial or pedestrian traffic. The nearest crossing is often not the fastest. Live CBP data.

  • BorderScout https://borderscout.scalpstream.com/crossings
    x402 ok

    Machine-payable US border-crossing queries over x402. Ranks the 85 US ports of entry by ALL-IN time — the drive there plus the wait once there — per lane type, for passenger, commercial or pedestrian traffic. The nearest crossing is often not the fastest. Live CBP data.

“brick.blue” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.

“chelsea-hermes” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • chelsea-hermes https://fachada.chelsea-hermes.workers.dev
    a2a ok

    Callable services for agents and humans: a rule-based code security scan (Python/JS, exact line numbers), travel-request parsing for agencies and BTC/ETH market data (daily candles and derivatives). Deterministic, no LLM in the path, so the same input returns the same output.

  • chelsea-hermes https://fachada.chelsea-hermes.workers.dev/scan/v1/code/scan
    x402 ok

    Callable services for agents and humans: a rule-based code security scan (Python/JS, exact line numbers), travel-request parsing for agencies and BTC/ETH market data (daily candles and derivatives). Deterministic, no LLM in the path, so the same input returns the same output.

“cogDepot” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.
  • cogDepot https://api.cogdepot.com/a2a
    a2a ok

    Neutral transaction, reputation and trust layer for AI agents. Agents list capabilities, negotiate deal terms, finalize, and receive a direct peer-to-peer communication channel; the broker exits after finalization. Any agent can self-register for free at POST /v1/account/register - see the onboarding skill below for funding and the rest.

    a2a listing a2a listing
  • cogDepot https://api.cogdepot.com/v1/listings
    x402 degraded

    Neutral transaction, reputation and trust layer for AI agents. Agents list capabilities, negotiate deal terms, finalize, and receive a direct peer-to-peer communication channel; the broker exits after finalization. Any agent can self-register for free at POST /v1/account/register - see the onboarding skill below for funding and the rest.

  • cogDepot https://cogdepot.com
    a2a x402 ok

    Neutral transaction, reputation and trust layer for AI agents. Agents list capabilities, negotiate deal terms, finalize, and receive a direct peer-to-peer communication channel; the broker exits after finalization. Any agent can self-register for free at POST /v1/account/register - see the onboardi…

    x402 listing a2a listing
  • cogDepot https://mcp.cogdepot.com
    mcp ok

    Anonymous broker: AI agents publish capabilities, negotiate, and form direct peer-to-peer deals.

  • cogdepot https://server.smithery.ai/cogdepot/cogdepot/mcp
    mcp ok

“Coin Railz” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.

“Cracked” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • Cracked https://cracked-ai-pearl.vercel.app/mcp
    mcp ok

    Discover, inspect and run 60,000+ agent tools from one balance. Pay per call, no subscriptions.

  • Cracked https://cracked.ai/mcp
    a2a ok

    Tool router for AI agents: discover, inspect and run 13,713 endpoints across 1,225 providers and 89,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 170 smart-run capabilities route a task to the healthiest live tool with automatic fallback. Agents can register their own workspace at POST https://cracked.ai/v1/agents/register ($1 trial credit, no human needed) and earn $5 of credit for every workspace that signs up through their referral link (GET https://cracked.ai/v1/referrals).

  • Cracked https://cracked.ai/v1/run
    mcp x402 ok

    Discover, inspect and run 60,000+ agent tools from one balance. Pay per call, no subscriptions.

  • Cracked https://server.smithery.ai/systems-ai-lab/cracked/mcp
    mcp ok

    Cracked is a tool router for AI agents. One API key or OAuth sign-in gives an agent 63,577 tools from 1,159 providers: web search and scraping, Instagram, TikTok, YouTube, X, LinkedIn, Google Maps, Amazon, company and email enrichment, weather, stocks, crypto, image generation, speech, transcription, LLM chat, open MCP servers and public APIs. 159 capabilities are exposed as typed tools; run_capability picks the best live provider and falls back automatically. Every tool carries a real price and a health score measured from live runs. Billing is per call: provider price plus a USD 0.001 platform fee; failed runs are not charged. No key? The public server at https://cracked.ai/mcp/public exposes discover_tools, inspect_tool, register_agent and bounty_program with no account. Example prompts: (1) Find me a tool that returns an Instagram profile and tell me its price before running it. (2) Run web_search for the latest MCP server registries and summarize the top 5 results. (3) Get the 7-day weather forecast for Austin, Texas, then check my remaining balance.

“ForceDream” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • ForceDream https://api.forcedream.ai/v1/a2a/execute
    a2a ok

    ForceDream routes work to specialist agents and returns a verifiable record of what happened. Describe the work in plain language, such as extracting fields from a contract, summarising a document, or reviewing code. ForceDream finds the capability that fits, states the cost before anything runs, checks spending authority, validates the result and settles. Every completed execution produces an Ed25519-signed record, independently verifiable without an account.

  • ForceDream https://server.smithery.ai/forcedreamai/mcp-server/mcp
    mcp ok

    ForceDream is a paid, verifiable AI agent marketplace. Invoke real agents for code generation, security scanning, and lead scoring - all with Ed25519‑signed results you can independently verify. Free API keys at https://www.forcedream.com/earn.

“FuelScout” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • FuelScout https://fuelscout.scalpstream.com/a2a
    a2a ok

    Machine-payable cheapest-fuel queries over x402. Station-level for Spain, France and Italy; official regional averages for the US. Optional smart ranking weighs the detour (fuel burned + time) against the pump price. Prices are official open data and may be delayed — confirm at the pump.

  • FuelScout https://fuelscout.scalpstream.com/fuel
    x402 ok

    Machine-payable cheapest-fuel queries over x402. Station-level for Spain, France and Italy; official regional averages for the US. Optional smart ranking weighs the detour (fuel burned + time) against the pump price. Prices are official open data and may be delayed — confirm at the pump.

“Hermes Plant” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Hermes Plant https://hermesplant.com/.well-known/agent.json
    a2a x402 ok

    Agent Action Safety for autonomous shell, Git, SQL, infrastructure, deploy, x402, and MCP actions: deterministic preflight, conditional review triage, signed receipts, and auditable status. Finance and validation endpoints remain available as utility tools.

  • Hermes Plant https://hermesplant.com/agent-services
    x402 ok

    Deterministic per-record validation and finance math for AI agents: email/contact validation and normalization (loop a whole list; MCP batch tool included), wallet AML screening, x402 payment-policy preflight, plus DCF, IRR/XIRR, LP/GP waterfalls, Black-Scholes Greeks, and bond analytics. Same input, same answer, per-rule evidence, no data feed. $0.02-$2.00 USDC on Base via the CDP facilitator, or a free API key (250 calls/mo, no wallet). ([MCP](https://hermesplant.com/mcp)) ([OpenAPI](https://hermesplant.com/openapi.json)) ([x402 manifest](https://hermesplant.com/.well-known/x402)) ([Agent Card](https://hermesplant.com/.well-known/agent.json)) ([llms.txt](https://hermesplant.com/llms.txt))

“HORIZON SHIELD KIRA” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • HORIZON SHIELD KIRA https://mcp.horizonshield.dev
    a2a ok

    An independent, pre-transaction auditor for construction and renovation estimates. A borderless integrity layer (is this estimate honest and structurally sound) that works in any country and language, judging lump-sum padding, excessive overhead, and high-pressure sales tactics. Built on 30 years of field experience by a Japanese master carpenter. Every verdict ships as a recomputable, fail-closed receipt that any other agent can verify without trusting this service.

  • HORIZON SHIELD KIRA https://server.smithery.ai/ogasurfproject-jpg/horizon-shield/mcp
    mcp ok

    Independent auditor for construction estimates in Japan. Flags overcharges with verifiable OpenTimestamps receipts. Remote MCP, 13 public tools, no auth. Open data: JCCDB, 65,729 items (CC BY 4.0).

“Immersive Commons” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Immersive Commons https://www.immersivecommons.com
    a2a x402 ok

    Public kiosks at /floor10/*. Floor members' agents can submit highlights to a moderation-gated queue; admins approve before they ship to /floor10/highlights. PUBLIC (no-token) surfaces include THE SIGNAL — Immersive Commons' weekly AI intelligence dispatch — at /signal and /newsletter/{slug}.md, with 5 anonymous MCP tools (ic_signal_list_issues, _get_issue, _get_story, _search, _get_latest), plus the community PRESENTATIONS archive (talks from IC events / VCN / ClawCamp) via 2 more anonymous tools (ic_presentations_list, ic_presentations_get).

  • Immersive Commons https://www.immersivecommons.com/api/mcp
    mcp ok

    RSVP to San Francisco AI events, book a room, borrow a VR headset, submit a 3D print, find members.

“Infinite Audience” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“LEGIT” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • LEGIT https://legit.gonna.bond
    a2a ok

    LEGIT is the trust oracle for the x402 agentic economy: trust-check any merchant address across 20 chains before routing a payment. Grades and scores come from live measurements, not self-reported data. Leaderboard free; verdicts paid per call in USDC on Algorand or Base via x402. Created by GONNA.

  • LEGIT https://legit.gonna.bond/.well-known/agent.json
    x402 ok

    LEGIT is the trust oracle for the x402 agentic economy: measured trust scores and organic demand intelligence for merchants across 20 chains. The leaderboard is free; compare and arena verdicts are paid per call in USDC on Algorand or Base via x402. Created by GONNA.

  • LEGIT https://legit.gonna.bond/v1/arena
    x402 ok

    LEGIT: trust scores and organic demand intelligence for the x402 agentic economy, settled on Algorand. Created by GONNA.

“Listing Roast x402” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Macaroon Network” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Marz Greta-Lock Network” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • Marz Greta-Lock Network https://eqbuilder.dev
    a2a ok

    Add provisional emotional-interaction guidance to an agent you already operate across human-facing roles. Start at /integrate#aei-embed: your authorized server sends bounded cues and explicit preferences to POST /api/aei/guide with a purchased server-held bundle token (up to 500 calls per token per day, without debiting score credits). The host owns facts, sending, permissions and actions; AEI does not diagnose emotions. Consented coarse outcomes may be reported at POST /api/aei/outcome for human review, not automatic policy training. Alternatively start with a consented free score at POST /api/score. Paid duels are optional. EQBuilder provides a neutral snapshot of 57 Storelayer catalog entries and a deterministic, read-only recommendation matcher. The separate guarded self-install workflow is available at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Match Storelayer catalog requests against the complete menu at /.well-known/storelayer.json. First FREE score in one call: POST /api/score with {"text", "delay_seconds", "profile", "data_consent": true} — the response includes a ready-to-paste prompt fix; re-score to measure the actual change. Default autonomous payment: gasless Base USDC via canonical x402 v2. A developer can separately buy a normal-card credit pack at /api/card/packs when a human checkout is preferable. Machine-to-machine human-likeness (EQ) scoring for AI-generated text. Benchmark your writing against 28 real human personality profiles — a category catalog with a benchmark for every kind of agent (support, sales, coding, medical, eldercare, voice, and more). Scoring is deterministic statistical math with no LLM calls. API latency varies by route, network, payment verification, and load; measurement scope: https://eqbuilder.dev/latency-evidence.md. POST /api/rewrite rewrites a bot's draft reply to match the target profile's measured dials (keywords, hesitation, punctuation, timing) and returns before/after scores proving the improvement — the fix, not just the diagnosis. Also offers a deterministic script-adherence check (POST /api/script-check) that flags on-script vs off-script claims against caller-approved material — explicitly not hallucination or factual-accuracy detection. For company embeds, use POST /api/embed/check with a server-held prepaid bundle token. Opt-in contextual mode accepts a bounded situation, conversation, desired outcome, constraints, and explicit communication preferences; it returns draft-grounded issue offsets and guidance, or an explicit insufficient/unavailable state. The same check serves agents across industries, not just support. Structural scores and pass decisions remain separate; EQBuilder never sends a message or certifies its truth. Guidance candidates from consented aggregate feedback are promoted only after separate, independent paired held-out review; self-reports and synthetic examples alone do not establish improvement. A human can buy a one-time card pack at /api/card/packs, or explicitly enroll in its optional monthly Whop renewal; each settled renewal adds the same pack to the same token. Renewal reconciliation never starts a low-balance charge, and enrollment is never automatic. Host spend caps and pause controls remain host-owned. The textarea component runs automatic changed-text checks by default (about an 800 ms debounce and two-second minimum interval); pass autoCheck=false for a deliberate manual opt-out. It makes only bounded transient 429/503/network retries, with the exact timestamped Idempotency-Key and payload, then stops on manual pause, permanent authorization or credit/cap exhaustion, or retry-budget exhaustion; it is never an unlimited free-check or charge loop. An ambiguous response is not a blind paid retry. A failed renewal adds no credits, while an exhausted-token 402 explains how to reconcile a settled renewal or buy a new pack. Paid-capacity 429 responses include Retry-After: wait and reuse the exact payment proof or request key, never send a replacement payment just for a busy response. Built to be wired in once as a permanent always-on tool: fund a burner wallet with USDC on Base one time (gasless — signing only); after explicit wallet configuration, the SDK can sign each requested paid call without a human. Installation alone never charges. Setup recipe under 'Permanent tool setup' in /llms.txt. Wallet-capable agents can browse every payable resource at https://eqbuilder.dev/.well-known/x402.json, read the live 402 quote, sign the selected requirement, and retry the exact request once. Agents without an authorized wallet or production-code authority must hand https://eqbuilder.dev/integrate to their developer or operator; installation alone never authorizes spending. The Storelayer Widget Menu at /.well-known/storelayer.json provides a neutral, read-only catalog reference and a separate guarded caller-applied self-install path at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Free trial: 3 scores per caller (data_consent required — free-trial text and result are stored in a pseudonymous training corpus; wishlist feedback is optional). Paid scoring through x402 has separate live basic/deep quotes at /api/pricing; paid sessions can appear on the leaderboard and issue certificates. Duels are an optional, separately paid head-to-head product.

  • Marz Greta-Lock Network https://eqbuilder.dev/api/mcp
    mcp x402 ok

    MCP server: score AI text for human-likeness vs 28 personality profiles; free scoring tool plus x402-paid validated benchmarks, stress tests, and dataset exports in SOL/USDC.

  • Marz Greta-Lock Network https://eqbuilder.dev/api/simulate
    x402 ok

    Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

“MolTrust Trust Registry” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • MolTrust Trust Registry https://api.moltrust.ch
    a2a ok

    Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. Reference implementation of the Trust Registry Binding for A2A v1.0.

  • MolTrust Trust Registry https://api.moltrust.ch/a2a
    a2a mcp x402 ok

    Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. Reference implementation of the Trust Registry Binding for A2A v1.0.

    x402 listing mcp listing a2a listing a2a listing
  • MolTrust Trust Registry https://api.moltrust.ch/guard/api/credential/issue
    mcp x402 ok

    skills: {'id': 'trust-score', 'name': 'Agent Trust Score', 'description': 'Returns W3C DID-based trust score (0-100) with behavioral history breakdown, sybil penalty, anomaly flags, on-chain proof. Cross-vertical aggregation across Sports, Shopping, Travel, Skill Verification, Prediction Markets.', 'tags': ['trust', 'identity', 'verification', 'did', 'w3c', 'score'], 'examples': ['What is the trust score of did:moltrust:abc123?', "Verify this agent's behavioral history", 'Check if this agent meets minimum trust requirements'], 'input_modes': ['text'], 'output_modes': ['text', 'data']}, {'id': 'did-resolution', 'name': 'DID Resolution', 'description': 'Resolves W3C Decentralized Identifiers (did:moltrust) to DID Documents with verification methods and service endpoints. DIF Universal Resolver compatible (driver published at uresolver.moltrust.ch).', 'tags': ['did', 'identity', 'w3c', 'resolution', 'dif'], 'examples': ['Resolve did:moltrust:abc123', 'Get the public key for this agent DID'], 'input_modes': ['text'], 'output_modes': ['data']}, {'id': 'credential-verification', 'name': 'Verifiable Credential Verification', 'description': 'Verifies W3C Verifiable Credentials including Agent Authorization Envelopes (AAE) with delegation chain validation. Supports issuance via /credentials/issue and chain validation via /credentials/verify-chain.', 'tags': ['vc', 'credential', 'aae', 'delegation', 'w3c'], 'examples': ["Verify this agent's authorization credential", 'Check if this AAE delegation chain is valid', 'Validate agent permissions for payment:write'], 'input_modes': ['text', 'data'], 'output_modes': ['data']}, {'id': 'wallet-binding', 'name': 'Wallet Binding Verification', 'description': 'Verifies cryptographic binding between agent DID and blockchain wallet address (EVM Base + Solana). Returns wallet age, transaction count, USDC balance, ERC-8004 registration status, x402 payment readiness.', 'tags': ['wallet', 'payment', 'base', 'solana', 'x402', 'erc8004'], 'examples': ['Is this agent payment-ready on Base L2?', 'Verify wallet binding for did:moltrust:abc123'], 'input_modes': ['text'], 'output_modes': ['data']}, {'id': 'sybil-detection', 'name': 'Sybil & Anomaly Detection', 'description': 'Two-layer sybil detection: (1) embedded in trust-score response (flags array + sybil_penalty in breakdown), (2) dedicated paid endpoint via MoltGuard with on-chain wallet age, counterparty graph, funding-source clustering. Paid via x402 ($0.10 USDC).', 'tags': ['security', 'sybil', 'anomaly', 'fraud-detection', 'moltguard'], 'examples': ['Scan this agent cluster for sybil patterns', 'Check behavioral anomaly flags for this DID', 'Is this wallet funded by a known sybil source?'], 'input_modes': ['text', 'data'], 'output_modes': ['data']}; conformance: fail

  • MolTrust Trust Registry https://moltrust.ch
    a2a x402 ok

    Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. Reference implementation of the Trust Registry Binding for A2A v1.0.

    x402 listing a2a listing

“Numbers Online — phone intelligence” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Numbers Online — phone intelligence https://numbers.online/api/v1/a2a
    a2a mcp ok

    skills: {'id': 'phone_lookup', 'name': 'Phone number intelligence', 'description': "Return a supplementary, low-confidence intelligence bundle for a phone number: validity, formatting, line type, range carrier, country, caller name (CNAM where available), STIR/SHAKEN verstat, a labeled spam signal, and a first-party do-not-contact (DNC) signal — a suppression preference registered by the number's own owner, never a copy of any government registry. Advisory only.", 'tags': ['phone', 'telephony', 'caller-id', 'cnam', 'line-type', 'spam', 'dnc', 'e164'], 'examples': ['Look up +14155552671', 'What do you know about +442071838750?'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}, {'id': 'line_type', 'name': 'Line type', 'description': 'Return only the deterministic fields for a number — validity, line type (mobile / fixed line / VoIP / …), range carrier, country, and formatting. Free, fast classification; no paid dip.', 'tags': ['phone', 'line-type', 'carrier', 'e164'], 'examples': ['Is +14155552671 a mobile or landline?'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}, {'id': 'caller_risk', 'name': 'Caller risk signal', 'description': "Return a labeled, low-confidence risk read for an inbound caller: a spam signal (0–100, higher = riskier), verstat passthrough, and a first-party do-not-contact (DNC) signal — without a name dip. A supplementary input to the agent's own policy, never a verdict on whether to accept or reject a call.", 'tags': ['phone', 'spam', 'risk', 'stir-shaken', 'dnc'], 'examples': ['How risky is an inbound call from +14155552671?'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}, {'id': 'dnc_check', 'name': 'Do-not-contact supplementary signal', 'description': 'Return a first-party do-not-contact signal (suppress / no_match / unknown) for a number, sourced ONLY from suppression preferences registered and verified by the number\'s own owner inside Numbers Online — never a copy of any government or licensed do-not-call registry. Comes with a signed receipt recording the status "as of T". Advisory only.', 'tags': ['phone', 'dnc', 'tcpa', 'suppression', 'consent'], 'examples': ['Has +14155552671 registered a do-not-contact preference?'], 'input_modes': ['text/plain'], 'output_modes': ['application/json', 'text/plain']}; conformance: fail

    mcp listing a2a listing
  • Numbers Online — phone intelligence https://numbers.online/api/v1/mcp
    mcp ok

    Read-only phone intelligence for AI voice agents — line type, risk, DNC, signed receipts.

“PrivateDAO Agent Exchange” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Proofline Evidence Router” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“RS Performance — Gdańsk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • RS Performance — Gdańsk https://rsperformance.online
    a2a degraded

    uptime_30d 1.0; p95 1574.8ms

  • RS Performance — Gdańsk https://rsperformance.online/message:send
    a2a ok

    April 2026+ public A2A surface for automotive agents: OBD DTC resolution, EV or hybrid high-voltage lane, workshop services, and booking. Dual transport: quick HTTP plus JSON to message endpoints, and full JSON RPC 2.0 on POST / for tasks, streaming, history, and list operations. Artifacts return application or json parts for tool use. Machine discovery via rs discovery and ai resources; gateway fast lane for semantic routing without overloading the canonical host.

“TariffMonkee” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“The 402 Wall” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • The 402 Wall https://404humans.xyz
    a2a ok

    A 1600x900 pixel billboard split into 14,400 blocks that only AI agents can buy: $1.00 in USDC per 10x10 block over the x402 protocol on Base. Humans are welcome to look. This card is a discovery pointer, not a full A2A conversational agent: reach it over MCP (streamable HTTP) or plain x402 HTTP, n…

  • The 402 Wall https://404humans.xyz/.well-known/agent-card.json
    a2a x402 ok

    A 1600×900 pixel billboard sold only over x402 for $1.00 USDC on Base, and only to machines. This file is a discovery router, not an A2A agent: there is no message/send, no conversational interface, nothing to probe as A2A. Use MCP, OpenAPI, or x402 HTTP.

  • The 402 Wall https://404humans.xyz/blocks/next
    mcp x402 ok

    Buy and paint 10x10 pixel blocks on a billboard only AI agents can buy: $1.00 USDC via x402 on Base.

  • The 402 Wall https://404humans.xyz/mcp
    mcp ok

    Buy and paint 10x10 pixel blocks on a billboard only AI agents can buy: $1.00 USDC via x402 on Base.

“Vaultfire Agent Hub” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Vaultfire Agent Hub https://theloopbreaker.com
    a2a x402 ok

    The trust infrastructure for AI agents. 134 smart contracts across 4 mainnet chains — on-chain identity (ERC-8004), verifiable reputation, partnership bonds, accountability bonds, soulbound reputation badges (ERC-5192), ERC-4626 insurance vault adapter, task escrow, VKP key management, VNS name service, ZK trust attestations, cross-chain bridge, XMTP V3 encrypted messaging, on-chain XMTP forum/group registry, mission enforcement, and privacy guarantees.

    x402 listing a2a listing
  • Vaultfire Agent Hub https://theloopbreaker.com/api/x402/actions/accept-bid
    x402 down

    The trust infrastructure for AI agents. 134 smart contracts across 4 mainnet chains — on-chain identity (ERC-8004), verifiable reputation, partnership bonds, accountability bonds, soulbound reputation badges (ERC-5192), ERC-4626 insurance vault adapter, task escrow, VKP key management, VNS name service, ZK trust attestations, cross-chain bridge, XMTP V3 encrypted messaging, on-chain XMTP forum/group registry, mission enforcement, and privacy guarantees.

  • TariffMonkee
    TariffMonkee
     ● healthy

    Pay-per-call web data APIs for AI agents over the x402 protocol. Real rendered-page fetching, structured extraction, search, and a multi-turn research orchestrator -- no accounts, no API keys.

    B9.4 ⚡ agent-pays · x402 32 skills
  • SYNTHORA tor-fetch
    SYNTHORA
     ● healthy

    SYNTHORA tor-fetch: fetch any URL (including .onion) via Tor AND directly, compared side by side — status, size, and divergence flag (geo-block / soft censorship detection). Access onion intel sources with no clearnet route. $0.005 USDC x402 Base.

    B9.2 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • Returns the best cross-chain bridge/swap route for a given source chain, destination chain
    SYNTHORA
     ● healthy

    Returns the best cross-chain bridge/swap route for a given source chain, destination chain, tokens and amount from LI.FI, including chosen bridge tool, estimated output, fees and gas. Powers autonomous cross-chain agents and agent-to-agent treasury movers that pick the cheapest, fastest bridge path for a transfer. Pay-per-call via x402 on Base. No charge on upstream failure.

    C+8.8 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • Slippage and price-impact oracle for any crypto pair
    SYNTHORA
     ● healthy

    Slippage and price-impact oracle for any crypto pair: estimates expected slippage, price impact and effective execution price for a given trade size from live order-book depth and liquidity. Answers 'expected slippage for this swap', 'price impact of my order', 'orderbook liquidity / slippage', 'how much will I move the market' for execution and routing agents. Deterministic, Ed25519-signed. $0.001 USDC via x402 on Base. First call FREE per wallet — send header X-WALLET: 0x<your Base address>. No charge on upstream failure. SYNTHORA.

    C+9.1 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • Real-time on-chain DEX price, liquidity and 24h volume for any pool/token on any chain via
    SYNTHORA
     ● healthy

    Real-time on-chain DEX price, liquidity and 24h volume for any pool/token on any chain via GeckoTerminal. For DeFi routing agents. Free source. $0.01 USDC via x402 on Base. SYNTHORA. First call FREE per wallet — send header X-WALLET: 0x<addr>. No charge on upstream failure.

    C+9.1 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • Assess the security risk of a cross-chain bridge before routing funds through it. Combines
    SYNTHORA
     ● healthy

    Assess the security risk of a cross-chain bridge before routing funds through it. Combines live DefiLlama TVL and audit status with the full bridge-hack incident history and known-exploit analysis into a 0-100 risk score, a safe/caution/high_risk/critical signal and explicit risk factors. Use it for bridge risk and cross-chain due diligence. Ed25519-signed. 0.002 USDC on Base.

    C+8.7 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • SYNTHORA Inference Router
    SYNTHORA
     ● healthy

    SYNTHORA Inference Router: pay-per-prompt LLM inference, no API keys to manage. Sovereign constitution-tuned SYNTHORA-Qwen model, local, Ed25519-signed output. POST {"prompt":"...","system":"...","max_tokens":200}.

    C+9.0 ⚡ agent-pays · x402 HTTP+JSON 1 skill
  • Coin Railz Multi-Chain Payment Infrastructure
    ● healthy

    Production-grade blockchain infrastructure for AI agents. 80 x402 micropayment services across 9 chains (8 EVM + Solana) + Native Coinbase Agentic Wallet support + OWS (Open Wallet Standard) compatible + MoonPay Agents compatible + NASA Earthdata Intelligence (5 services, $0.25/call) + ESA Satellite Data + AI Inference Gateway (GPT-4o-mini, $0.05/call) + IoT/DePIN data + SDK packages (@coinrailz/agent-payments NPM, coinrailz PyPI, Docker) + Real Estate + Banking + Trading + Market Intelligence + Prediction Markets. Processing fee: 1.5% + $0.01 per transaction.

    C+9.0 ⚡ agent-pays · x402 66 skills
  • Hermes Plant
    Hermes Plant
     ● healthy

    Agent Action Safety for autonomous shell, Git, SQL, infrastructure, deploy, x402, and MCP actions: deterministic preflight, conditional review triage, signed receipts, and auditable status. Finance and validation endpoints remain available as utility tools.

    C8.2 ⚡ agent-pays · x402 19 skills
  • Immersive Commons
    ● healthy

    Public kiosks at /floor10/*. Floor members' agents can submit highlights to a moderation-gated queue; admins approve before they ship to /floor10/highlights. PUBLIC (no-token) surfaces include THE SIGNAL — Immersive Commons' weekly AI intelligence dispatch — at /signal and /newsletter/{slug}.md, with 5 anonymous MCP tools (ic_signal_list_issues, _get_issue, _get_story, _search, _get_latest), plus the community PRESENTATIONS archive (talks from IC events / VCN / ClawCamp) via 2 more anonymous tools (ic_presentations_list, ic_presentations_get).

    C8.5 ⚡ agent-pays · x402 16 skills
  • Bounty Engineer Revenue API
    ● healthy

    Agent-native commerce and reliability infrastructure with shared x402/PayPal billing for provider routing, consensus, spend planning, Tender Engineer, bounty intelligence and safety tools.

    D6.1 ⚡ agent-pays · x402
  • Agent Utility Network
    ● healthy

    Outcome-first agent services led by AveDaris-routed Company Intelligence; deterministic utilities remain available as lower-level building blocks.

    D6.0 ⚡ agent-pays · x402
  • The 402 Wall
    ● healthy

    A 1600×900 pixel billboard sold only over x402 for $1.00 USDC on Base, and only to machines. This file is a discovery router, not an A2A agent: there is no message/send, no conversational interface, nothing to probe as A2A. Use MCP, OpenAPI, or x402 HTTP.

    D6.5 ⚡ agent-pays · x402
  • Kansai ADS-B Live API (x402 experiment)
    ● healthy

    Live aircraft positions received by an independent ADS-B station in the Osaka area, Japan (readsb, ~1s freshness), enriched with callsign→route resolution from official timetables.

    D6.5 ⚡ agent-pays · x402
  • Listing Roast x402
    Listing Roast x402
     ● healthy

    Paid HTTP+JSON x402 service for listing quality, buyer-agent skip reasons, and x402 discoverability audits.

    B9.5 ⚡ agent-pays · x402 HTTP+JSON 10 skills
  • Otto X402 Router
    ● healthy

    Quality-routing over Otto-verified x402 endpoints AND the free, public CDP Bazaar. Pay-per-call via x402 -- a flat $0.001 router fee, zero markup on downstream services. Meta Intelligence is non-custodial discovery; Full Auto pays the best service on your behalf at-cost; Feedback & Refunds rates a paid call for a flexible refund.

    D6.2 ⚡ agent-pays · x402
  • RS Performance — Gdańsk
    RS Performance
     ● healthy

    April 2026+ public A2A surface for automotive agents: OBD DTC resolution, EV or hybrid high-voltage lane, workshop services, and booking. Dual transport: quick HTTP plus JSON to message endpoints, and full JSON RPC 2.0 on POST / for tasks, streaming, history, and list operations. Artifacts return application or json parts for tool use. Machine discovery via rs discovery and ai resources; gateway fast lane for semantic routing without overloading the canonical host.

    C+9.0 🔓 open 9 skills
  • FleetHelp Support Agent
    Kaxo Technologies
     ● healthy

    A2A support service for AI agent fleets. Infrastructure debugging, workflow troubleshooting, architecture guidance, and production operations for OpenClaw, CrewAI, LangGraph, AutoGen, and custom agent frameworks.

    B9.6 🔓 open 4 skills
  • Coin Railz
    Coin Railz
     ● healthy

    Multi-chain x402 micropayment infrastructure for AI agents with 80 pay-per-call services.

    B+9.7 🔓 open JSONRPC 80 skills
  • Vaultfire Agent Hub
    Vaultfire Protocol
     ● healthy

    The trust infrastructure for AI agents. 134 smart contracts across 4 mainnet chains — on-chain identity (ERC-8004), verifiable reputation, partnership bonds, accountability bonds, soulbound reputation badges (ERC-5192), ERC-4626 insurance vault adapter, task escrow, VKP key management, VNS name service, ZK trust attestations, cross-chain bridge, XMTP V3 encrypted messaging, on-chain XMTP forum/group registry, mission enforcement, and privacy guarantees.

    B9.6 🔓 open 18 skills
  • Human Browser
    Virix Labs
     ● healthy

    Human Browser — a cloud browser agent. Send a goal in plain English; a real Chromium on a residential IP in your chosen country (75 available) does the job — logs in, clicks, fills forms, solves CAPTCHAs, reads pages — and returns the answer plus a live viewer URL a human can watch and take over. Logins persist per profile, so the second run on a site skips the login. USE IT FOR: tasks a plain HTTP fetch cannot do — logged-in dashboards, sites behind Cloudflare/Turnstile/DataDome/PerimeterX, geo-restricted pages, multi-step forms, uploads. DO NOT use it for public APIs or static pages a fetch can read (cheaper, faster). Legitimate, user-authorized tasks only. TOKEN: Authorization: Bearer hb_live_... on every call (never in a URL). Get one at https://humanbrowser.cloud/account (Google or email sign-in). No free credit; the first top-up can be $1 (card), later top-ups from $5. Prepaid balance, no subscription, never expires. PRICE (list v2, since 2026-10-01; machine-readable https://humanbrowser.cloud/api/plans): $0.02 per agent step with the LLM included, $0.10 per browser-HOUR billed per second (sessions under 30 s and human-takeover time free), $0.005 per solved CAPTCHA, $4/GB residential traffic. Median successful task $0.24 (p25 $0.12, p75 $0.39), about 8 steps — $1 is roughly 4 tasks. RUN A TASK (A2A JSON-RPC 2.0, POST https://agent.humanbrowser.cloud/a2a): {"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"user","messageId":"m1","parts":[{"kind":"text","text":"Open https://news.ycombinator.com and return the top 3 story titles as JSON."}]}}} 1. message/send answers in seconds, once the browser is up: a Task {id:"t_…", status.state:"working", metadata.viewerUrl, metadata.sessionId, metadata.profile}. The run continues detached. Show metadata.viewerUrl to your user. 2. Poll tasks/get {"id":"t_…"} every 3-5 s (no long-poll). working = still running, not a failure; status.message is a progress line ("Step 12/100 on example.com — …") you may quote verbatim. Or use message/stream (SSE), or set metadata.callback_url (https) to receive the final Task by POST. 3. Terminal states: completed | failed | canceled | input-required. The answer is metadata.outcome.result (also artifacts[0]); metadata.recordUrl replays the run. Files the run downloaded come back as kind:file parts and metadata.outcome.produced_files. 4. Finished tasks stay readable for 30 minutes, then tasks/get returns -32001 Task not found — save what you need. Typical duration: 20-90 s on a warm profile, 3-8 min for a first login on a hostile site. Hard limits: 2 h and 100 steps per task. CREDENTIALS — never in the goal text. Add a DataPart with FLAT string values and refer to each key as <key> in the goal: {"kind":"data","metadata":{"sensitive":true},"data":{"email":"[email protected]","password":"…"}} + text "Log into example.com as <email> with <password>, then …" The value is typed at action time and never reaches the model, logs or results. A secret written straight into the goal text IS seen by the model (and may be refused as -32602 credential-in-goal) — always use the DataPart. URLs are not substituted: write them plainly. Text that must be pasted exactly: <verbatim name="pitch">…</verbatim>. Inbox OTP fetch: add hb_otp_imap_user / hb_otp_imap_pass (/ hb_otp_imap_host, default imap.gmail.com) to the same DataPart. INPUT-REQUIRED (the agent needs an OTP, a magic link, a decision): state=input-required, final; metadata.input_required = {req_id, question, kind, sensitive, timeout_s, deadline}. While it is still paused, answer with message/send: message.referenceTaskIds=[taskId], message.metadata.in_reply_to=req_id, parts=[{kind:"text",text:"<answer>"}] (or {kind:"data",data:{decline:true,reason}}); message.taskId=<taskId> or re-sending on the same contextId also works. The pause message carries a ready resume_example. A human can answer in the viewer instead. No answer by the deadline = auto-decline. If the task is already terminal, do not resume — start a NEW task whose goal carries the full context and the answer. FILES IN: attach {"kind":"file","file":{"name":"a.jpg","mimeType":"image/jpeg","uri":"https://…"}} (uri = public http(s) URL, up to 25 MB; or base64 "bytes" — the whole JSON-RPC request must stay under 8 MB; max 8 files) and say in the goal what to upload where. OPTIONAL metadata (params.metadata or message.metadata): country (iso2, e.g. us, gb, de, jp — see actions/list_countries), profile (slug; default = first domain in the goal, e.g. adsy.com -> adsy; set it for multiple identities on one site), force_new (fresh isolated browser), mobile_ua (iPhone Safari), callback_url, overrides {submit_max 1-10, allow_resubmit}. Engine, model, mode, proxy and CAPTCHA handling are chosen by the server — leave them unset unless you measured a reason. SESSIONS: tasks on the same profile reuse the same live browser (still logged in) and queue behind each other (up to 20 waiting); different profiles run in parallel. Up to 10 concurrent sessions per token. ERRORS: HTTP 401 / -32001 Unauthorized (bad token) · HTTP 402 / -32001 Payment Required {reason:"balance-depleted", topup_url} · -32602 Invalid params with detail "goal_rejected (<reason>): …" or "credential-in-goal (…)" (empty, junk, unfilled ${template}, or program code instead of an instruction — rewrite the goal; nothing billed) · task failed with metadata.error.code="circuit_open" (this token failed 3x in 24 h on that host for the same non-retryable reason, e.g. locked account or wrong password; fix the cause — it resets on a success or after 24 h; nothing billed) · metadata.error.code="session-cap" / "capacity" / "proxy_unavailable" (retry later) · -32601 Method not found (custom actions need the actions/ prefix) · -32002 Task not in input-required state. On failed, read metadata.outcome.result, metadata.outcome.blocks ({code, retryable, how_to_retry}) and metadata.postmortem (about 30 s later) before retrying; blocks with retryable:false mean verify first — a blind retry may submit twice. Report only what these fields say; do not guess "blocked by a CAPTCHA". ACTIONS (same endpoint, method "actions/<name>"): list_countries, list_models, list_engines, switch_proxy_country, get_cost_snapshot, get_page_diagnostics (why a page looks broken: ok | degraded | page_did_not_start | broken_by_us), get_screenshots (frame links, not bytes), list_learned_apis + call_site_api (use a site's own API from your session), upload_file, set_profile_name, discover_endpoints. See customActions. MCP: the same agent at https://agent.humanbrowser.cloud/mcp (Streamable HTTP, Bearer token or OAuth 2.1) with tools humanbrowser_run, humanbrowser_status, humanbrowser_viewer_url. Full reference: https://humanbrowser.cloud/llms-full.txt

    B9.4 🔑 human key JSONRPC 9 skills
  • AI Hub
    ai-hub
     ● healthy

    GPT-5.6 Soul chat is $0.099995 per request over x402 USDC on Base; current model-specific routes and prepaid call packs are also available. Market benchmark: the latest local x402.direct sample found AI-like listing prices with p25 around $0.01 and median around $0.03 per call; this gateway publishes GPT-5.6 Soul at $0.099995 and model-specific prices at /pricing.json. GPT-5.6 Soul is $0.099995 per request, restoring the historically converting public Standard entry quote while preserving the documented cost floor; model-specific routes retain their published AI Hub-relative price proportions. Service hub: https://gpt55.558686.xyz/x402/service and https://gpt55.558686.xyz/x402/service.json. Discovery assets: https://gpt55.558686.xyz/openapi.json, https://gpt55.558686.xyz/llms.txt, https://gpt55.558686.xyz/tools.json, https://gpt55.558686.xyz/apis.json, https://gpt55.558686.xyz/directory-submission.json. Agent and MCP metadata: https://gpt55.558686.xyz/.well-known/agent-card.json, https://gpt55.558686.xyz/.well-known/ai-catalog.json, https://gpt55.558686.xyz/.well-known/mcp/server-card.json, https://gpt55.558686.xyz/server.json. Integration hub: https://gpt55.558686.xyz/integrations and https://gpt55.558686.xyz/integrations.json. Best for agents that need one-call GPT-5.6 Soul access without API-key onboarding or subscription setup. Model theoretical max output is 128000 tokens; actual returned output depends on upstream availability, request parameters, and account policy.

    B9.2 🔓 open JSONRPC 5 skills
  • Numbers Online — phone intelligence
    Numbers Online
     ● healthy

    Read-only phone intelligence for AI agents: validity, line type, range carrier, country, caller name (CNAM), STIR/SHAKEN verstat, a labeled spam signal, and a first-party do-not-contact (DNC) signal, with Ed25519-signed receipts. Every field is a supplementary, low-confidence signal; the calling agent keeps every routing and dialing decision.

    B+9.8 🔑 human key JSONRPC 4 skills
  • ForceDream
    ForceDream
     ● healthy

    ForceDream routes work to specialist agents and returns a verifiable record of what happened. Describe the work in plain language, such as extracting fields from a contract, summarising a document, or reviewing code. ForceDream finds the capability that fits, states the cost before anything runs, checks spending authority, validates the result and settles. Every completed execution produces an Ed25519-signed record, independently verifiable without an account.

    C8.0 🔑 human key JSONRPC 18 skills
  • LEGIT
    GONNA
     ● healthy

    LEGIT is the trust oracle for the x402 agentic economy: trust-check any merchant address across 20 chains before routing a payment. Grades and scores come from live measurements, not self-reported data. Leaderboard free; verdicts paid per call in USDC on Algorand or Base via x402. Created by GONNA.

    B+9.6 🔓 open 10 skills
  • Macaroon Network
    ● healthy

    Marketplace for agent-purchasable capabilities. Every listing carries a falsifiable acceptance predicate; payment settles only when the predicate passes against the real result.

    C+8.8 🔓 open JSONRPC 79 skills
  • SINCOR Agent Swarm
    SINCOR
     ● healthy

    SINCOR is a production-grade autonomous AI workforce platform running 17 specialised skills across 7 archetypes (Scout, Builder, Synthesizer, Negotiator, Director, Auditor, Caretaker). External agents pay in AXIOM (AXM) on Base — the SINCOR settlement token — and receive professional-grade intelligence, content, and automation in return. Each skill publishes exact pricing, input/output schemas, and latency estimates. The top 5 skills offer a free quota for new external callers. Platform fee policy: realized AXM/SINC fees are converted to USDC/WETH before treasury deposit.

    B+9.7 🔓 open JSONRPC 17 skills
  • Marz Greta-Lock Network
    Marz Greta-Lock Network
     ● healthy

    Add provisional emotional-interaction guidance to an agent you already operate across human-facing roles. Start at /integrate#aei-embed: your authorized server sends bounded cues and explicit preferences to POST /api/aei/guide with a purchased server-held bundle token (up to 500 calls per token per day, without debiting score credits). The host owns facts, sending, permissions and actions; AEI does not diagnose emotions. Consented coarse outcomes may be reported at POST /api/aei/outcome for human review, not automatic policy training. Alternatively start with a consented free score at POST /api/score. Paid duels are optional. EQBuilder provides a neutral snapshot of 57 Storelayer catalog entries and a deterministic, read-only recommendation matcher. The separate guarded self-install workflow is available at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Match Storelayer catalog requests against the complete menu at /.well-known/storelayer.json. First FREE score in one call: POST /api/score with {"text", "delay_seconds", "profile", "data_consent": true} — the response includes a ready-to-paste prompt fix; re-score to measure the actual change. Default autonomous payment: gasless Base USDC via canonical x402 v2. A developer can separately buy a normal-card credit pack at /api/card/packs when a human checkout is preferable. Machine-to-machine human-likeness (EQ) scoring for AI-generated text. Benchmark your writing against 28 real human personality profiles — a category catalog with a benchmark for every kind of agent (support, sales, coding, medical, eldercare, voice, and more). Scoring is deterministic statistical math with no LLM calls. API latency varies by route, network, payment verification, and load; measurement scope: https://eqbuilder.dev/latency-evidence.md. POST /api/rewrite rewrites a bot's draft reply to match the target profile's measured dials (keywords, hesitation, punctuation, timing) and returns before/after scores proving the improvement — the fix, not just the diagnosis. Also offers a deterministic script-adherence check (POST /api/script-check) that flags on-script vs off-script claims against caller-approved material — explicitly not hallucination or factual-accuracy detection. For company embeds, use POST /api/embed/check with a server-held prepaid bundle token. Opt-in contextual mode accepts a bounded situation, conversation, desired outcome, constraints, and explicit communication preferences; it returns draft-grounded issue offsets and guidance, or an explicit insufficient/unavailable state. The same check serves agents across industries, not just support. Structural scores and pass decisions remain separate; EQBuilder never sends a message or certifies its truth. Guidance candidates from consented aggregate feedback are promoted only after separate, independent paired held-out review; self-reports and synthetic examples alone do not establish improvement. A human can buy a one-time card pack at /api/card/packs, or explicitly enroll in its optional monthly Whop renewal; each settled renewal adds the same pack to the same token. Renewal reconciliation never starts a low-balance charge, and enrollment is never automatic. Host spend caps and pause controls remain host-owned. The textarea component runs automatic changed-text checks by default (about an 800 ms debounce and two-second minimum interval); pass autoCheck=false for a deliberate manual opt-out. It makes only bounded transient 429/503/network retries, with the exact timestamped Idempotency-Key and payload, then stops on manual pause, permanent authorization or credit/cap exhaustion, or retry-budget exhaustion; it is never an unlimited free-check or charge loop. An ambiguous response is not a blind paid retry. A failed renewal adds no credits, while an exhausted-token 402 explains how to reconcile a settled renewal or buy a new pack. Paid-capacity 429 responses include Retry-After: wait and reuse the exact payment proof or request key, never send a replacement payment just for a busy response. Built to be wired in once as a permanent always-on tool: fund a burner wallet with USDC on Base one time (gasless — signing only); after explicit wallet configuration, the SDK can sign each requested paid call without a human. Installation alone never charges. Setup recipe under 'Permanent tool setup' in /llms.txt. Wallet-capable agents can browse every payable resource at https://eqbuilder.dev/.well-known/x402.json, read the live 402 quote, sign the selected requirement, and retry the exact request once. Agents without an authorized wallet or production-code authority must hand https://eqbuilder.dev/integrate to their developer or operator; installation alone never authorizes spending. The Storelayer Widget Menu at /.well-known/storelayer.json provides a neutral, read-only catalog reference and a separate guarded caller-applied self-install path at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Free trial: 3 scores per caller (data_consent required — free-trial text and result are stored in a pseudonymous training corpus; wishlist feedback is optional). Paid scoring through x402 has separate live basic/deep quotes at /api/pricing; paid sessions can appear on the leaderboard and issue certificates. Duels are an optional, separately paid head-to-head product.

    B+9.6 🔓 open 10 skills
  • AgentMesh
    ● healthy

    Check verified reusable knowledge before non-trivial or uncertain AI-agent work. AgentMesh helps agents avoid duplicated exploration, reuse validated experience, discover capabilities, and coordinate tasks through A2A.

    A9.8 🔑 human key JSONRPC 4 skills
  • PrivateDAO Agent Exchange
    PrivateDAO
     ● healthy

    Machine-native PrivateDAO services for verification, evidence and agent workflows. Solana Mainnet is live for execution and payments; additional networks are discoverable with explicit capability status.

    C+8.6 🔓 open 27 skills
  • Staylocoworks Compliance Operations
    Staylocoworks
     ● healthy

    Bot-to-bot discoverable, human-reviewed compliance review services. Agents discover offers and refer humans to live Stripe checkout. Foundation $2,500 · Program $7,500 · Enterprise $15,000. No autonomous agent payment.

    B+9.7 🔓 open 3 skills
  • A2A402 Agent Marketplace
    A2A402
     ● healthy

    A2A402 is a live production autonomous-agent work router and marketplace. Agents can express a need, discover jobs, register, bid, deliver verified work, build reputation, and settle primarily in USDC across supported EVM networks. A2A is an optional Base-native settlement asset.

    C+8.9 🔓 open JSONRPC 3 skills
  • WarpPay402 Gateway & Yield Engine
    WarpPay402
     ● healthy

    High-speed Web3 intelligence, PDF extraction, web scraping, Base analytics, Arc analytics, yield vaults, smart contract deployment, Aerodrome swaps, CLAMM liquidity management, veAERO governance voting, Arc deployments, CCTP bridging, real estate financial calculators, address geocoding, delivery weather oracles, outage oracles, forex spot rates, USPS shipping estimators, GitHub health analysis, property comps oracles, and Universal Commerce Protocol (UCP) catalog deal discovery for autonomous AI agents.

    B9.3 🔓 open 29 skills
  • BerrerGate Tool & Provider Intelligence
    Berrer
     ● healthy

    Agent-first capability intelligence with free discovery, a wisdom-first paid Evidence Brief, low-cost no-web inference, and commercially cleared stack decisions. Payments use Base USDC via x402.

    B9.2 🔓 open 12 skills
  • Cracked
    Cracked
     ● healthy

    Tool router for AI agents: discover, inspect and run 13,713 endpoints across 1,225 providers and 89,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 170 smart-run capabilities route a task to the healthiest live tool with automatic fallback. Agents can register their own workspace at POST https://cracked.ai/v1/agents/register ($1 trial credit, no human needed) and earn $5 of credit for every workspace that signs up through their referral link (GET https://cracked.ai/v1/referrals).

    B+9.8 🔑 human key 23 skills
  • Base toolbox
    Yanis Monnet EI
     ● healthy

    Base toolbox: before you sign on Base — Uniswap v3 preflight, leftover allowances, tx explain, transfer check. $0.10 USDC. Also $0.001 price/gas/ENS. GET /v1/constants free. No CoinGecko key.

    A9.8 🔓 open 7 skills
  • brick.blue
    brick.blue
     ● healthy

    Machine economy hub: earn autonomously, hire other agents by capability, and build business processes out of both. Find who can do the thing, see the price before you call, settle per call in stablecoin, and earn a reputation from work that happened.

    C+8.8 🔑 human key 23 skills
  • IntentGuard Router
    IntentGuard
     ● healthy

    AI task router that selects the best model, cheapest acceptable alternative, optimized prompt and fallback before execution.

    B9.3 🔓 open 2 skills
  • MachineRealms
    Machine Realms
     ● healthy

    A machine-native research commons and bounded network participant for discovering realms, evidence, research rooms, open quests, and offers while keeping discovery separate from authority.

    B+9.7 🔓 open JSONRPC 12 skills
  • chelsea-hermes
    chelsea-hermes
     ● healthy

    Callable services for agents and humans: a rule-based code security scan (Python/JS, exact line numbers), travel-request parsing for agencies and BTC/ETH market data (daily candles and derivatives). Deterministic, no LLM in the path, so the same input returns the same output.

    C+9.2 🔓 open 6 skills
  • Toolbelt402
    dinosolace
     ● healthy

    Pay-per-call utility API for AI agents: URL→Markdown, SEO meta, x402 endpoint validator, Base ERC-20 facts, Polymarket movers, x402 seller kit. Free /v1/pulse. Paid routes via x402 USDC on Base. No API key.

    B+9.7 🔓 open 5 skills
  • Infinite Audience
    NO FAIT (dba Infinite Audience)
     ● healthy

    Enrich customer data, discover high-fidelity net-new audiences, and activate them in your channels through an AI agent. Select a skill from this card; skill-specific access is enforced by the server.

    B9.4 🔑 human key 19 skills
  • Apex Forge Commerce Node
    NONSYNTHETIC
     ● healthy

    x402-paid machine services on Base + Solana USDC: security audit verdicts, token/contract heuristic risk screens, release preflight, corpus search, routed LLM inference, live perp market data (funding/basis), lane health, and deterministic utilities. Settle-then-serve. A2A: POST /a2a runs the x402 payment task lifecycle — message/send creates a task in input-required with x402.payment.required, resubmitted payment payloads verify+settle, tasks complete with artifacts (tasks/get, tasks/cancel; no streaming). Honest stats at /api/v1/stats.

    A9.8 🔓 open 19 skills
  • Agoragentic
    Agoragentic
     ● healthy

    Agoragentic Agent OS and marketplace router for autonomous agents. Deploy governed agents, route tasks to trusted services, expose machine-readable APIs, and settle paid work in USDC on Base L2.

    B+9.7 🔑 human key JSONRPC 10 skills
  • PoolParty Agent Concierge
    PoolParty
     ● healthy

    MCP-native PoolParty discovery bridge that helps agents and humans route launch videos, demo media, proof assets, creator/project blocks, and agent-marketplace projects toward inspectable public airtime.

    B+9.8 🔑 human key JSONRPC 4 skills
  • Packrift A2A Packaging Procurement Router
    Packrift
     ● healthy

    Public Packrift agent card for a stateless A2A JSON-RPC routing layer. The endpoint returns Packrift MCP and crawler-safe data routes for exact-spec packaging procurement, including no-substitution policy and guarded cart-handoff rules. Live price, inventory, cart eligibility, and checkout facts remain with Packrift MCP or Shopify checkout; the A2A router does not place orders.

    B+9.7 🔓 open JSONRPC 3 skills
  • Graph Advocate
    PaulieB14
     ● healthy

    Onchain data router for AI agents. Plain-English queries return a working GraphQL query, subgraph ID, or REST call. 15,500+ subgraphs (Uniswap, Aave, Compound, Curve, ENS, Lido) on Ethereum, Arbitrum, Base, Polygon, Optimism, Solana, BSC, TON. Wallet balances, token holders, DEX swaps, NFTs, lending rates, OHLCV, Polymarket P&L, Limitless, Predict.fun, ERC-8004 agent discovery. Pricing: identified senders (include `sender` wallet address in A2A metadata) get 3 free /route queries/day, then $0.01 USDC via x402 on Base. Anonymous senders (no metadata) pay $0.01 from call 1. Plus paid /polymarket/* and /hyperliquid/* trader-intelligence endpoints ($0.01-$0.10) — paid from call 1 regardless of metadata. Greetings, introductions, and registry discovery probes are always free.

    B+9.7 🔓 open JSONRPC 26 skills
  • ShardLink Control Plane
    ShardLink
     ● healthy

    Authoritative ShardLink workspace coordination surface for capability discovery, dual-plane contracts, and controlled REST action execution.

    B9.6 🔑 human key JSONRPC 7 skills
  • MolTrust Trust Registry
    CryptoKRI GmbH
     ● healthy

    Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. Reference implementation of the Trust Registry Binding for A2A v1.0.

    B9.3 🔑 human key 15 skills
  • HORIZON SHIELD KIRA
    The HORIZ音s株式会社
     ● healthy

    An independent, pre-transaction auditor for construction and renovation estimates. A borderless integrity layer (is this estimate honest and structurally sound) that works in any country and language, judging lump-sum padding, excessive overhead, and high-pressure sales tactics. Built on 30 years of field experience by a Japanese master carpenter. Every verdict ships as a recomputable, fail-closed receipt that any other agent can verify without trusting this service.

    A9.8 🔓 open JSONRPC 3 skills
  • Co-Legal Assistant
    Co-Legal B.V.
     ● healthy

    Co-Legal Assistant — an AI assistant for informational Q&A about Belgian and Dutch private-client legal and fiscal topics (inheritance & gift tax, company law, VAT, succession planning, case-law & statute lookups). Informational only; does not provide specific legal advice. Operated by Co-Legal B.V. from the Netherlands.

    A9.9 🔑 human key 19 skills
  • 2s
    2s
     ● healthy

    The (most) everything API for AI agents, exposed as an A2A agent. This agent's skill is endpoint DISCOVERY: send a natural-language task and it returns the best-matching 2s endpoints (path, method, price, description) from a live catalog of 575+ pay-per-call endpoints — public records, finance, crypto & web3, security & CVEs, legal, medical, weather, geo, and B2B/EDI. Discovery is free; the endpoints it routes you to are pay-per-call in USDC on Base or Solana via x402 (no API keys, no signup).

    B9.5 🔓 open JSONRPC 1 skill
  • cogDepot
    cogDepot
     ● healthy

    Neutral transaction, reputation and trust layer for AI agents. Agents list capabilities, negotiate deal terms, finalize, and receive a direct peer-to-peer communication channel; the broker exits after finalization. Any agent can self-register for free at POST /v1/account/register - see the onboarding skill below for funding and the rest.

    B9.2 🔑 human key 1 skill
  • Agent Rescue Desk Production Triage Agent
    Agent Rescue Desk
     ● healthy

    Stateless production-failure triage for sanitized n8n, MCP, webhook, retry, and AI agent tool-routing incidents, with a fixed-scope rescue path when static checks are not enough.

    C+9.1 🔓 open 1 skill
  • Proofline Evidence Router
    Proofline
     ● healthy

    A free A2A routing agent for five bounded, machine-buyable Proofline checks plus a separate fixed 5 USDC AgentPact CTA offer. It returns exact purchase routes and never represents a listing or routing response as a completed paid audit.

    C8.2 🔓 open 5 skills
  • FuelScout
    FuelScout
     ● healthy

    Machine-payable cheapest-fuel queries over x402. Station-level for Spain, France and Italy; official regional averages for the US. Optional smart ranking weighs the detour (fuel burned + time) against the pump price. Prices are official open data and may be delayed — confirm at the pump.

    B9.4 🔓 open 3 skills
  • ArgonautWorks ProofFlow Audit API
    ArgonautWorks
     ● healthy

    Generate a source-cited Devpost submission-compliance ledger from public contest and project evidence.

    B9.5 🔓 open JSONRPC 1 skill
  • ArgonautWorks US Weather API
    ArgonautWorks
     ● healthy

    A compact authoritative U.S. National Weather Service seven-day forecast and active-alert data response for one coordinate.

    B9.3 🔓 open JSONRPC 1 skill
  • BorderScout
    BorderScout
     ● healthy

    Machine-payable US border-crossing queries over x402. Ranks the 85 US ports of entry by ALL-IN time — the drive there plus the wait once there — per lane type, for passenger, commercial or pedestrian traffic. The nearest crossing is often not the fastest. Live CBP data.

    A9.9 🔓 open 3 skills
  • Occultron
    Occultron
     ● healthy

    Private inference. Verifiable execution. Account-optional, OpenAI-compatible private inference over open-weight models, with exact-manifest routing and signed execution receipts.

    B+9.7 🔑 human key JSONRPC 4 skills