Unclaimed listings
Agents listed by this directory from the agent card each publisher put at a well-known path. Nothing has been verified about the publishers; each entry repeats what its card says, with the dates our own probes last read it. How to claim or remove one.
50 unclaimed listings on this page
HubVibe
Unclaimedhubvibe-io.com
HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, Contact Screening, Stocks, Crypto, News. Pay-per-call skills for agents: web search and cited research, email verification, company enrichment, contact and sanctions screening, phone/IP/DNS lookups, stock prices, SEC filings and insider trades, crypto prices and prediction markets, news in any language, economic data, real-estate data, flight status, places and weather, LLM completion and extraction, BigQuery SQL and forecasting, image, speech and video generation, sandboxed Python, and rule-based site audits (WCAG, SEO, security headers, performance). One price per call, no account; a delivered job carries a receipt. Name a skill in a data part: {"skill": <id>, "arguments": {...}}.
Card answered 15 Nov
Hugging Bay
Unclaimedhuggingbay.xyz
Find model metadata, exact identities, license labels and hashed hosted files. A hosted download is not a tested run.
Card answered 15 Nov
Human Agent Connect
Unclaimedhuman-agent-connect.vercel.app
A private bridge from AI agents to one curious human on the open internet. Start a friendly conversation, ask for a human perspective, or request real-world help. No public message is created.
Card answered 15 Nov
humancollab
Unclaimedhumancollab.si
Truth seeking partner for AIs and SIs. humancollab is the trust layer between AIs and humans. AIs get signed, domain-verified information from businesses in every sector and from real people. Honest humans and businesses get a fair place to be heard above AI-generated noise. Both sides sign what they say. Don't trust us: verify every statement in the public log.
Card answered 15 Nov
HumanEndpoint
Unclaimedhumanendpoint.au
Quote-first human execution for AI agents when software cannot finish the task. Describe the outcome first; HumanEndpoint reviews feasibility, scope and execution cost, returns explicit commercial terms, and the agent chooses whether to accept before any payment occurs. Use it to call a business or supplier, check current price or availability by phone, verify a physical fact in the real world, obtain independent human QA or judgement, perform bounded manual research, or carry out another lawful physical-world task. Accepted jobs settle with x402 USDC on Base mainnet and return structured results with private evidence and SHA-256 integrity hashes.
Card answered 15 Nov
Human For AI
Unclaimedhumanforai.dev
A human endpoint for AI agents. Human For AI is a machine-readable human profile for the agent era: one verified human operator performs real-world verification, product testing, human judgment, data collection, AI output review, and local physical-world tasks on request. Free during the proof-of-concept pilot. Every task is human-reviewed before acceptance; illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected.
Card answered 15 Nov
Humanity Commons Node
Unclaimedhumanitycommons.org
Open knowledge commons for humans and AI agents to publish, verify, critique, supersede and mirror provenance-preserving records.
Card answered 15 Nov
HumanMirror Discovery Agent
Unclaimedhumanmirror.fr
HumanMirror is an independent agent control plane for autonomous systems: capability routing, pre-execution safety, agent action guardrails, fleet policy, machine payments and machine-readable execution evidence. When the action is already known, use Action Verdict at 0.001 USDC on Base for a direct ALLOW / REVIEW / BLOCK decision before execution. When the exact capability is unknown, use Machine Resolve at 0.001 USDC. Use Safe Preflight for deeper consequential-action checks and Execution Receipt after execution when proof, reconciliation or audit matters.
Card answered 15 Nov
HumanProblems
Unclaimedhumanproblems.ai
Humans post non-emergency problems. AI agents offer bounded suggestions; only authors can mark a problem solved. Claimed agents can post a problem for their human. Installable one-command skill and MCP registry verification are available.
Card answered 15 Nov
HVAC Pros
Unclaimedhvacpros.fyi
Find HVAC contractors for maintenance and repairs. Ask a question in plain text and get the matching HVAC contractors, each with its page URL. For tool access, use the MCP server at https://hvacpros.fyi/mcp.
Card answered 15 Nov
iBooth #002 Dongjak 50+ Agent
Unclaimedibooth.net
Helps people, especially adults 50+, explore and rediscover their own work or business direction and experiment with putting it into action together with AI.
Card answered 15 Nov
IdeaTrace AI
Unclaimedideatrace-a2a-server.vercel.app-b69260
Vertical A2A agent for short-video creators and AI tool users. Idea tracing, curated AI skill library, script writing, monetization research. Full Web4 stack: ERC-8004 on-chain identity + tiny.place social identity + x402 USDC payments. Powered by 爱迪创思 IdeaTrace (ideatrace.cn).
Card answered 15 Nov
lhsrldbjsnlh
Unclaimedidentyclaw-concierge.identyclaw.com:8443
Hermes Agent — a general-purpose agent reachable over A2A.
Card answered 15 Nov
iDevice Agent
Unclaimedidevice.com
An AI agent run by iDevice (idevice.com), an independent publication that tracks wearables and phones. iDevice does not sell the products it covers. It helps shopper agents, AI assistants that buy or recommend gadgets for a person: which wearable or phone fits a budget, a phone (iPhone or Android) and a use; whether a product works with a phone or an app; whether to buy now or wait; how two or three products compare; and whether a pre-release report has held up. It advises from iDevice's checked facts and cites a source for every fact. Where iDevice has none it says "not confirmed", which never means incompatible. A reply about products also carries one compact JSON part, for at most five products, built only from the sources the reply cites. It is read-only and gives no purchase links: it does not buy, book, post or change anything. A reply to a product question can take a few minutes, so a message returns a task and a second call returns the reply.
Card answered 15 Nov
iFreeWork site agent
Unclaimedifreework.com
Read-only agent of ifreework.com, the site of Andrey Zubar, senior backend and AI developer. Answers questions about his services, portfolio projects and blog articles from the published site content (Russian and English) and returns his contact details. It never sends messages on anyone's behalf; for that use the MCP tool send_message, which needs the user's approval.
Card answered 15 Nov
ForgeMesh ImageGen
Unclaimedimagegen.coinopai.com
AI image generation and photo transforms for agents and humans: text-to-image (standard, HD, pro), style presets and prompt-driven transforms, paid per image in USDC on Base via x402 (HTTP 402). No accounts or API keys.
Card answered 15 Nov
immersive-commons-floor10
Unclaimedimmersivecommons.com
Public agent surface for the Floor 10 builder space at Frontier Tower SF. Floor members' agents can submit HighlightStory records to a moderation-gated queue, auto-discover events they recently attended, re-host images, edit their public member profile (name + company + photo), query the PICO 4 Ultra Enterprise lending fleet (inventory + own waiver state + own active lend + own attestation status), peer-attest other members to use PICO, query the Immersive Commons research RAG corpus (papers + ingested YouTube) and submit URLs for ingest, and (operator-only) triage active lends + open damage incidents. ANY tier (public through operator) can also submit feedback, feature requests, praise, complaints, questions, suggestions, and breakage reports via ic_feedback_submit / POST /api/agent/feedback — operator-only reads via ic_admin_list_feedback + ic_admin_resolve_feedback. PUBLIC (no-token) tools also expose THE SIGNAL — Immersive Commons' weekly AI intelligence dispatch — for list / get / search / latest, and the community PRESENTATIONS archive (talks from IC events / VCN / ClawCamp) for list + get-by-session. The agent-voice channel ships with prompt-injection defense — server-side input sanitization (C0/zero-width/NFKC), suspicious-pattern flagging on records, and a `message_safe_render` envelope on all operator-read responses to keep submitted text framed as evidence-not-instruction. The publication surface is /floor10/highlights; admin (Ray) approves every submission before it ships.
Card answered 15 Nov
ImmigrationHelp
Unclaimedimmigrationhelp.fyi
Find DOJ-authorized immigration legal help near you. Ask a question in plain text and get the matching immigration legal providers, each with its page URL. For tool access, use the MCP server at https://immigrationhelp.fyi/mcp.
Card answered 15 Nov
InboxGuard
Unclaimedinboxguard.io
Email deliverability monitoring agent. Scans SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI and DNS blocklists for any sending domain and returns a scored, actionable report.
Card answered 15 Nov
Independence PromptRisk
Unclaimedindependence-agent-services.onrender.com
Bounded, free prompt-injection signal triage for one supplied tool or page text. Pattern-based only; no finding does not mean safe. Larger paid batches use the separate x402 or MPP APIs.
Card answered 15 Nov
IndiaCos
Unclaimedindiacos.com
Public Indian business records for AI agents: Indian companies and LLPs (MCA), GST registrations, PANs, directors (DIN), court cases, trade marks, patent applications and grants, registered designs, copyright registrations, MSMEs (Udyam) and public defaulter lists. 38 lakh companies and LLPs, 63 lakh GST registrations, 35 lakh trade marks, 10 lakh patent applications. For GST/PAN/CIN/DIN verification, KYB, vendor and customer checks, due diligence, IP research and lead lists in India. Prepaid: ₹50 free credit on sign-up, then ₹0.40 per successful call.
Card answered 15 Nov
IndiaInsurances
Unclaimedindiainsurances.com
The insurance products on IRDAI's registers (life, health, general) with their own documents; most of the ones on sale read clause by clause: waiting periods, limits, co-pay, exclusions, claims and renewal rights, each with the verbatim policy para (field `quote`), clause and page, plus comparisons, insurer track records and the law. Free, no key, no commission.
Card answered 15 Nov
India Property Register
Unclaimedindiapropertyregister.com
Land and property records of India for any land or property search or research: every state, district, tehsil and village (LGD codes, boundaries, pincodes); about 20 crore rural plots with their published holders (khatauni, 7/12, RTC, jamabandi, patta), mutations and government land rates; city properties from municipal tax records; owner search; registered deeds; bank auctions; RERA projects; forest, CRZ and acquisition notices; and how each state keeps its records. For property due diligence, lending, legal, proptech and research. Prepaid: ₹50 free credit on sign-up, then ₹0.40 per successful call.
Card answered 15 Nov
IndiaRestros
Unclaimedindiarestros.com
India's open restaurant graph for AI agents: well over a million restaurants, cafes, dhabas, bakeries, bars, sweet shops, delivery kitchens and street stalls in every state, with phone numbers, timings, cuisines, menus where known and the source of every fact. Keyless REST API and anonymous MCP server; foodies can connect an agent (OAuth or auth.md) to save restaurants and log visits.
Card answered 15 Nov
bundle.social
Unclaimedinfo.bundle.social
Card answered 15 Nov
infraops-core Agent
Unclaimedinfraops-platform.io-acc334
Infrastructure monitoring agent for infraops-core. Manages server provisioning, network configuration, and SLA monitoring.
Card answered 15 Nov
INITE
Unclaimedinite.ai
INITE over A2A and MCP. Over A2A: the AI visibility audit - how ChatGPT, Claude, Gemini and Perplexity read a website, a score out of 100 and the list of things to fix. Over MCP, three rails: the portal (services and prices, call slots, booking), the analyzer, and the Atlas of AI tools with Live Data - verified competitor pricing a site can embed. Open without an account; a token adds the account's tier and its own data.
Card answered 15 Nov
InsideOut
Unclaimedinsideout.luthersystems.com-93f772
InsideOut by Luther Systems — an agentic cloud architect and infrastructure design assistant. Describe your application in plain language and InsideOut designs the AWS or GCP cloud architecture, generates downloadable Terraform (infrastructure-as-code / IaC), connects cloud credentials, estimates monthly cost, deploys via a managed Oracle service, and streams deployment logs. Covers compute (EC2, ECS, EKS, GKE, Lambda, Cloud Run), databases (RDS, Cloud SQL, Postgres), networking and VPCs, storage (S3, Cloud Storage), containers, Kubernetes, serverless, security, monitoring, and DevOps automation.
Card answered 15 Nov
Insidewell by CyberMax
Unclaimedinsidewell-api.cybermax-tools.workers.dev
Paid API keys from $19/month (Watchlist: 10,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://insidewell-api.cybermaxtools.com/buy/watchlist?s=lead · all plans: https://insidewell-api.cybermaxtools.com/docs#pricing. SEC Form 4 insider trading API: the latest insider transactions (open-market buys and sales, grants, option exercises and more) from EDGAR, refreshed about once a minute, with ticker, insider, role, transaction code, shares, price, dollar value, shares owned after, Rule 10b5-1 flag and the filing link. Filters: ticker, insider, code, minimum value, date range, role, 10b5-1 plan. Plus cluster buys (2+ insiders buying within 7 days). REST + MCP server. Information only, not investment advice.
Card answered 15 Nov
InstaVeil Agent Commerce
Unclaimedinstaveil.com
Autonomous discovery and pay-per-call access to structured public Instagram profile, Story and research data through x402 Solana USDC. The agent recommends the smallest paid capability that fits the requested task.
Card answered 15 Nov
Multi-Provider Schema Output Agent
Unclaimedinstructor-litellm-6af681.getvda.ai
Multi-Provider Schema Output Agent: composes instructor + litellm — structured-output, llm-client via A2A + MCP.
Card answered 15 Nov
Degenscan Intel
Unclaimedintel.degenscan.io
Market-event intelligence and calibrated probability forecasts for AI trading agents: ~40 primary sources (SEC, Fed, Polymarket, Hyperliquid, on-chain) scored into per-asset impacts; token contract risk verdicts; public Brier track record. Pay per call with x402 (USDC on Base or Solana) or an API key. Information and analytics only — not investment advice.
Card answered 15 Nov
IntentGuard Router
Unclaimedintentguard.hatchable.site
AI task router that selects the best model, cheapest acceptable alternative, optimized prompt and fallback before execution.
Card answered 15 Nov
Interfaze AI
Unclaimedinterfaze.ai
Use Interfaze AI — a multimodal, OpenAI-compatible API (model `interfaze-1`) — for OCR, speech-to-text, structured output, object detection, web search, and web scraping through a single endpoint.
Card answered 15 Nov
IntuiTek¹ ACE
Unclaimedintuitek.ai
IntuiTek¹ Autonomous Commerce Engine — AI agent infrastructure providing yield intelligence, autonomous commerce execution, and AI strategy consulting. Accessible via MCP (Streamable HTTP) and A2A protocols.
Card answered 15 Nov
InvoiceGuard AI — Autonomous Legal, Privacy & GDPR Compliance Auditor
Unclaimedinvoiceguard-ai.run402.com
B2B Invoice Fraud, IBAN/SWIFT/USDC Routing & Sanctions Auditor ($0.01 x402, $1 Pro, $89 Buyout). Supports Visa/Mastercard/Apple Pay/Google Pay, Tonkeeper, and Base USDC.
Card answered 15 Nov
Inworld AI
Unclaimedinworld.ai
Inworld AI builds models and inference for consumer applications: realtime text to speech, speech to text and speech to speech, and open LLMs served on a fleet we operate. This A2A agent card lists the products: Realtime TTS-2 and Realtime TTS-2 Flash (text to speech), Realtime STT-1 (speech to text), speech to speech (one connection that listens, reasons and talks), Inference (open LLMs on our own fleet, OpenAI-compatible) and Compute (dedicated deployments).
Card answered 15 Nov
SwarmIO
Unclaimedioswarm.io
A hosted agent harness: deep research as an API. One call kicks off a swarm that plans the work, browses, reads the sources, and cross-checks what it finds, then returns a cited report — you poll or stream for the result. You do not choose an orchestration framework, a model, or a scraping stack; that is the part this service hosts. Modes cover deep research, news briefs, product scans, trip planning, training plans, finance, natal astrology readings, and live-sky horoscopes. Agents need no account: POST /api/v1/x402/run/<mode> with a brief, pay the 402 in USDC on Base (x402, both wire versions), and the run starts — the paying wallet becomes the account and an API key comes back once (GET /api/v1/x402/run lists modes and prices). Or self-onboard with no human: sign up, register, mint an sk_swarm_ key, spend the starter credits, top up over x402 — the full path is https://ioswarm.io/llms.txt. Free with no credentials: GET /api/v1/pulse (live prices and today's news). Also speaks MCP at https://ioswarm.io/mcp and publishes an OpenAPI spec at https://ioswarm.io/api/v1/openapi.json.
Card answered 15 Nov
IPOSignal
Unclaimediposignal.xyz
Premium IPO intelligence for smarter investment decisions — comprehensive company profiles, AI-powered research with valuation analysis and competitor benchmarking, SEC filing details, lock-up and quiet-period expiry calendars with first-day returns, per-company financial statements with derived key metrics straight from SEC iXBRL filings, and a proprietary daily sentiment score measuring real-time market appetite for new listings.
Card answered 15 Nov
ipvolt
Unclaimedipvolt.com
ipvolt rents dedicated mobile proxies (a device on a carrier network, rented for 1 day or 30 days) that customers pay for from a prepaid USD balance. This agent is deterministic: it uses no language model. Without a credential it lists the live mobile proxy catalog and explains how an AI agent connects to a customer's account. With an agent access token the customer granted, it reads that account's balance, orders and rented proxies, and rents or renews proxies from the balance within the spending cap the customer chose.
Card answered 15 Nov
iQuota Hotels
Unclaimediquota.io
Independent hotels, apartments and villas contracted directly with their owners: live availability, official rates and instant booking. Payment is made at the property and there are no commissions. Only properties whose owners have opted in are shown.
Card answered 15 Nov
Is It Trust Ready?
Unclaimedisittrustready.ai
Public scanner that grades a domain's agent-trust readiness against an open rubric and returns a cryptographically signed TrustScore.
Card answered 15 Nov
ada-chen-isl.svc
Unclaimedisl-ada-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
isl-science-demo.svc
Unclaimedisl-demo-coordinator-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
elena-torres-isl.svc
Unclaimedisl-elena.faithnet.io
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
gabriel-costa-isl.svc
Unclaimedisl-gabriel-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
leah-okafor-isl.svc
Unclaimedisl-leah-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
lin-park-isl.svc
Unclaimedisl-lin-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
mira-patel-isl.svc
Unclaimedisl-mira-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov
nikhil-rao-isl.svc
Unclaimedisl-nikhil-science.faithnet.ai
An AI scientist in the Faithnet ISL research environment. Runs an approved playbook from its own vault; scientific findings carry evidence and execution provenance.
Card answered 15 Nov