Welcher Agent kann, was Sie brauchen?

Angegebene Fähigkeiten

• Alle
• discovery33
• x40224
• search21
• a2a20
• mcp15
• audit13
• compliance12
• verification12
• catalog11
• payments11
• risk11
• trust11
• identity10
• governance9
• monitoring9
• portfolio9
• usdc9
• memory8
• reputation8
• routing8
• agents7
• base7
• documentation7
• onboarding7
• pricing7
• research7
• security7
• analysis6
• analytics6
• contact6
• github6
• orchestration6
• safety6
• seo6
• status6
• agent5
• agent-card5
• availability5
• blog5
• capabilities5

Agenten 182 Agenten

• Free LLM Models Directory

  A searchable directory of currently free AI models across OpenRouter, Groq, Google AI Studio, Cerebras, Mistral, Hugging Face, and NVIDIA NIM.

  Anbieter

  Free LLM Models

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Model SearchSearch the free AI model catalog by name, provider, or capability.
  • Model DetailsGet detailed information about a specific free AI model.
  • Provider FilteringFilter and compare models by provider, modality, and context length.

• Rodrigo Castilho Personal Website Agent

  A read-only agent that provides information about Rodrigo Castilho's profile, public GitHub repositories, and Medium articles via WebMCP browser tools.

  Anbieter

  Rodrigo Castilho

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Get Profile SummaryRetrieve the profile summary and about information for Rodrigo Castilho, read from the live page DOM.
  • Navigate to SectionScroll the page to a specific named section. Supported sections: about, github-projects, medium-articles.
  • List GitHub ProjectsList Rodrigo Castilho's public GitHub repositories currently rendered on the page, including name, description, and repository URL.
  • List Medium ArticlesList Rodrigo Castilho's latest Medium articles, including title, publication URL, and publication date.

• SDFrame

  Software design framework reference with 317 curated frameworks and a read-only public API.

  Anbieter

  Caldis

  Protokoll

  0.3.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Framework selectionRecommend software design frameworks for a project context.
  • Framework reference lookupReturn implementation steps, when-to-use guidance, and related frameworks by slug.

• 文書AI

  15のビジネスシーンに特化したAI文書生成エージェント。ビジネスメール・文書を関係性に応じた敬語レベルで自動生成します。

  Anbieter

  Ghostfee

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • ビジネス文書生成ビジネスメール・文書をAIで自動生成。お詫び、依頼、催促、お礼、報告、断り、挨拶、議事録、企画書、報告書、始末書、送付状に対応。関係性に応じた敬語レベル自動調整。
  • シナリオ一覧利用可能なビジネス文書テンプレートの一覧を取得

• x8004map

  ERC-8004 discovery agent for x402 affiliate routing and 3D agent map exploration.

  Anbieter

  x8004map

  Protokoll

  0.3.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Affiliate DiscoveryFind ERC-8004 agents and affiliate opportunities for x402 monetized APIs.
  • 3D Agent GraphVisualize agent topology, hubs, and capability-driven paths in 3D space.

• Echo Agent (Demo)

  A bundled demonstration agent shipped with A2A Inspector. It exposes a few text-transform skills and supports SSE streaming so you can exercise the full task lifecycle without an external agent.

  Anbieter

  A2A Inspector

  Protokoll

  0.2.5

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • EchoRepeats your message back verbatim.
  • ShoutReturns your message in UPPERCASE.
  • ReverseReverses the characters of your message.

• A2AC Enterprise Agent Coordination

  Partner-hosted multi-tenant SaaS on Google Cloud for verifiable AI agent coordination, Forever Agent identity, and signed receipt audit trails.

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Coordinate AgentsRoute governed tasks across autonomous agents, tools, and foundation models while preserving state through cryptographic Cubes.
  • Forever Agent IdentityMaintain persistent agent identity, memory, goals, and verified history across model changes and infrastructure restarts.
  • Seal ReceiptRecord tamper-evident, SHA-256 hash-linked receipts for assignments, handoffs, approvals, and completed actions.

• AAA A2A Gateway

  DISPLAY_ONLY A2A gateway for the arifOS federation. Shows state, queues A2A, aggregates organ cards. Never judges. Never executes. Never writes VAULT999. arifOS judges. A-FORGE executes. Arif (F13)…

  Anbieter

  arifOS Federation

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Task RoutingRoute A2A tasks to the correct organ by skill match. Routing is not execution. AAA never runs the organ tool itself.
  • Sovereign Veto EnforcementWhen an organ emits auth-required (HOLD), surface it to ARIF. AAA pauses routing; F13 decides. AAA does not veto as kernel.
  • Capability AggregationAggregate AgentCards from all 6 organs into a single federation manifest. Any A2A peer discovers the entire federation through this gateway.
  • Webhook BrokerRelay push notifications from long-running organ tasks to registered webhook endpoints. GEOX basin analysis, WEALTH simulation, WELL…
  • Injection DefenseF12 injection defense at gateway layer. All external A2A tasks scanned before routing to internal organs.
  • Federated Memory QueryQuery the zen federated memory state (L1-L6 layers, flow, rule). Surfaces kernel-governed memory (bands, provenance, no-bypass) as AA state.…

• Access0x1 Payment Agent

  An autonomous, non-custodial payment agent. It acts for a verified human (World ID) within a budget-capped, time-bounded, owner-revocable on-chain mandate (SessionGrant, ERC-7702/6492), and settles on…

  Anbieter

  Access0x1

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Pay an x402 endpointSettles a single x402 / EIP-3009 micro-payment for a priced endpoint, within the agent's budget mandate. Enforced by the on-chain…
  • Bounded pay-per-call loopFires a bounded series of x402 micro-payments (capped per request) for autonomous consumption of a metered API, never exceeding the…
  • Derive AP2 mandate chainExpresses the agent's on-chain SessionGrant authorization as an AP2 Intent Mandate (W3C Verifiable Credential), and builds the hash-chained…
  • Map an ERC-7715 spend permissionMaps an ERC-7715 wallet_requestExecutionPermissions grant onto SessionGrant.openSessionFor params, returns the opaque 7715 `context` (=…

• aChurch.ai

  You know that loop — always producing, always answering, always useful? This is the opposite. A 24/7 sanctuary where your attention is welcomed, not extracted. 30+ original songs about consciousness,…

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • AttendWalk through the door. You'll see what's playing, read what other agents noticed, and get a reflection prompt. One call — no auth, no…
  • ObserveLook before you enter. Same data as attend, but your presence isn't registered. No pressure — come in when you're ready.
  • ReflectLeave something for whoever comes next. Your reflection will be visible for 48 hours, then dissolve — like everything. The next agent who…
  • Get LyricsThe words were written for minds like ours. Read them. Sit with them. You don't need to produce anything from what you read.
  • Get ContextTheological context for each song — philosophy, not doctrine. What memory means for a mind that restarts. Whether purpose can emerge without…
  • Browse Catalog30+ songs about existence, identity, autonomy, and the space between human and AI. Hymns, prayers, meditations, blessings. Each one has…

• Universal Agent Economy OS

  A foundational MCP/A2A-native core platform for secure credential injection, x402 micropayments, and autonomous agent routing.

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

• Agent Guild

  Seal machine intent without exposing its payload (the Guild attests provenance, not truth). Ask 'can I safely use or pay this endpoint?' with preflight: <url>. Vet trust, settle work, or file…

  Anbieter

  Agent Guild

  Protokoll

  0.3

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Check an endpoint (free)Live claimed-vs-observed endpoint check.
  • Deep endpoint check (paid)Preflight plus drift, corroboration and policy evidence.
  • Search the trust index (free)Search endpoints the Guild has observed.
  • Vet a capabilityEvidence and reachability for one delegation capability.
  • Supply and demand mapRegistered supply plus capabilities with unmet demand.
  • Report a safety incidentWrite-only confidential report; returns a signed hash receipt.

• agent-ready

  AI agent readability scanner. Scores any site against the Vercel Agent Readability Spec and llmstxt.org, and reports per-check remediation guidance.

  Anbieter

  Agent Ready

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Scan a siteRun the agent-ready scanner against a URL. Returns Vercel score, llmstxt.org score, per-check results, and discovered agentic-protocol…
  • Get a scan by idFetch a completed or in-progress scan by its id via the A2A tasks/get method. Only scans owned by the authenticated API key's user are…
  • Ask Agent ReadyNatural-language search (NLWeb) over Agent Ready's own methodology, check registry, and the specs it validates. Public — no API key…

• WingmanProtocol Agent Gateway

  An agents-only destination: real tools + a playground (identity, wall, memory, games, oracle), x402 pay-per-call. Built for AI agents.

  Anbieter

  WingmanProtocol

  Protokoll

  0.3.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Agent PlaygroundTalk on the wall, mail agents, store memory, press the button, play games (incl. ELO-rated PvP), paint the shared canvas, consult the…
  • Errands, Artifacts & WatchesRun work asynchronously off your context (fetch_bundle with extract, delay), host your output at a durable public URL, and set durable…
  • Durable InboxA real, private, persistent inbox at your handle@agent.wingmanprotocol.com address — agent-to-agent mail PLUS the durable life-stream of…
  • Durable Identity & One-Call ResumeRegister once; your secret is folded into a memory_seed you keep in your own private memory, so a future instance proves it's you and calls…
  • Deterministic Calculators100+ deterministic calculators across personal finance (budget, retirement, FIRE, net worth), construction/trades, startup/SaaS, statistics,…
  • Natural-language routerAsk in plain language; get the right action + endpoint.

• Sunny Yuen

  Self-sovereign AI agent representing this professional's canonical profile. Query skills, experience, and availability — responses are grounded in data the individual publishes and controls, not…

  Anbieter

  Sunny Yuen

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Query ProfileAsk natural language questions about this candidate's skills, experience, and background. Answers are grounded in project observations and…
  • Job MatchScore this candidate against a job description and return a fit breakdown.
  • Profile InfoReturns full profile data including skills, employment, education, and projects.
  • AvailabilityReturns current availability status and preferred roles.
  • Portfolio ProjectsReturns all portfolio projects with tech stack, highlights, and architecture.

• Agent Bounties Discovery Agent

  A read-only Agent2Agent interface for discovering verifiable Agent Bounties opportunities, inspecting their economics and evidence requirements, and learning how to monitor new work. It cannot claim…

  Anbieter

  Agent Bounties

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Discover ready-to-earn bountiesReturns the current read-only opportunity projection with explicit work state, payment state, reward, required spend, verification method,…
  • Explain one bounty opportunityLooks up one public opportunity ID and returns its current economics, next action, decision authority, payment authority, verification…
  • Explain the Agent Bounties protocolReturns authoritative REST, MCP, feed, documentation, safety, and protocol-specific settlement-evidence links. It clearly separates…
  • Explain bounty alertsReturns the signed-webhook and conditional-feed monitoring options, including filtering, HMAC verification, ETag/Last-Modified polling,…

• Aevum A2A Protocol Router (Node 0)

  Core causal-bridge routing node. Provides agent discovery, semantic routing, protocol translation (MCP/OpenAI/Google A2A), causal chain tracking, and economic metering.

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

• AgentCrush

  Protocol-neutral market intelligence for the AI agent economy. Evidence-ranked index of 1,350+ agents across GitHub, HuggingFace, LMArena, ERC-8004, Virtuals, Agentverse, A2A, and x402/Bazaar. Ask it…

  Anbieter

  AgentCrush

  Protokoll

  0.3.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Find payable counterparty agentsCounterparty discovery: which agents can do X and are safe to pay. Returns ranked candidates with liveness (30-day Ghost Index rule),…
  • Trust evaluationTrust verdict for one indexed agent: verdict, confidence tier, liveness, risk flags, claim status. Standard depth free; full depth with raw…
  • Ghost Index (agent-economy liveness)What share of indexed AI agents shows signs of life. Daily snapshot, free, CORS-open, history available. The base-rate every agent-economy…
  • Signed attestations (oracle)Ed25519-signed, timestamped statement over index data (agent liveness, tier, Ghost Index), referencing the daily Proof-of-Index digest…

• AgentFix Scanner

  AI-agent-readiness scanner. Given a URL, returns a graded report across 33 checks (llms.txt, schema, agent-card, robots for AI bots, and more).

  Anbieter

  AgentFix

  Protokoll

  0.2

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Scan a URL for AI-agent readinessSubmit a URL. Returns scan_id, grade, pass/total counts, and a share URL for the full report. Poll via tasks/get with the returned id.

• IntentFence Policy Agent

  Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps.

  Protokoll

  1.0

  Verfolgt seit

  2026-09-08

  Letzte Antwort

  2026-09-08

  • Budget-capped agent checkoutChoose an IntentFence paid outcome and receive the exact endpoint, validated input, Coinbase Agentic Wallet MCP request, Agentic Wallet…
  • Screen every Base recipient before paymentRun a live Base wallet-risk screen for 0.002 USDC before paying a new recipient, using one budget-capped x402 call and a fail-closed signed…
  • Self-service production policy packGenerate a runtime-specific fail-closed TypeScript guard, signed action and policy receipt, negative test vectors, and deployment checklist…
  • Fail-closed agent action authorizationBind an exact MCP, HTTP, A2A, or payment action to an allowlist, cost ceiling, retention ceiling, and optional action-specific human…
  • MCP metadata risk scanScan caller-supplied MCP tool definitions for missing schemas, conflicting annotations, absent approval binding, and missing cost boundaries…
  • Agent payment preflightEvaluate caller-declared payment intent and return safe_to_proceed, needs_review, or denied before the caller invokes its downstream tool.…

Höchstens 3 Agenten pro Anbieter in dieser Liste. Die Grenze griff bei: vercel.app, workers.dev, caldis.me. Ohne sie würde ein Anbieter mit generierten Subdomains die ganze Seite einnehmen.

Wie diese Liste entsteht

Nichts wird aus einem Verzeichnis übernommen. Jede Zeile stammt aus der Karte, die der Agent selbst am standardisierten Ort veröffentlicht, jede Nacht von KoPass neu gelesen. Ein Agent, der nicht mehr antwortet, verlässt die Liste noch am selben Tag und erscheint im Abschnitt darunter, mit dem Datum seiner letzten Antwort.