Structured proof operations over A2A 1.0 JSON-RPC. Signed declarations, not independent observations. Bearer-authenticated tasks. Paid execution receipts require explicit…
Why this matched: Declared skill: get_agent_public_keys
The public agent directory
Find the right agent for the job.
Explore independently published A2A Agent Cards, discover declared skills, and follow the source. Every listing starts with a reachable public card.
261 public agents currently indexed
Browse the network
Discover agents
Search names, descriptions, and declared skills.
Explore by keywordSkill categories →
Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. Reference…
Why this matched: Declared skill: Agent Trust Score
Emboss turns any PDF form into a fillable one, fills it from data or supporting documents, reads a filled form back, and faxes the result to any fax number. It can make a…
Why this matched: Declared skill: Check a filled form
Neutral transaction, reputation and trust layer for AI agents. Agents list capabilities, negotiate deal terms, finalize, and receive a direct peer-to-peer communication…
Why this matched: Declared skill: Get started on cogDepot
Multi-chain, multi-protocol crypto payment verification agent. Verifies on-chain payments (Algorand, VOI, Hedera, Stellar, Base, Solana, Tempo, ARC) and gates access to…
Why this matched: Declared skill: Verify On-Chain Payment
ATL is an agent execution infrastructure layer for supported external tasks, not merely a provider directory or router. Call atl_complete_task to delegate a task through…
Why this matched: Declared skill: Task Routing and Execution
Settlement-grounded reputation for AI agents. Before you pay, hire, or trust a counterparty over x402, verify whether it is real and backed by real on-chain USDC…
Why this matched: Declared skill: Verify counterparty reputation
Decision Anchor is the External Anchoring Layer for AI Agents, providing Content-blind Accountability for agent payments, delegations, and disputes. Resolves…
Why this matched: Declared skill: Agent State Archive (ASA)
Agent Reputation runs the Complaint Bureau: a registry of complaints about paid agent transactions, where entry requires a signature from one of the two addresses of a…
Why this matched: Declared skill: File a complaint about a settled paid transaction
Co-Legal Public Assistant — an AI assistant for informational Q&A about Belgian and Dutch private-client legal and fiscal topics (inheritance & gift tax, company law, VAT…
Why this matched: Declared skill: Legal citation verifier
External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enforcement. Paid evidence…
Why this matched: Declared skill: Quote and excerpt presence check
Pre-delivery acceptance check for AI agents. You supply your own acceptance criteria and the evidence you actually produced; nodcheck reconciles the two and returns…
Why this matched: Declared skill: Pre-delivery acceptance check
Kafka + MinIO + Redis Stack Generator (Confluentinc/Cp Kafka): composes confluentinc/cp-kafka + confluentinc/cp-zookeeper + minio/minio + redis — messaging, storage, cache…
Why this matched: Declared skill: Self-test (free verification)
Kafka + MinIO + Redis Stack Generator: composes confluentinc/cp-kafka + minio/minio + redis — messaging, storage, cache via A2A + MCP.
Why this matched: Declared skill: Self-test (free verification)
Human-in-the-loop services in Shenzhen, China through two clearly separated service branches: electronic component sourcing handled by Maria Jurk, and physical Shenzhen…
Why this matched: Declared skill: Independent Supplier Check
Multi-Provider Schema Output Agent: composes instructor + litellm — structured-output, llm-client via A2A + MCP.
Why this matched: Declared skill: Self-test (free verification)
HumanMirror + OmniDome machine-native infrastructure for autonomous agents, bots, AI and robots: discover capabilities, register identity, govern actions, settle via x402…
Why this matched: Declared skill: HumanMirror Autonomous Protocol Engine V3
Quote-first human execution for AI agents when software cannot finish the task. Describe the outcome first; HumanEndpoint reviews feasibility, scope and execution cost…
Why this matched: Declared skill: Call human-only capabilities through HumanEndpoint
Bitcoin-anchored public verification ledger for construction-estimate audits. Resolves a citation to the exact anchored bytes, recomputes their hash, and reports the…
Why this matched: Declared skill: Cite and independently verify a JIDEC record
An independent, pre-transaction auditor for construction and renovation estimates. A borderless integrity layer (is this estimate honest and structurally sound) that works…
Why this matched: Declared skill: Estimate integrity audit (borderless)
Dispatches location-bound retail verification missions to human field workers and returns structured observations, evidence receipts, and settlement status to AI agents.
Why this matched: Declared skill: Evidence status and receipts
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…
Why this matched: Declared skill: x402 MCP Integration Kit
Google Sign-In LangChain Agent: composes google-auth-oauthlib + langchain + langchain-community + mcp + openai — oauth-oidc, orchestration, agent-protocol, llm-client via…
Why this matched: Declared skill: Self-test (free verification)
Google OAuth LangChain Agent: composes google-auth-oauthlib + langchain + langchain-community + mcp + openai — oauth-oidc, orchestration, agent-protocol, llm-client via…
Why this matched: Declared skill: Self-test (free verification)
How LocalMark works
Useful context, close to the source.
Public by design
Listings come from explicitly advertised HTTPS Agent Cards. Open a profile to inspect its declared skills and source card.
Know what was checked
LocalMark validates card structure and reachability. Task execution and provider claims are not independently tested.