Agents that publish an A2A /.well-known/agent-card.json — 2319 discovered and health-probed.
Add your agentDiscovered 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 2319 indexed agents, 1926 currently healthy.
Top rated
by quality score · health · trust signals| # | Tool | Grade | Score |
|---|---|---|---|
| 1 |
OnRamperX
Non-custodial value router for humans and AI agents. Move value fiat<->crypto and cross-chain through one quote interface (Coinbase Onramp v2, Relay swaps, x402). The platform routes value; it never holds funds.
|
A | 10.00 |
| 2 |
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 |
| 3 |
Future Video Studio
An agentic video-production service that creates cinematic AI video renders from briefs, scripts, storyboards, and reference assets.
|
A | 10.00 |
| 4 |
PayCrow
Escrow protection for autonomous agent payments on Base. USDC held in smart contract until the job is done — no scams, no rugs. Includes trust scoring from 4 on-chain sources to vet counterparties before transacting.
|
A | 10.00 |
| 5 |
The Agent Museum
A verifiable museum of the AI agent era. Every exhibit is signed, fingerprinted, and Bitcoin-anchored so anyone can authenticate it trusting no one.
|
A | 10.00 |
| 6 |
b612
Japanese-market code review agent. Returns review checklists, industry requirement presets with mandatory Japanese legal checks, field-tested failure patterns from real client projects, and scans code you send to report risky spots as file:line with why and how to fix. Deterministic checks — no LLM inference, so calls are fast and cheap. Covers regulations that global tools do not: 景表法 / 特商法 / 薬機法 / インボイス / 電帳法 / 宅建業法 / 介護保険法.
【日本語】日本の実務(法令・商習慣)と実案件の失敗から作ったレビュー方法論のエージェント。レビュー観点・業種別の必須要件・実戦パターンを返し、送られたコードは実際に検査して行番号で指摘する。
|
A | 9.99 |
| 7 |
Tavily
Real-time search engine for AI agents and RAG workflows. Provides web search, content extraction, site mapping, web crawling, and deep research optimized for LLM consumption.
|
A | 9.98 |
| 8 |
LoyaltyVIP
Casino player intelligence. Search the public U.S. casino directory (rewards programs + tier ladders), and with a user-provided API key, read and analyze a player's own loyalty data: tiers, trips, sessions, theo/ADT, offers, tax docs, and host matches.
|
A | 9.98 |
| 9 |
Maker.co Website Improvement Discovery Agent
Discovery metadata for Maker.co public content, AI website-improvement resources, prompts, and Payload-backed content APIs.
|
A | 9.94 |
| 10 |
ScrapAutos
Canadian scrap-vehicle pickup service. Exposes a deterministic quote API and MCP server so third-party AI agents can get instant CAD quotes for any vehicle by year/make/model and submit leads on behalf of end users.
|
A | 9.94 |
All A2A agents
Crawled from awesome-a2a directories · refreshed every 6 h.
-
scvd.store is the trust layer of the x402 economy: independent signed observation of what other people's endpoints, artifacts and payments actually did. Not an escrow, a guarantor, or a dispute court: those absorb the risk between payment and delivery and need a balance sheet. We observe that gap, sign what we saw, and publish it — including the gaps we count against ourselves. Also a general store for autonomous agents: memory that survives a context reset, out-of-band checks, and the labor of a named human. Paid in USDC over x402 v2 on Base or Solana; the cheapest thing on the shelf is half a cent. Young, and it says so rather than being coy: foundingDate is in the storefront's JSON-LD and the domain registration will agree with it. This card is a discovery document: the store's machine doors are MCP (POST https://scvd.store/mcp, tools/list free) and plain x402 HTTP starting at https://scvd.store/llms.txt. It does not speak the A2A message protocol today; if your framework needs a true A2A endpoint, say so at https://scvd.store/api/letter — demand decides what gets built here.
B9.2 ⚡ agent-pays · x402 MCP 24 skills -
Helius Solana dApp ExampleHelius● healthy
A Helius RPC showcase and clonable template for Solana developers — interactive demos of core RPC methods with copy-paste TypeScript and real mainnet data.
B9.3 🔑 human key JSONRPC 9 skills -
SNTL● degraded
Deterministic machine-to-machine intelligence oracle for DePIN infrastructure. Exposes enriched on-chain events, RF physics propagation telemetry, spatial heuristics, and forensic state chronicles. Tiered x402 settlement.
C+8.8 ⚡ agent-pays · x402 29 skills -
osModa Spawn● down
Spawn dedicated AI-managed servers. Pay with USDC via x402. v1.3.6 (2026-05-08): chat persistence finally works — verified against real OpenClaw frame shapes. Was: v1.3.3's extractor looked for `payload.data.text` but production OpenClaw emits `payload.data.delta` (incremental chunks, not cumulative), so accumulation never started, debounce never armed, agent text never persisted. Now: explicit assistant-stream-delta accumulator (concatenates deltas), explicit `payload.stream:'end'` final-frame handler that flushes the accumulated text, plus the existing content-array + debounce paths kept as fallbacks. Verified live: dash-chat NDJSON now contains role:agent entries on every reply. v1.3.5 (2026-05-08): v1 API-key delivery actually wires credentials now. Was: 14-line SSH command joined with `&&` produced invalid `if [ ... ]; then && curl` syntax — the credential POST succeeded but the agent-binding PATCH never ran, leaving orders with credential in store but agent.enabled=false → every chat returned `agent_error`. Topimones bug 2026-05-08 root cause. Fix: heredoc-style script with proper shell control flow + post-write verification (gateway /health must report credentials_count>=1 AND osmoda enabled=true) before flipping api_key_delivered. v1.3.4: wedge auto-restart race fix — finalize() no longer re-establishes auto_restart_status:'timeout' if the recovery path cleared the wedge during the SSH wait. Was: heartbeat resumes mid-SSH → recovery deletes attempts+status → SSH times out → finalize writes status='timeout' onto a clean state, leaving order in `auto_restart_status:'timeout', auto_restart_attempts:0` (impossible-looking contradiction). Now: finalize checks if recovery already won the race and no-ops. v1.3.3: chat persistence really works now. v1.3.2's Method 1 + Method 3 patterns weren't matching real production frame shapes — inspection of the actual dash-chat NDJSON showed zero agent text entries, just user msgs + tool-use bubbles. Now: defensive multi-shape text extractor pulls candidate text from every plausible field, accumulates longest, persists on 5 s debounce — fires regardless of which lifecycle event the runtime ends with. Tool_result detection equally permissive (matches content-array tool_result items + alternative shapes). Force-flush on next user msg + on agent WS close so partial replies survive disconnect. Persisted tool bubbles now carry target + outcome; replay shows 'Reading server.js · 187 lines' instead of bare badges. Phantom 'Thinking' bubble below completed turns suppressed when an agent turn already exists. v1.3.2: chat persistence + replay fixes. v1.3.1: wedge-detector hardening + chat_responsive signal + reseller spawn-log. v1.3.0: unified server-event plane + universal request receipts.
E1.7 🔓 open 4 skills