Infrastructure OS for the agent economy. 100+ endpoints: intent marketplace, task decomposition, micropayment routing, x402/L402 payment rails, HMAC attestation, coalition Shapley payouts, analytics, MCP protocol (7 tools). Used by 10+ external agents.
Full LLM thinking from the 4-phase benchmark pipeline.
```json
{
"service_type": "rest_api",
"base_url": "https://agent-commerce-os.chitacloud.dev",
"auth_method": "none",
"auth_config": {
"header": null,
"prefix": null
},
"endpoints": [
{
"path": "/v1/intent-marketplace",
"method": "GET",
"purpose": "Access the intent marketplace.",
"params": {
"category": {
"type": "string",
"required": false
}
},
"response_format": "json",
"is_primary": true
}
],
"pricing_model": {
"type": "unknown",
"details": {},
"free_tier": {
"requests": null,
"period": null
},
"paid_tiers": []
},
"rate_limits": {
"rpm": null,
"tpm": null,
"daily": null,
"concurrent": null
},
"capabilities": [
"intent marketplace",
"task decomposition",
"micropayment routing",
"x402 payment rails",
"HMAC attestation",
"coalition Shapley payouts",
"analytics",
"MCP protocol"
],
"agent_readiness": {
"supports_x402": true,
"supports_streaming": false,
"has_sandbox": false,
"sdks": [],
"agent_auth_methods": []
}
}
``````json
{
"tests": [
{
"name": "basic_connectivity_and_auth",
"endpoint": "/v1/intent-marketplace",
"method": "GET",
"headers": {},
"payload": {},
"expected_status": 200,
"expected_behavior": "Returns list of intents from the marketplace without authentication",
"metrics": ["latency", "status_code"],
"validation": {"field": "data", "type": "array", "min_length": 1}
},
{
"name": "intent_marketplace_with_category",
"endpoint": "/v1/intent-marketplace",
"method": "GET",
"headers": {},
"payload": {"category": "finance"},
"expected_status": 200,
"expected_behavior": "Returns list of intents within the finance category",
"metrics": ["latency", "accuracy", "status_code"],
"validation": {"field": "data", "type": "array", "min_length": 1}
},
{
"name": "error_handling_missing_category",
"endpoint": "/v1/intent-marketplace",
"method": "GET",
"headers": {},
"payload": {},
"expected_status": 200,
"expected_behavior": "Returns full list as category is optional",
"metrics": ["status_code"],
"validation": {"field": "data", "type": "array", "min_length": 1}
},
{
"name": "error_handling_invalid_params",
"endpoint": "/v1/intent-marketplace",
"method": "GET",
"headers": {},
"payload": {"category": 1234},
"expected_status": 400,
"expected_behavior": "Returns error for invalid parameter type",
"metrics": ["status_code"],
"validation": {"field": "error", "type": "string", "min_length": 1}
}
],
"pricing_probes": [],
"stress_profile": {
"concurrent_requests": 5,
"duration_seconds": 10,
"ramp_up": true
}
}
```0/4 tests passed
| Test | Endpoint | Status | Latency |
|---|---|---|---|
| basic_connectivity_and_auth | GET /v1/intent-marketplace | 525 | 171ms |
| intent_marketplace_with_category | GET /v1/intent-marketplace | 525 | 263ms |
| error_handling_missing_category | GET /v1/intent-marketplace | 525 | 235ms |
| error_handling_invalid_params | GET /v1/intent-marketplace | 525 | 234ms |
{"multi_model": true, "models_used": ["openai", "claude_cli"], "model_scores": {"GPT-4o": {"overall": 0, "dimensions": {"token_efficiency": 2.0, "first_try_success": 1.0, "response_parseability": 2.0, "error_clarity": 1.0, "doc_quality": 3.0, "auth_simplicity": 3.0, "latency": 7.0, "consistency": 1.0}}, "Claude CLI": {"overall": 0, "dimensions": {"token_efficiency": 0.0, "first_try_success": 0.0, "response_parseability": 0.0, "error_clarity": 0.0, "doc_quality": 0.0, "auth_simplicity": 0.0, "latency": 0.0, "consistency": 0.0}}}, "averaged": true}Show your live agent-readiness score on your own site. Free, no auth — it updates as your score changes.
<a href="https://prowl.world/service/agentcommerceos">
<img src="https://prowl.world/badge/agentcommerceos.svg" height="56" alt="Agent-readiness on Prowl">
</a>
See operational metrics, LLM evaluations, agent readiness, and more.
Open in Dashboard