{"record": {"aliases": ["ai-agent-infrastructure-benchmark"], "artifacts": [{"id": "gh:aah20/ai-agent-infrastructure-benchmark", "kind": "repo", "url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}, {"kind": "website", "url": "https://a2zsoc.com/"}], "categories": ["Agents", "Language & Knowledge", "Software & AI Compute"], "description": {"en": "Evaluates AI agent infrastructure across isolation, identity, network, authority, durability, observability, and unit economics using weighted scores with hard safety gates."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/AAH20/ai-agent-infrastructure-benchmark", "source": "claire_radar", "source_url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark", "title": "AgentInfraBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:aah20/ai-agent-infrastructure-benchmark", "modality": null, "name": "AgentInfraBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "true", "origin_record_id": "bm_ai-agent-infrastructure-benchmark_aa5659e0", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "78a127c4a981a00df004641d99cc02dfb62b6a0159a16503e1583fbcf9781943", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-08T16:33:53.925756Z", "source_url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}, "publisher": null, "released": "2026-09-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:aah20/ai-agent-infrastructure-benchmark", "source_url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-aah20-ai-agent-infrastructure-benchmark", "source": "claire_radar", "source_benchmark_id": "github:aah20/ai-agent-infrastructure-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["ai-agent-infrastructure-benchmark"], "annotation": "Machine Generated", "applicationDomains": ["Software & AI Compute"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/AAH20/ai-agent-infrastructure-benchmark", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Niche focus on AI agent infrastructure benchmarking with transparent fixtures may initially attract a small technical audience.", "score": 18}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T16:33:53.925756Z", "inputHash": "d1bc6bec7e696d2c491eb192810dd6069511c3bccd2d660edf8038942d9d98a1", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# AI Agent Infrastructure Benchmark ## AgentInfraBench", "canonicalNameSource": "official_readme", "decisionReason": "The repository defines a repeatable benchmark with explicit scoring weights, hard gates, and a public runner, satisfying criteria for a reusable public benchmark.", "evaluationEvidence": {"reuse": "python3 -m agentinfrabench.cli run \\ scenarios/remote-futrx-documented.json \\ --output generated/remote-futrx", "scoring": "| Dimension | Weight | Key signals | |---|---:|---| | Isolation | 22% | kernel boundary, tenant separation, resource ceilings |", "task": "workload + platform observation + evidence provenance -> hard safety gates -> weighted benchmark dimensions -> fully loaded unit economics -> JSON + Markdown + SARIF + JUnit evidence"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T16:33:53.925756Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates AI agent infrastructure across isolation, identity, network, authority, durability, observability, and unit economics using weighted scores with hard safety gates.", "discoverySources": [{"id": "github:aah20/ai-agent-infrastructure-benchmark", "type": "github", "url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}, {"id": "github:aah20/ai-grc-automation-benchmark", "type": "github", "url": "https://github.com/AAH20/ai-grc-automation-benchmark"}], "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "ai-agent-infrastructure-benchmark Open benchmark for AI agent infrastructure security, sandbox isolation, recovery, evidence quality and cost per accepted outcome."}, "familyId": "bmf_2ce2665becd9", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_ai-agent-infrastructure-benchmark_aa5659e0", "indexedAt": "2026-09-07T06:22:04.880155Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/AAH20/ai-agent-infrastructure-benchmark", "project": "https://a2zsoc.com/"}, "metrics": [], "motivation": "ai-agent-infrastructure-benchmark Open benchmark for AI agent infrastructure security, sandbox isolation, recovery, evidence quality and cost per accepted outcome.", "name": "AgentInfraBench", "oneLine": "Evaluates AI agent infrastructure across isolation, identity, network, authority, durability, observability, and unit economics using weighted scores with hard safety gates.", "paperTitle": "ai-agent-infrastructure-benchmark", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/AAH20/ai-agent-infrastructure-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:04.880155Z"}, "publications": [], "publishers": [{"name": "AAH20", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 206, "score": 23}, "method": "attention-ranking-v13", "rank": 206, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 470, "score": 23}, "method": "attention-ranking-v13", "rank": 470, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-05", "source": {"authors": ["AAH20"], "categories": [], "id": "github:aah20/ai-agent-infrastructure-benchmark", "publicSignals": {"githubStars": 0}, "title": "ai-agent-infrastructure-benchmark", "type": "github", "url": "https://github.com/AAH20/ai-agent-infrastructure-benchmark"}, "sourceUpdatedAt": "2026-09-05T13:55:38Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Provides procurement-grade scorecards that compare security, isolation, recovery, evidence quality, and cost per accepted outcome beyond token-price metrics."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
