{"adoption": {"forks": 85, "observed_at": "2026-08-28T04:03:56.251864+00:00", "stars": 1192}, "canonical_url": "https://ross.abutalabs.com/products/commerceagentbench", "card": {"archived": false, "artifact_type": "dataset", "description": "CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services", "domain": ["artificial-intelligence", "e-commerce", "large-language-models", "developer-tools"], "enriched": true, "function": ["benchmarking", "agent-framework", "testing", "mcp"], "health_score": 80, "homepage": "https://commerce-agent-bench.site.accio.ai/", "language": "HTML", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Accio-org/CommerceAgentBench"], "name": "Accio-org/CommerceAgentBench", "platform": ["python", "cli"], "pushed_at": "2026-08-24T03:20:19+00:00", "repo": "Accio-org/CommerceAgentBench", "stars": 1192, "tags": ["agent-evaluation", "llm-benchmark", "stateful-mocks", "long-horizon-tasks", "reproducibility", "leaderboard", "commerce-workflows", "containerized-eval", "ai-agents", "docker", "web-server"], "topics": [], "urls": [], "use_cases": ["benchmark llm agents on real-world commerce workflows", "evaluate long-horizon agent task completion", "compare models on browser, CLI, and API/MCP tasks", "test agents against stateful replicas of real web services", "measure agent reliability with reproducible verifiers", "run cross-harness agent evaluations"], "what_it_is": "CommerceAgentBench is a benchmark of 107 long-horizon agent tasks evaluated in high-fidelity, stateful, reproducible replicas of real online services (Shopify, Gmail, Stripe, Jira, etc.). It ships containerized task environments with deterministic or LLM-assisted verifiers and a public leaderboard for comparing model-harness pairs.", "when_to_avoid": ["you need a lightweight single-turn QA benchmark", "your domain is unrelated to commerce or business workflows", "you want a benchmark that runs without container infrastructure"], "when_to_choose": ["you need reproducible, stateful evaluation of agents on multi-step business workflows", "you want to compare LLMs on browser, CLI, and API/MCP task execution", "you need deterministic or LLM-assisted grading of agent outcomes"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/commerceagentbench", "repo": "Accio-org/CommerceAgentBench", "role": "main", "score": 57}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.251864+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:22:26.831417+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "65769d00216708d83df8cdf84ea6693d3706618d388741b731bd646bb5e8a8f8", "fetched_at": "2026-08-28T04:03:56.251864+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Accio-org/CommerceAgentBench"}, {"content_hash": "fd4e8d205cecfd2b3ac19b1be2f28f3c41b100524869d706382d3476585563cd", "fetched_at": "2026-08-29T12:29:45.682759+00:00", "kind": "homepage", "missing": false, "url": "https://commerce-agent-bench.site.accio.ai/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 2, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 31, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 57, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}