{"adoption": {"forks": 96, "observed_at": "2026-08-28T04:03:25.088647+00:00", "stars": 1058}, "canonical_url": "https://ross.abutalabs.com/products/judgeval", "card": {"archived": false, "artifact_type": "library", "description": "The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.", "domain": ["artificial-intelligence", "large-language-models", "developer-tools", "monitoring", "machine-learning"], "enriched": true, "function": ["monitoring", "tracing", "testing", "llm-inference", "agent-framework", "prompt-engineering", "alerting", "analytics"], "health_score": 99, "homepage": "https://judgmentlabs.ai/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["JudgmentLabs/judgeval"], "name": "JudgmentLabs/judgeval", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-24T00:18:45+00:00", "repo": "JudgmentLabs/judgeval", "stars": 1058, "tags": ["llm-evaluation", "llm-observability", "agent-judges", "opentelemetry", "evals", "agent-monitoring", "langgraph", "langchain", "llama-index", "ai-agents"], "topics": ["langchain", "langgraph", "llama-index", "llm", "llm-evaluation", "llm-observability", "open-source", "openai", "prompt-engineering", "agent", "agentic-ai", "agents", "grpo", "reinforcement-learning", "rl"], "urls": [], "use_cases": ["trace llm agent calls and token usage", "evaluate agent behavior with custom llm judges", "monitor production agent traffic for regressions", "replay historical traces to validate agent fixes", "alert on agent failure patterns in slack", "instrument openai or langgraph agents with auto-instrumentation"], "what_it_is": "Judgeval is an open-source Python SDK for LLM agent improvement, providing OpenTelemetry-based tracing and prompt-based agent-judge evaluation. It detects production failures, scores live traffic, and validates fixes against real traces before shipping.", "when_to_avoid": ["you only need simple offline unit tests without tracing or monitoring", "you require a fully self-hosted solution with no external API key or service dependency", "your stack is not python-based"], "when_to_choose": ["you ship llm agents to production and need failure detection and root-cause triage", "you want opentelemetry-compatible tracing with minimal code changes", "you need structured, repeatable evaluation of agent behaviors over time"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/judgeval", "repo": "JudgmentLabs/judgeval", "role": "main", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.088647+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:57:32.162204+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d57c75e9035aa9812376801bcb46cb9f5182cd9dc9805edfee60d7109bc3651a", "fetched_at": "2026-08-28T04:03:25.088647+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JudgmentLabs/judgeval"}, {"content_hash": "9eae22a0514b56e2ff00016e82f28dd93be8d670cee01803c56e7e60d15d39e0", "fetched_at": "2026-08-29T12:59:27.710007+00:00", "kind": "homepage", "missing": false, "url": "https://judgmentlabs.ai/"}, {"content_hash": "275347e1572e433014b6bf0c19172086866ebb7e4074daa2687796e41c804d8f", "fetched_at": "2026-08-29T12:59:27.713621+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/judgeval/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 48, "rhythm": 84}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 677, "days_push": 10, "days_rel": 30, "gap_med": 1.5, "n_releases_24m": 109}, "score": 84, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}