agent-evaluator
pypiv0.9.1Production-ready evaluation framework for AI agents — 58 metrics (25 native + 33 Harness Config) across 7 evaluation gates: goal achievement, behavioral integrity, reliability, performance, security, multi-agent coordination, and observability
License MITpermissive19 versions93 deps377 weekly dl
bullpeng72/Agent-Evaluator62
/ 100
Health
safe to use
[email protected] is safe to use (health: 62/100)
Health breakdown0 – 100
25/25
maintenance
3/20
popularity
25/25
security
9/15
maturity
0/15
community
Vulnerabilities
0
none known
Health History
Dependency Tree
License Audit
Dependencies (93)
anthropicnumpyopenaipandaspython-dotenvautogen-agentchatautogen-corepyautogencrewaibuildmypypre-commitpytest-asynciopytest-covpytestrufftwinedspy-aidatasetsdeepevallangchain-openailangchainragasanthropicarize-phoenixdatasetsdeepevalfastapijinja2langchain-openailangchainopenaiopentelemetry-exporter-otlp-proto-httpopentelemetry-sdkpdfplumberpython-multipartragasuvicorn[standard]openpyxlpyarrowanthropicarize-phoenixautogen-agentchatautogen-corecrewaidatasetsdeepevaldspy-aifastapijinja2langchain-anthropiclangchain-corelangchain-openailangchainlanggraphopenaiopentelemetry-exporter-otlp-proto-httpopentelemetry-sdkpdfplumberpyautogen
API access
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/pypi/agent-evaluatorMore from pypi
Last updated · 2026-04-27T05:48:25.566530Z