Keyword: Evaluation
- langsmithReleased3d agoVersion0.7.12
Client library to connect to the LangSmith Observability and Evaluation Platform.
- @n8n/expression-runtimeReleased5d agoVersion0.17.1
Secure, isolated expression evaluation runtime for n8n
- @arizeai/phoenix-clientReleased3d agoVersion6.11.1
A client for the Phoenix API
- @braintrust/trace-opencodeReleased5d agoVersion0.0.9
Automatically trace OpenCode conversations to Braintrust. Captures user messages, assistant responses, and tool calls for observability.
- @remnic/benchReleased2d agoVersion9.3.643
Retrieval latency ladder benchmarks + CI regression gates for @remnic/core
- @axiom-lattice/agent-evalReleased3d agoVersion2.1.81
Agent evaluation for Axiom Lattice framework
- sentinel-agentosReleased4d agoVersion0.4.9
Sentinel AgentOS — 确定性 Guard 层 + 分层记忆 + 自动评估，让任何 Agent 变得可靠、可审计、可改进
- @botpress/evalsReleased3d agoVersion2.0.1
Evaluation definitions and runner for ADK-based Botpress agents
- @goyamegh/agent-healthReleased4d agoVersion0.5.23
Agent Evaluation and Observability Framework
- autoctxReleased4d agoVersion0.10.0
autocontext — always-on agent evaluation harness
- @yuheinakasaka/nimbus-evalReleased3d agoVersion0.0.5
Evaluation framework for Nimbus agents
- agoda-agent-catalog-evalReleasedyesterdayVersion0.7.0
CLI to evaluate coding-agent skills against a catalog of test cases.
- @driftgard/nodeReleased2d agoVersion1.25.1
Official DriftGard Node.js SDK — evaluate LLM interactions against your compliance policy
- @softlaunch/coreReleasedyesterdayVersion0.1.1
Softlaunch feature flag evaluation engine
- @evalgate/sdkReleased2d agoVersion3.5.1
EvalGate SDK - AI quality infrastructure. Capture real failures, promote reviewed eval coverage, and gate regressions.
- @dzhechkov/skills-academicReleased2 weeks agoVersion0.3.1
Academic skill pack — dissertation review, question generation, document checking for thesis defense (ГЭК). Contains only evaluation criteria and methodology, no student data.
- @forwardimpact/gearReleased1 week agoVersion0.1.6
Shared libraries and services for platform builders and agents — CLIs, retrieval, evaluation, and infrastructure published to npm.
- @twilio-alpha/assistants-evalReleased6d agoVersion0.1.1
promptfoo extension for writing AI evaluations for Twilio AI Assistants
- @ykstormsorg/goldsetReleased5d agoVersion0.2.4
Lock your AI app's behavior. Golden datasets + LLM-as-judge + structural assertions in CI.
- @hlido/cliReleased6d agoVersion0.2.0
Hlido CLI — independent, evidence-backed scorecards for AI agents. Inline scorecard, search, compare, and tier rankings, fetched live from hlido.eu.
- ultimath-mcpReleased1h agoVersion0.1.4
Stop hallucinating numbers. MCP server for Ultimath: math on multiple independent engines, in parallel.
- stt-evaluationReleased4 years agoVersion1.4.0
Generic word-error-rate evaluation package
- seeboReleased3h agoVersion0.2.0
Suspendable Evaluation Engine Built with Opus — a typed, suspendable expression/template engine with a pure synchronous core.
- @mostajs/gradebookReleased17h agoVersion0.1.0
Évaluations, notes, niveaux atteints et progression (CEFR/1→N). DB-agnostique ; compose questa (quiz). Délègue catalogue/niveaux à @mostajs/training.