JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 106
  • Score
    100M100P100Q95137F

Agent evaluation and benchmarking for AgentsKit.

Package Exports

  • @agentskit/eval

Readme

@agentskit/eval

Agent evaluation and benchmarking for AgentsKit.

Coming soon. This package is scaffolded and will be implemented in a future release. See #15.

Planned features

  • eval.run(agent, testCases) API
  • Metrics: accuracy, latency, cost, token usage
  • Designed for CI/CD integration

Docs

Full documentation