Files

T

Andrey Kumanyaev fd89126884 Add SWE-bench evaluation framework for benchmarking tool effectiveness

Go side: eval-server HTTP endpoint, index caching keyed by (repo, commit),
  and integration with the existing MCP server. Python side: full eval harness
  with single/matrix/debug modes, Docker-based environments, agent wrapper
  with augmentation support, composable YAML configs for models and modes
  (baseline/native/native_augment), bridge scripts for CLI tool access,
  and property-based tests. Tracks resolve rate, cost, tool call counts,
  and augmentation hit rate.

2026-04-09 18:29:27 +02:00

195 B

Raw Permalink Blame History

Gortex Eval Framework

SWE-bench evaluation harness for measuring Gortex code intelligence impact on AI agent performance.

See the spec for full design details.

195 B Raw Permalink Blame History

Gortex Eval Framework

195 B

Raw Permalink Blame History