Repository navigation

feat: AI eval framework for benchmarking MCP servers - #2414

Merged

kodiakhq[bot] merged 25 commits into

mainfrom

brandon/ai-evals

Jun 9, 2026

Merged

feat: AI eval framework for benchmarking MCP servers#2414
kodiakhq[bot] merged 25 commits into
mainfrom
brandon/ai-evals

Commits on Jun 1, 2026
- initial commit
  brandon-pereira
  committed
  7bd6d60
- stream seeding results
  brandon-pereira
  committed
  d93aa98
- general setup fixes
  brandon-pereira
  committed
  37f9abe
- general eval improvements
  brandon-pereira
  committed
  e07e4c7
- improvements to framework
  brandon-pereira
  committed
  2fdc6d7
- add eval skill
  brandon-pereira
  committed
  019db69
- fix: track src/runs/ files and anchor gitignore to root runs/ only
  brandon-pereira
  committed
  3256e47
- chore: remove ablation scripts, experiment artifacts, and notes
  brandon-pereira
  committed
  a4df2b3
- refactor: DRY scenario generators and compact rubric format (-772 lines)
  brandon-pereira
  committed
  b74bf07
Commits on Jun 3, 2026
- feat: MCP-agnostic eval framework with N-way comparison support
  brandon-pereira
  committed
  ac37fe1
- chore: fix knip errors and add changeset for hdx-eval
  brandon-pereira
  committed
  8701385
Commits on Jun 4, 2026
Commits on Jun 5, 2026
Commits on Jun 9, 2026