Open Experiment Forge

Blog

Everything published

Projects, journal notes, and guides in one chronological stream.

Ten Python task cards entering a forge-like benchmark machine and flowing through nine evaluation paths toward cost and correctness instruments
Project / active

Python Agent Cost Benchmark

Ten controlled Python tasks for measuring how skills and agent configurations affect cost without sacrificing correctness.

  • python
  • agents
  • benchmarking
  • evaluation
Read
Journal / seed

First sparks

A short opening note about what this journal is for.

  • process
  • notes
Read
Project / active

Building Open Experiment Forge

A public workbench for the website itself: static-first, safe, and easy to expand.

  • website
  • astro
  • safety
Read
Guide / seed

A safe static website baseline

A practical starting checklist for publishing a simple website with fewer moving parts.

  • security
  • static-site
  • deployment
Read