Meet Factory Droid 1.0: A Model-Independent Coding Agent Harness Built on Script Mode

TL;DR

Factory released Droid 1.0, a model-independent coding agent that simplifies programmatic tool calling; it scored 65.2% on Terminal-Bench 4 runs with Claude Opus 5.5 at a cost of $4.73 per passed task, marking a step towards more accessible and efficient coding assistance.

Detailed Summary

Factory released Droid 1.0, a model-independent coding agent harness that facilitates programmatic tool calling, achieving a score of 65.2% on Terminal-Bench 4 runs with Claude Opus 5.5. The cost for passing tasks is $4.73. This innovation could significantly impact the efficiency and accessibility of automated coding processes across various industries.

Key Points

• • Factory Droid 1.0 is a model-independent coding agent harness.
• • It uses script mode for programmatic tool calling.
• • Scores 65.2% on Terminal-Bench 4 runs with Claude Opus 5.5.
• • Costs $4.73 per passed task on Terminal-Bench 4.