DigestAI news desk

Cut through the AI noise.

Agents & Tools4 min read

Factory releases droid 1.0 coding agent harness

Factory has rolled out Droid 1.0, the largest update to its Droid agent harness. The update makes programmatic tool calling the default, letting a single model request drive hundreds of tool calls. The base prompt shrank to 13,055 tokens, a 37 % reduction from the previous 20,887, and only two tool definitions ship up front.

1 source

Key points

  • factory releases droid 1.0, making programmatic tool calling default
  • base prompt shrank 37 % to 13,055 tokens, only two tool definitions ship
  • droid 1.0 scores 65.2 % on terminal‑bench 4 with Claude Opus 5.5

Performance data from Factory’s own tests shows Droid 1.0 achieving a 65.2 % pass rate on Terminal‑Bench 4 with Claude Opus 5.5, at $4.73 per passed task, and a 57.6 % rate on GPT‑6.1 Sol at $0.79 per passed task. The harness also reports lower costs and faster execution on Opus 5.5, cutting time by 16‑26 % per passed task and using 17 % fewer tokens versus other harnesses.

The update includes a leaner first request, a prompt cache that reads 98 % of input from cache, bounded autonomy limits, and a 488 ms first‑paint latency. Paid plans start at $20 per month, and the SDK is available on macOS, Windows, terminal UI, and Node via @factory/droid-sdk.

Model pages: Claude Opus 5.5 → · GPT-6.1 Sol → · Kimi K3 →

Full story from MarkTechPost · by Asif RazzaqOpen source ↗

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

MarkTechPost · 31 October 2026

Loading the full article…

This text was published by MarkTechPost and written by Asif Razzaq. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories