~ / agents / droid

Factory Droid 1.0

Factory’s model-independent coding agent harness got its largest update on 31 October 2026: programmatic tool calling is now the default, so the model writes a sandboxed program that runs hundreds of tool calls while only printed output returns to the context.

Overview

One-line facts, source-labelled.

VendorFactory
FormModel-independent coding agent harness (desktop app, terminal UI, Node SDK)
LaunchedOctober 31, 2026 (Droid 1.0; research post October 29)
ARscorenot scored
Pricingbring any supported model or your own API keys
Core changeprogrammatic tool calling (Script mode) on by default
Open sourceNo

Harness comparison (Terminal-Bench 4, Claude Opus 5.5)

Factory ran every harness against Droid on the same model.

Droid

at $4.73 per passed task

65.2 † self claim

Cursor

same model, same runs

62.1 † self claim

OpenCode

same model, same runs

62.1 † self claim

Devin

same model, same runs

59.6 † self claim

Claude Code

same model, same runs

57.6 † self claim

Bar length equals Terminal-Bench 4 pass rate on Claude Opus 5.5. All figures self-reported by Factory (3 trials per task, runs 23–28 October 2026), not independently reproduced. Vendor self-claim

Second model check (GPT-6.1 Sol)

The same harness race replayed on an OpenAI flagship.

HarnessPass rateCost per passed task
Droid57.6$0.79
Codex54.0—
OpenCode51.0—
Devin45.0—

Same caveat: Factory’s own runs. Droid is 10% slower per passed task than Codex on this model, by Factory’s own numbers.

Features

What changed in the harness (presence, not benchmark performance).

CapabilityStatusSource
Script tool: model writes sandboxed JavaScript that runs the tools✓Official
Raw files, search results and logs stay inside the program✓Official
Independent tool calls run concurrently✓Official
Base prompt cut 37% to 13,055 input tokens✓Official
2 tool definitions up front, down from 11✓Official
Typical production request reads 98% of input from cache✓Official
Works with any supported model, including your own API keys✓Official
Factory Router picks a cost-efficient model mix✓Official

Efficiency figures (vendor-reported)

Factory’s own sessions, shown as before/after.

TaskDirect callsScript mode
Unit-test fix (15 tool calls, GPT-6.1 Sol)10 model calls, 56.8 s5 model calls, 41.6 s
Linear cleanup (151 issues, 312 tool calls)est. 36 requests, ~3.1M tokens2 requests, ~61,000 tokens
CI sweep (5,384 jobs across 547 runs)—2 requests; under 0.1% of tool results reached the model

Script mode cuts cost by 15% on Claude Opus 5.5 versus direct tool calling; on by default for 10 models including GPT-6.1 Sol and Kimi K3. Vendor self-claim

Setup and configuration requirements

What you need before first use.

Runs onmacOS and Windows desktop app, a terminal UI, and the Node SDK @factory/droid-sdk
Modelany supported model or your own API keys; Factory Router can choose the mix
Script modeon by default for 10 models; sandbox has no file, network or system access of its own
Deploymentruns locally and in the cloud; sessions share one daemon (~20 MB each)

Use cases

Scenario coverage, not benchmark performance.

Bulk operations

Move and verify 151 tracker issues in two model requests.

Vendor self-claim

CI sweeps

Thousands of jobs checked with almost nothing loaded into context.

Vendor self-claim

Delegated development

Delegate work at scale; ship PRs, configured infrastructure, incident investigations.

Official

Harness portability

Keep one workflow while swapping models — the model-independent pitch.

Official

Download and official links

Outbound, for trial and verification.

Release notehttps://factory.com/news/frontier-harness
Benchmark pagehttps://factory.com/news/terminal-bench
Factory Routerhttps://factory.com/product/router
Factoryhttps://factory.com
News coverageAgentRanks news feed

Compare further

The sibling harnesses and the scored incumbents.

DeepSeek HarnessOS

the MIT plugin harness in the same category

not scored / CLI

OpenCodeOS

the open harness Droid beat on its own board

see leaderboard

Claude Code

the architecture leader, 57.6 on Droid’s own board

score 86

Cursor

daily IDE coding, 62.1 on the same board

score 71 / IDE