Droid is Factory's AI software-engineering agent product for automating development workflows such as coding, repository documentation, code review, browser-based QA testing, and deployment-related tasks.
Recent stories
GLM-5.2 added Perplexity Agent API, Droid, and more hosting options, while Baseten reported over 280 TPS and sub-0.8s TTFT. Builders should watch the cost and benchmark data as it moves into production agent stacks.
Builders published Claude Code and Droid setups for GLM-5.2 while Unsloth quantized it for local 256GB machines and Hugging Face opened temporary free inference. Teams can now run the open-weight model across hosted, local, and agent workflows.
Two days after Factory 2.0 launched, Factory added AutoWiki, which turns a repo into structured engineering docs that update on every push and can be generated from Droid with /wiki. The feature keeps architecture and request-path context aligned with the live codebase.
Factory launched Automated QA in Droids, adding /install-qa and /qa to drive apps like a real user and attach screenshots, traces, and logs to PRs. The feature packages browser-based regression testing as a built-in agent workflow.
Independent tools and platforms shipped GPT-5.5 support within a day of the API rollout, spanning IDEs, hosted research agents, enterprise stacks, and coding agents. That shortens evaluation time because teams can test the model inside existing workflows instead of rebuilding around a single OpenAI surface.