Factory

Assembling @droid, the frontier software development agent. Available to anyone, with any model, in any IDE/terminal.

[Factory @FactoryAI]

Introducing model routing to Factory.

Factory Router picks the right model for every task, automatically.

Maintain frontier performance while cutting costs by 25%.

[Factory @FactoryAI]

@petiosz @manishtyagi__ HI Petio, here are our pricing plans:
https://t.co/zmtG8OuC6A

Factory Pro is $20/mo, gives you a full coding agent.

[Anthony Ronning @anthonyronning]

Downtime protection from codex/claude is huge

[Eno Reyes @EnoReyes]

One of the things that often surprises our customers is that we have more 9's of reliability than our underlying providers.

Another benefit of being an aggregator is that you have access to multiple redundant infrastructure providers!

[Matan Grinberg @matanSF]

Cost isn’t the only reason for model routing.

You also get dramatically higher reliability

[Factory @FactoryAI]

Droid works across Slack, Desktop, CLI, CI, phone, and others. It's completely LLM-agnostic, and just got new Factory Router for making the decisions between different models as smooth as possible for organizations and engineering teams.

Try it here: https://t.co/le6do9mTrQ

[Factory @FactoryAI]

Reliability is built into @droid. Factory Router has auto-failover across model providers, so your sessions keep running even when one of the providers goes down.

We also provide dedicated compute capacity for enterprises, and we reserve a guaranteed TPM (token per minute) allocation.

We believe that diversifying LLMs in your agent stack is the future, and the way to achieve the highest reliability in production.

[Factory @FactoryAI]

@anasibnanwar Thank you for writing this, we appreciate your feedback!

[Matan Grinberg @matanSF]

I am very excited to officially welcome @tereza_tizkova to Factory.

Tereza is joining us to work on all things growth. A few days in and she's already crushing it -- she owned the launch of Factory Router on Tuesday.

An ambitious scope for a truly 1 of 1 individual. Welcome!

[Tereza Tizkova @tereza_tizkova]

https://t.co/uYZs2N2D3o

[Factory @FactoryAI]

@manishtyagi__ Thank you!

[Factory @FactoryAI]

@itsakhilp 🫡Excited to hear your thoughts!

[Factory @FactoryAI]

Introducing model routing to Factory.

Factory Router picks the right model for every task, automatically.

Maintain frontier performance while cutting costs by 25%.

[Factory @FactoryAI]

@DosMenoncin @scaling01 @droid We also have (persistent) computer use, if you'd like to check it out! @scaling01
https://t.co/Pd0iuituAu

[Factory @FactoryAI]

@nathankochera @sonyatweetybird @harvey Here is some of our research & benchmarks if you'd like to check it out.

- Benchmarking LLMs for code review: https://t.co/l30oDzIXbJ
- Factors that determine whether organizations are going to adopt AI well, or not: https://t.co/H8XL9v2vic

[Factory @FactoryAI]

@anasibnanwar It's available in research preview for now. We are making it available soon to more people.

[Factory @FactoryAI]

@tadasayy We think what people tend to overlook is the potential speed improvement and keeping the same quality & performance.
It's not just about cost-saving, but about overall better way to use AI.

[Gergely Orosz @GergelyOrosz]

This is what I mean by Factory's smart routing:

https://t.co/nGB4GOmPxb

[Factory @FactoryAI]

@xadisingh @aradotso It is not open-source.

[Factory @FactoryAI]

@FlippyMeister It is still in research preview, but will be available in Missions soon.

[Factory @FactoryAI]

@mattlam_ @GergelyOrosz We do have automatic failover and multiple model providers.

[Factory @FactoryAI]

@mattlam_ @GergelyOrosz Can't speak for others, but Factory Router is customizable, so you can set up preferences for your teams or individuals.
We can also automatically route for example if one provider has a downtime.