Assembling @droid, the frontier software development agent. Available to anyone, with any model, in any IDE/terminal.
curl -L app.factory.ai/cli |sh
Based in United States
- Tweets 1,795
- Following 48
- Followers 54,928
- Likes 11,134
Pinned Tweet
Introducing Factory Private, a new deployment option that lets organizations run Factory in their own VPCs, on-premises environments, or air-gapped networks.
24
18
175
76,550
How does self-improving software work? Listen to our CTO @EnoReyes talk about building the machine that builds the software powering thousands of developers globally.
Listen to the episode here: piped.video/watch?v=NLsiZtle…
4
44
4,418
Factory retweeted
Big Token hates this one simple trick!
Dynamic model routing allows for a more efficient free market across the model providers.
This puts pricing pressure on them to provide the best/fastest/cheapest tokens for any given task, lest the tokens get routed to a competing model.
Factory Router now cuts inference costs by 63% in production, up from 42% in late June, while routed session volume grew roughly 4x.
8
7
82
9,125
See how frontier models handle software written in COBOL, Java 7, BASIC, C89, Fortran, and Assembly.
Today, our benchmark, Legacy-Bench, joins @FireworksAI_HQ’s Specialized Intelligence Index.
Frontier models have blind spots for legacy code, what’s benchmarked is improved. Legacy-Bench tests how well AI models can debug, extend, and migrate historic systems, to drive the future of software.
1
6
31
3,667
Today, our benchmark, Legacy-Bench, joins @FireworksAI_HQ’s Specialized Intelligence Index.
Frontier models have blind spots for legacy code, what’s benchmarked is improved. Legacy-Bench tests how well AI models can debug, extend, and migrate historic systems, to drive the future of software.
18
8
133
30,753
Factory Router now cuts inference costs by 63% in production, up from 42% in late June, while routed session volume grew roughly 4x.
9
8
72
16,953
Lower cost does not mean sending every task to the least expensive model.
Factory Router selects an efficient model when it can complete the work reliably, and moves to a stronger model when the task requires it.
1
12
1,017
Organizations can configure Factory Router around their workflows, codebase, toolchains, model preferences, and cost requirements.
Routine work goes to efficient models. Critical work gets the additional reasoning it requires.
Read the results: factory.com/news/factory-rou…
11
716
Factory retweeted
Today, @FactoryAI joins the Specialized Intelligence Index with Legacy-Bench!
The SII keeps growing, now with benchmarks testing how models handle the legacy software behind payroll, financial settlement, and more.
Submissions are open for teams with proprietary benchmarks.
Get listed: fireworks.ai/contact-special…
1
5
45
8,875
Introducing Teams.
Bring Factory to your whole engineering team. With Teams, you can now add multiple users to a self-serve plan with centralized billing.
Delegate bug fixes, tests, and migrations to Droids while your team focuses on what to build next.
9
13
139
25,314
Every user gets their own Pro rate limits.
$60/month per team, plus $40/month per seat, for up to 10 seats.
1
12
1,612
Bring your team and for a limited time, get $500 toward your plan.
Learn more here: factory.com/teams
11
1,205
Opus 5.5 is live in Factory. Some initial observations:
/ Medium is a strong default
/ 20–25% fewer output tokens than @AnthropicAI Opus 5 at the same effort
/ Clear, actionable answers on long investigations
Try it now: factory.com/
6
7
151
13,716
Grok 4.7 is live in Droid. Observations so far:
- Strong across engineering, debugging, data, and infrastructure work
- Moves into concrete command discovery faster than @SpaceXAI Grok 4.6
- Medium is a strong default
- High adds lift on legacy-code work
Try it here: factory.com/
12
5
111
10,217
Factory retweeted
Droid is seriously impressive. The AI Agent Harness has become part of my daily workflow — coding, debugging, investigating issues, and handling complex tasks with multiple agents running in parallel.I use it every day, and it keeps getting better. Great work, @droid, @FactoryAI
5
3
29
3,237
Factory retweeted
From @Factory Managed to Factory Private, our customers and partners have deployment options that meet their security boundaries.
Learn more here, or DM me.
lnkd.in/gnKrgztK
Introducing Factory Private, a new deployment option that lets organizations run Factory in their own VPCs, on-premises environments, or air-gapped networks.
1
1
27
3,543
Factory retweeted
Extremely smart move by @FactoryAI.
On-prem / own VPCs may become a much larger part of workloads with AI, as large enterprises will care more about protecting sensitive information and controlling costs.
Introducing Factory Private, a new deployment option that lets organizations run Factory in their own VPCs, on-premises environments, or air-gapped networks.
2
4
32
11,489
Factory retweeted
The companies that will win enterprise AI are the ones that let customers run the agents in their own VPC, on-prem, or air-gapped.
Data residency isn’t a “nice to have.” It’s the product. Everything else is just another black box you don’t control.
Introducing Factory Private, a new deployment option that lets organizations run Factory in their own VPCs, on-premises environments, or air-gapped networks.
1
2
17
1,539
Factory retweeted
Many are surprised to hear that Factory is the first and only on-prem Software AI product that exists today. One with the ability for the control plane to be hosted in the customers' VPC or on-prem environment.
These are the real challenges to AI adoption in the enterprise. We are proud to support a best-in-class experience for customers' to own their intelligence while deploying AI at scale.
Introducing Factory Private, a new deployment option that lets organizations run Factory in their own VPCs, on-premises environments, or air-gapped networks.
4
8
85
26,778