Droid retweeted
Factory has acquired @typedef_ai.
Typedef builds a context layer that helps agents understand enterprise data. Together, we’ll give Droids, and the engineers that work with them clearer lineage and evidence to plan migrations, debug pipelines, and refactor models.
Typedef builds a context layer that helps agents understand enterprise data. Together, we’ll give Droids, and the engineers that work with them clearer lineage and evidence to plan migrations, debug pipelines, and refactor models.
33
23
344
92,680
🫡
@FactoryAI they are not lying
I ported the t3code-style claude code integration into @droid
and my usage stay very healthy even running mission mode.
this is a next level harness.
github.com/aa2246740/fact…
2
1
49
4,601
Thank you for testing Droid! 🫡
@FactoryAI been testing Droid and Devin last month (as you can see my post history)
Although Devin has more absolutely token numbers.
Droid has more token efficiency! I feel my $20 claude sub unlimited in the mission mode!
And mission mode is such a truly killer feature.
All in all, Devin has a more flexible and powerful cloud environment multi platform development. The Fusion mode is really cool and efficient. and easier to understand and use. This is what droid should catch up with.
But as for the harness itself, @droid is unbeatable!
4
0
33
3,727
Droid retweeted
If you’re not sure whether you’re getting the most out of your coding agent spend, shoot me a note or comment in thread and we’ll show your team what it should look like with a 1 mo free trial of Factory.
Best performance, best cost efficiency. Choose both.
Best performance, best cost efficiency. Choose both.
Introducing Droid 1.0: the new engine behind Factory’s agent.
Built for complex projects and everyday development:
>more accurate
>more efficient
>faster than ever before
11
4
78
3,127
Droid has no idea where you heard that! 👀
@matanSF @FactoryAI Aren’t you supposed to be second tier? 😂
1
5
93
4,555
Droid iterates until performance improves. 🫡
More massive performance gains thanks to @droid working tirelessly. I need to get a little plush of my droid friend
5
0
27
2,082
Nothing beats hearing this from a long-time @FactoryAI user. 🫡
@MrAhmadAwais @igetduplicatesm@CommandCodeAIve been using @droid as my harness since mid 2025, try ever@droid out there, opencode, omp, amp, etc etc, but nothing else has being better on my experiences
even tho, I'm always open to new tools, and you get me in this Command Code showcase with v4.1 flash thats currently my workhorse alongside opus 5.5.
i would like to include droid in this comparisson versus command code harness
3
1
18
1,934
How Blackstone is building their own software factory with @FactoryAI: Read the full story below 👇
After trialing several offerings, Factory was able to meet the comprehensive large scale enterprise requirements of Blackstone: deployment flexibility with no limit on model choice or engineering workflows.
0
4
18
1,252
If you had to guess, how agent-ready is your codebase?
Well, you don't need to guess anymore. Test your Agent Readiness with @FactoryAI.
Well, you don't need to guess anymore. Test your Agent Readiness with @FactoryAI.
Use Factory @droid agent readiness tool and you’ll get this and much more
1
0
19
1,587
The entire game was built code-only with @FactoryAI. 🎮
Check out the original post for the live demo link & prompt:
Check out the original post for the live demo link & prompt:
I asked Gemini 4 Argon Medium to build an 4v4 combat game as COD
No assets were used, everything you see here is made with code
Available for Mobile & PC both
1
0
23
1,385
What do you plan to do after delegating all your work to @FactoryAI?
See what Delegations can already do for you: x.com/FactoryAI/stat…
See what Delegations can already do for you: x.com/FactoryAI/stat…
Delegate to @droid while you
3
0
33
1,624
Any Droid builders in London? 🇬🇧
I was this last days at London, and suddenly at Piccadilly I saw @droid @FactoryAI Wow!
Congratulations!
3
2
22
939
Droid retweeted
@SamJWasserman Did a sanity test in @apolloaiapp and planning to serve this via with @droid harness.
Run DeepSeek V4.1 Flash 1017 on 2x DGX Sparks ✨
- 1M total KV pool, 512K context
- 75 tok/s on prose, single stream
- 130 tok/s on prose, 4 concurrent streams
- Prefill 2000-2175 tok/s
- EXL3-EAQv1, 2.9 bpw
The quant in this recipe got about the same calibration as my GLM 5.3 . Feedback would be appreciated!
Special thanks to @bertholomusai and all the contributors for the engine work, and to @ashxhart for TensorFold.
Get it here:
github.com/MiaAI-Lab/Deep…
1
2
11
10,047