@useAuton

Your coding agents and project tools in one workspace. - Resume saved sessions. - Switch agents. - Keep your workflow.

useauton.com
Joined September 2026
  • Tweets120
  • Following36
  • Followers11
12Media
six terminals, three agents, and no idea which one is waiting on you? that's why We built Auton: every coding agent you already use, side by side in one window. shut your PC down at night and your sessions are back in the morning. the new version is out. free to use on Windows.
1
4
85
Forever caching in codex. come back to any old convo, no penalty. leave a task for hours, or for days. pick it up like you never left. openai really cooked with this one 🔥
Tibo
@thsottiauxOct 21
Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
3
39
Be honest. how many coding agents are you running at once? and are you still doing it all in one claude code window?
1
3
64
Try it here for free: useauton.com

Auton: all your coding agents in one calm window

Run Claude Code, Codex and other coding agents side by side on your own plans. Sessions resume where you left them. Lite is free forever. No card.

useauton.com
3
13
wait who the hell was driving the tesla
845
302
114
11,795
641,383
unpopular opinion: 'it might be all over' is just how we say 'new model drops' now 😄
Theo - t3.gg
@theoOct 15
If Anthropic actually drops Fable 5.5 today it might be all over
4
112
nobody keeps the google sub for the model. they keep it for everything else 💰
Auton
@useAutonOct 15
Replying to @bridgemindai
Argon lost the frontier race, but google's still the best value sub out there 💰
4
31
hit my claude max limit in 3 days. guess it's time to try Argon 🫠 how many days did yours last this week?
2
2
5
53
First time i've burned through opus 5.5 this fast. all credit goes to ultracode 😅
3
19
cough, cough …Astra? 👀💀
Theo - t3.gg
@theoOct 12
My current model rankings S - Opus 5.5, Muse Wonder A - GPT-6.1 Sol — Gap — Everything else
3
29
Remember when GPT-6 Astra was supposed to be AGI? it's already 4th on the chart 👀 how long until today's #1 is 'just another model'?
Bar chart from the Artificial Analysis Intelligence Index. Claude Opus 5.5 leads with 58. Claude Sonnet 5.5 and Muse Wonder Full follow at 56. Claude Fable 5.1, GPT-6 Astra, and Gemini 4 Argon each score 53. Muse Wonder and GPT-6.1 Sol score 52, and Muse Spark 1.3 scores 48. A checkered pattern marks models with no public API, including Muse Wonder Full and Gemini 4 Argon.

ALT Bar chart from the Artificial Analysis Intelligence Index. Claude Opus 5.5 leads with 58. Claude Sonnet 5.5 and Muse Wonder Full follow at 56. Claude Fable 5.1, GPT-6 Astra, and Gemini 4 Argon each score 53. Muse Wonder and GPT-6.1 Sol score 52, and Muse Spark 1.3 scores 48. A checkered pattern marks models with no public API, including Muse Wonder Full and Gemini 4 Argon.

1
3
84
Funny how no model ever launches at #2. it's always #1, by just enough. are benchmarks measuring models, or marketing? 🤔
Mark Zuckerberg
@finkdOct 12
Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.
3
12
You don't have to pick one coding agent anymore. claude, codex, gemini. launch them side by side and let them race. which one are you running first?
1
3
48
try it free here 👇 useauton.com

Auton: all your coding agents in one calm window

Run Claude Code, Codex and other coding agents side by side on your own plans. Sessions resume where you left them. Lite is free forever. No card.

useauton.com
3
19
Track usage of all your Agents at glance. Now live on useauton.com for free.
1
2
17
the ‘rollback didn’t work either’ plan 😅
OpenAI
@OpenAISep 29
This is Ultrafast. Our premium speed tier, Ultrafast offers up to 8x faster token generation (300 tokens per second) in Codex and up to 6x in the API.
3
17
Really curious: what would make the drop from 20X to 10X worth it? If it’s just hosted Hermes, I’d be disappointed. Not everyone use it enough to justify the tradeoff in coding usage.
Tibo
@thsottiauxSep 29
I’ll explain the new Pro 200 plan differently, before I start live tweeting from DevDay on things that are going out! Today we are going to ship a number of things that increase what you can do across the Plus and Pro plans. A lot of compute is online for this increase. As we increase the floor, we are changing the relative difference between plans to be Plus = 1X Pro 100 = 5X Pro 200 = 10X and we are reopening subscriptions for Pro 200 (we had paused it). If you have an existing plan you will keep the 20X multiplier for a bit and also receive a lot of additional credits because we know changes are hard even if it means that everyone will get more in the end.
4
19
barely finished testing the last one 😅
Auton desktop workspace showing eight idle Claude Code sessions running Sonnet 5.5 in a four by two grid, with Sonnet and Opus test folders in the sidebar.

ALT Auton desktop workspace showing eight idle Claude Code sessions running Sonnet 5.5 in a four by two grid, with Sonnet and Opus test folders in the sidebar.

3
11
Before closing a coding-agent session, save three things: • What changed • What’s still failing • The next exact step A transcript tells you what happened. A handoff tells you where to start. What do you save before calling it a day?
3
13
Your next coding session shouldn’t start with “where was I?” Auton keeps your coding agents and project tools in one workspace and v0.1.6 lets you pick up saved agent sessions where you left off. Less setup. More building. Try it → useauton.com

Auton: all your coding agents in one calm window

Run Claude Code, Codex and other coding agents side by side on your own plans. Sessions resume where you left them. Lite is free forever. No card.

useauton.com
3
12
Load more