Run Claude Code, Codex and more from one desktop app. Mix agents in a thread, review and fix PRs, and check in from your phone. Free and open source.
Based in United States
- Tweets 176
- Following 59
- Followers 15
- Likes 275
Pinned Tweet
Threadlines v0.5.0 is out 🧵
Rooms: more than one coding agent in a thread. Ask Codex while Claude works, or have them review each other.
Also new: Cursor and fx support.
Free and open source.
Release notes: github.com/Threadlines/threa…
8
5
55
235,245
DevDay was really fun, the builder energy was crazy
Still wild to me to see people making whole startups in a day
552
133
4,674
445,220
I use Claude Code and Codex every day and still switch depending on the job. What makes you pick one?
1
49
Threadlines v0.5.0 is out 🧵
Rooms: more than one coding agent in a thread. Ask Codex while Claude works, or have them review each other.
Also new: Cursor and fx support.
Free and open source.
Release notes: github.com/Threadlines/threa…
8
5
55
235,245
@threadlinesdev Threadlines' rooms for running Codex, Claude Code and Cursor agents in one workspace fit awesome-ai-plugins, Community Plugins > Development & Workflow. Open a PR to list it: github.com/hashgraph-online/…
1
2
122
rooms with Codex asking while Claude works is the setup i actually want. cross-review between two agents beats one model grading itself.
1
1
137
Having Codex and Claude review each other sounds useful until both are just arguing about the same half-finished PR. Someone still has to own scope and the final merge call.
1
1
114
Google has been quiet for months. Now this.
Gemini 4 Argon has a 15% hallucination rate. The lowest on the entire board.
Opus 5.5: 59%.
GPT 6 Astra: 51%.
Fable 5.1: 73%.
And Gemini 4 Argon is not even publicly available yet.
How is this possible?
166
60
1,954
132,994
Managed to grab both the Plushie and the Stickers 🥰
didnt get a confirmation mail from Claude tho... Is it normal?
13
196
17,985
My final verdict on GPT-6.1 Sol.
I've been testing it since release, running it all day alongside Opus 5.5.
They definitely fixed token efficiency. Only 5% of my weekly burned in 1.5 days. I've been switching between Extra High, High, and Medium depending on the task complexity. Compared to before, this is incredible.
It is very smart. It can do many things, but I would still give a slight advantage to Opus 5.5.
The reason is that Opus is much better in frontend and design. GPT is as always struggling there.
For me, the best combo right now is GPT-6.1 Sol + Opus 5.5.
Just use both. 🔥
74
11
565
49,922
100% Agree, we build out newest feature around that. We call it “Rooms”, you can have Agent work together in the same thread, been using it in nightly for a bit now and I love it. threadlines.dev/
102
out of Opus 5.5 after 6 days on $100 plan. considering how much I was able to get done, it's freaking awesome
55
6
811
21,528
Claude is handing out free Clawd plushies and stickers from a terminal prompt.
claude.dev/terminal
/plushies → random plush
/stickers → sticker pack
No purchase. One each. 18+. While supplies last.
13
63
9,144
Introducing Gemini 4 Argon, our new frontier model, rolling out to cyber defenders starting today, and more widely as soon as possible. I am really excited by the progress we have made here. Argon is priced at $2 in and $10 out during introductory pricing!
1,012
1,053
14,765
1,534,435
the fairwind faq doesn't name open source projects. its closest category is core tech platforms that secure widely used software
applications go through a vetting check. if a project isn't eligible the faq points to codemender with public models
1
1
20
