Cline (@cline) / X

Cline

3,848 posts

Cline

@cline

The open source coding agent that takes over your editor, terminal, and browser to complete work autonomously. npm i -g cline

VS Code, JetBrains, the CLI

github.com/cline/cline

Joined January 2025

Following

72.1K

Followers

Affiliates Replies Articles Media

Pinned
Cline
@cline
Jul 31
We are making the updated DeepSeek V4-Flash 0731 free in Cline. This is the first flash model we've found performs at SOTA levels, and are excited for you to feel the new frontier. 1. npm i -g cline 2. Open /settings > Cline provider 3. Select deepseek-v4-flash
GIF
Cline
@cline
Jul 31
DeepSeek silently updated their changelog with a new V4-Flash upgrade 1 hour ago. Their new Terminal-Bench score is 82.7, a massive +25.8 point leap from its initial April preview score of 56.9. Currently only available via their API, open weights release will follow shortly.
Cline
@cline
Aug 6
We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container. So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added
Alexandr Wang
@alexandr_wang
Aug 5
muse code in beta is live. first coding agent from msl, built on muse spark 1.2. install: curl -fsS dev.meta.ai/install.sh | bash here's what you should know:
Cline
@cline
Aug 5
just added /theme in cline cli 😎
GIF
Cline
@cline
Aug 4
Qwen3.8-Max is now available in ClinePass, a subscription for ~5x discounted access. Use it on Cline CLI w/ $4.99 special promo: npm i -g cline This is currently the most affordable way to access Qwen.
Cline
@cline
Aug 4
We're on track to spend millions of dollar a year on Kimi inference at Cline. This is everything we learned trying to make that number smaller.
Ara
@arafatkatze
Aug 4
Article
How to Save Millions by Self-Hosting LLMs
At @cline we're on track to spend about $3M a year on inference for Kimi models. Everyone told us the same thing: it's open-weights, so just self-host and save. This post is the actual math behind...