The open source coding agent that takes over your editor, terminal, and browser to complete work autonomously.
Joined January 2025
- Tweets 3,665
- Following 8
- Followers 61,979
- Likes 1,333
1,171 Photos and videos
Kimi K2.7 Code scores higher than K2.6 on benchmarks while using ~30% fewer tokens.
It's the first time Moonshot has put "Code" in a K2 model name. Every other K2 release was a general purpose agentic model.
Try in Cline now! (good model to put in our upcoming subscription 👀)
23
37
757
66,221
To install Cline in your CLI run: `npm i -g cline`
Available as an extension for VS Code and JetBrains as well!
(Free, open source, bring your own API key and use any model)
github.com/cline/cline
15
3,686
2/ Cline, Claude, Codex allow you to create a loop with the "/goal" command to force the agent to continue working until some criteria is met.
Using this approach with the adversarial review technique forces the model to check its work until it's verified to work without issues.
2
4
117
14,781
3/ Try it in Cline with:
`npm i -g cline`
`cline plugin install goal`
Or available on VS Code and JetBrains as well!
github.com/cline/cline
1
3
57
8,260
We’re working on a subscription plan for Cline to give you the best value for open-weights models.
Which of the models below is your "must-have" daily driver? (Can only include four options in the poll, comment to leave your favorites if not in the list!)
40%
Kimi K2.6
12%
GLM 5.1
36%
DeepSeek V4 Pro
13%
MiniMax M3
379 votes • Final results
44
6
105
11,560
Anthropic's new Claude Fable 5 is #1 on Terminal-Bench 2.1 at 88.0%, beating GPT 5.5 by 4.6%.
Under the hood it's their Mythos model with safeguards that route dangerous requests to Opus 4.8, which Anthropic claims triggers in under 5% of sessions.
Available in Cline now!
23
18
274
16,461
To install Cline in your CLI run: `npm i -g cline`
Available as an extension for VS Code and JetBrains as well!
cline.bot/
1
11
2,042
Introducing Cline Spec Driven, our enterprise AI engineering platform built with LG CNS.
A team of specialized agents takes work from request to enterprise-grade code, using your business context and operational standards.
cline.bot/spec-driven
13
2
32
5,332
NVIDIA just released Nemotron 3 Ultra, a 550b-parameter agentic coding model with a 1m context window. It was built for token efficiency, and is up to 5x faster and 30% cheaper than other similar models.
It's the largest US open-weights model release ever.
Free in Cline now!
18
7
224
10,141
With the rise of npm supply chain attacks, it's important to regularly scan your machine for compromises against threat catalogs like Bumblebee.
Here's how to use a coding agent like Cline to run scans on a cron job that text you whenever a compromise is detected 🧵
Microsoft has identified a npm supply chain compromise impacting 90 redhat-cloud-services/* packages, including patch-client 4.0.4, insights-client 4.0.4, rbac-client 9.0.3, host-inventory-client 5.0.3, frontend-components 7.7.2, and others. The payload is a self-propagating worm that infects other npm packages and self-publishes.
Each compromised package adds a malicious preinstall hook, embedding an index.js script in the package.json that silently executes “node index.js” during installation, downloads Bun, and runs a payload that steals secrets from npm, GitHub, Amazon Web Services (AWS), and Secure Shell (SSH). The added code bloats index.js from ~8KB to ~4.3MB, acting as a heavily obfuscated ROT-9 eval loader.
If any of the compromised packages are installed, users and organizations should assume compromise, rotate credentials, revert to a previously trusted version, and block compromised packages. Identified compromised npm packages have been taken down, and we continue to work with the npm team. Microsoft continues to investigate this attack and will publish updates as more information is available.
ALT Image for supply chain attacks
3
2
27
5,309
You can use the Cline CLI to schedule a task that runs at 8am everyday to pull the latest Bumblee catalog, scan repositories on your machine for matches, and text you when a compromise is detected.
You can also specify how often to run the scan, what directories to look at, etc.
1
1
5
2,106
You can install Cline with:
npm i -g cline
(Free, open-source, and use any provider like your chatgpt subscription for inference)
Full setup guide (to use Bumblebee, connect Telegram, schedule jobs) in our docs:
docs.cline.bot/cli/samples/s…
1
1
1,166
Congrats to the @Alibaba_Qwen team, the new Qwen-3.7 Plus is a best in class multimodal model, performing near SOTA as both a coding and general purpose agent across benchmarks.
Free to try in Cline now! `npm i -g cline`
25
24
441
19,388
Cline retweeted
Jun 1
1/ Using rules like "don't read .env" are not reliable to protect your keys since models many times ignore one-off instructions like this in long horizon, large context work.
Give Cline plugins a try, where you can hook into the agent lifecycle with simple TypeScript:
1
2
19
3,317
Cline retweeted
Jun 1
MiniMax's new m3 model scores the same as opus 4.7 on terminal-bench 2.1 at 1/20th the compute/cost of their previous model.
Their blog credits this to their new 'MiniMax Sparse Attention' architecture next to this crazy diagram.
Here's a breakdown of how this works 🧵
3
2
53
5,546
The new MiniMax-M3 is their first model to have 1m context, multimodal, and agentic coding capability.
Congratulations to @MiniMax_AI for the breakthrough in sparse-attention architecture cutting compute & cost to 1/20th their previous generation.
Free to try in Cline now!
54
67
1,256
55,615
Anthropic's new Opus 4.8 scores 3.6% lower than GPT 5.5 on Terminal-Bench 2.1. Available to compare side-by-side in Cline now.
(They also announced a plan to release new models with higher intelligence than Opus after adding stronger cyber safeguards in the coming weeks.)
44
58
977
64,493
Use your 99% discounted MiMo model in BYOK agents like Cline today!
May 26
🚀 Better inference efficiency, lower costs, broader access.
MiMo-V2.5 Series API pricing is now permanently reduced — by up to 99% compared to previous pricing.
✨ Unified pricing across all context lengths.
MiMo Token Plans have also been upgraded:
• 5–8× more usable tokens at the same price
• Simpler and more transparent billing rules
🎁 As a thank-you to current users, all current Token Plan credits will be fully reset.
🎧 MiMo-V2.5-TTS remains free for a limited time.
⏰ Effective May 26 at 6:00 PM PDT.
These improvements are powered by continued inference optimization and serving efficiency upgrades across the MiMo stack.
🛠️ We’ll also publish a detailed technical blog on the inference optimizations later — stay tuned.
8
2
96
10,762