Cline
@cline
The open source coding agent that takes over your editor, terminal, and browser to complete work autonomously.
npm i -g cline
15 Following 80.3K Followers
Pixel Canary (stealth model) has just released and is free in Cline.
It's tied with GPT-6 Astra and beats Kimi K3 on Next.js Agent Evals, a benchmark for real Next.js tasks for web and mobile development.
Show more
Gemini 3.8 Flash is free in Cline.
It scores 41 on the Artificial Analysis Intelligence Index, the highest of any model in its price tier. 291 tok/s, 1M context, and it beats GPT-5.6 Luna, DeepSeek v4.1 Flash, and Qwen3.8 on benchmarks.
Show more
Stealth Bunny Alpha is now free in Cline.
It's a stealth model with fast inference, strong coding capabilities, multimodal input support, and a 1M-token context window.
Anthropic’s new Opus 5.5 beats Fable 5.1 on AAII at ~2.5x lower cost.
An hour later OpenAI releases GPT-6 Sol and Luna, both at half price of 5.6 predecessors.
This is an unprecedented jump in performance and drop in price for frontier intelligence.
Show more
After seeing the live RL trainings for the MiMo model, it officially comes out with crazy performance!
The flagship model MiMo-v2.6-Pro is officially the best performing open weights model on artificial intelligence index.
Available in ClinePass already, go try it out!
Show more
1 week since launch and Cline Desktop already runs over 6% of all tasks.
And half of those are from brand new users, welcome aboard! ❤️💪
(If you haven't tried it yet, Kimi K3 is still free in the app for a limited time. Give it a spin!)
Show more
Introducing Cline Desktop - a native interface for working with open weights models.
Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!
Show more
Kimi K3 is now free in Cline Desktop to celebrate all the new users and give them more tokens to continue exploring the app ❤️
(...for a limited time, we'll keep it running as long as we can!)
Introducing Cline Desktop - a native interface for working with open weights models.
Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!
Show more
We’re launching the Cline Ambassador Program.
If you’re a developer or technical creator who enjoys building with Cline and sharing what you learn through projects, blogs, videos, or social content, we’d love to hear from you.
As an ambassador, you’ll get early access to what we’re building, exclusive perks, and opportunities to work more closely with the Cline team. The top ambassadors will be promoted to paid partners.
Apply now:
Show more
The model could be a bit slow right now - still working with upstream provider to improve it
Use in Cline with:
npm i -g cline
/model
Under 'Free', choose 'Union Alpha'
Union Alpha (stealth model) is now free in Cline.
256k context, multimodal, built for agentic coding.
It is near GPT-6 Astra and Opus 5 performance for ~18x lower expected cost.
Show more
Introducing Cline Desktop - a native interface for working with open weights models.
Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!
Show more
Introducing Cline Desktop - a native interface for working with open weights models.
Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!
Show more
It's incredible seeing Anthropic commit to third-party evaluators.
However, we believe open weights takes this same idea further. Anyone can inspect, evaluate, and red-team the model.
We hope to see more open collaboration in building this powerful technology.
Show more
We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so.
Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training.
You can read the full post here:
Show more
Fun fact: avg turns per task in Cline went from 26 in March → 50 in August. Nearly 2x in 5 months.
We’re trusting agents with bigger jobs faster than ever before.
This wouldn’t be possible without cost efficiencies like with the latest DeepSeek models 💪
Show more
DeepSeek V4.1-Flash beats V4-Pro 0813 less than a month after its release.
And it's $0.30/$1.20 per 1M input/output. That's roughly:
- 1/20th cost of Opus 5
- 1/17th cost of GPT-5.6 Sol
- 1/12th cost of Kimi K3
...while beating all three on Terminal-Bench.
Show more
DeepSeek v4.1-Flash is also available on ClinePass, a subscription to get ~5x discounted access.
/settings > Provider > ClinePass, and you can select from any of the best open weights models available today.
Show more
DeepSeek V4.1-Flash beats V4-Pro 0813 less than a month after its release.
And it's $0.30/$1.20 per 1M input/output. That's roughly:
- 1/20th cost of Opus 5
- 1/17th cost of GPT-5.6 Sol
- 1/12th cost of Kimi K3
...while beating all three on Terminal-Bench.
Show more
Try in cline with:
1. npm i -g cline
2. /model
3. Select Muse Spark 1.3 Contributor under 'Free'
Meta’s Muse Spark 1.3 Contributor model is now available for free in Cline.
Benchmarks show it’s similar in performance to Opus 5, but considerably more affordable.
