Cline was featured at Meta Connect! We are one of the best harnesses to use their Muse Spark 1.3 model, and their contributor variant is completely free through Cline provider. Incredible seeing Meta make a comeback 🔥

Sonnet 5.5 beats Opus 5.5 on Terminal-Bench 4.0 at half the cost. It uses far fewer tokens than previous models to do the same work, showing costs reduced up to 30% per task. It also generates output 30% faster than its predecessor, making it the fastest Sonnet model to date.

Trending on OpenRouter and climbing the ranks to #2 top coding agent after our desktop app release!

Ember-1 by the Fireworks Research team is built on Kimi K3, and uses ~40% fewer tokens while achieving the same performance on benchmarks. This was accomplished by post-training K3 to think less repetitively. Reasoning models spend most of their output tokens (sometimes 90%+) on thinking before they answer, which gets expensive in agentic loops where the model tends to re-think the same thoughts on every step. Fireworks RL trained on real agentic coding task loops to teach the model which reasoning actually changes the answer vs which is just looping. In a live A/B test on coding traffic, Ember-1 used 71% fewer reasoning tokens and 39% fewer total tokens than K3 at the same success rate.

This is the first model out of the new Fireworks Research team - it’s wonderful to see an inference provider doing post-training on open weights to reduce costs. Great work @FireworksAI_HQ 💪 fireworks.ai/blog/ember-1

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.

New in Cline Desktop: SSH support! The app stays on your laptop while Cline works on e.g. a dev server, raspberry pi, docker container, anything you can SSH into. Docs (w/ some videos & getting started guide on SSH): docs.cline.bot/usage/cline-d…

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.

New in Cline Desktop v0.0.34: > Worktrees - run multiple tasks in parallel each on its own branch in ~/.cline/worktrees/<id> > GitHub PR status - see branch’s PR link, merge status, and CI checks (needs gh) > Parallel subagents - delegate multiple tasks at once in each session

Cline has a new look. Two years ago Cline was a weekend hackathon project with an icon thrown together overnight. Now it's on millions of computers, and it felt time for the mascot to catch up.