Cline 3.55 adds two open models worth paying attention to. Arcee Trinity Large is free, US-built, and licensed under Apache 2.0. Kimi K2.5 is an open-source model that outperforms Opus 4.5 on certain benchmarks.
There's a growing assumption that AI coding assistants are fundamentally incompatible with regulated environments. This belief usually stems from how most AI tools are architected, not from AI-assisted development itself. Security constraints in these environments are real and non-negotiable. Restricted networks, strict compliance requirements, long approval timelines, and
If you have an OpenAI subscription, you can now use it directly in Cline without managing API keys
Cline now offers comprehensive Jupyter Notebook support, giving data scientists the same AI-assisted experience that developers have come to expect – but designed specifically for how notebooks actually work.
Cline 3.51.0 is now available. This release adds support for OpenAI GPT‑5.2 Codex. OpenAI GPT‑5.2 Codex (gpt-5.2-codex) Cline 3.51.0 adds support for OpenAI GPT‑5.2 Codex (gpt-5.2-codex). OpenAI positions GPT‑5.2 Codex as an agentic coding model optimized
Most AI coding tools require sending code through their servers. For healthcare systems protecting patient records, banks safeguarding transaction data, and defense contractors working with sensitive or classified code, that approach fails immediately. Security teams block the tool. Developers revert to manual workflows. Productivity drops, not because AI is ineffective,
Biweekly livestream every other Thursday at 9 am PT. One hour of Cline updates, industry expert guests, and Q&A.
Cline 3.48.0 adds Skills compatibility. If you've already built Skills, you can now use them in Cline. This release also adds websearch tooling through the Cline provider, giving Cline access to real-time information when you need it. Skills Think about how you'd onboard a
One of the most common pieces of feedback we hear: "I want to keep coding while Cline works." When Cline edits a file, it opens the diff view and takes your cursor along with it. That's fine when you're watching Cline work, but not
We're partnering with LG CNS to build “AI-Native Development” (AIND) an agentic AI solution that handles the entire development lifecycle from requirements to code.
What if you could get plain-English explanations for every line of AI-generated code? Meet Cline's Explain Changes feature: your AI slop detector, code review accelerator, and sanity-preservation tool rolled into one.
Faster response times, zero markup fees, and better global coverage. The Cline provider now runs on Vercel's infrastructure, delivering measurable performance improvements while staying true to our open source values.
Updates
GPT-5.2 brings frontier-level agentic performance. Devstral 2 is the best open-weights option for Cline. And the new model picker makes switching between them instant.
Announcements
The stealth model is finally public: Devstral 2 scores 72.2% on SWE-bench Verified and works smoothly with Cline's multi-step tool workflows. Free for a limited time!
Updates
Understand AI-generated code before you ship it
Announcements
A new agentic coding model built for Cline drops today with free access during alpha.
Models
DeepSeek's new reasoning-first models are live. V3.2 for daily agentic coding; V3.2-Speciale for maximum reasoning power. Both at $0.28/$0.42 per million tokens.
Models
Opus 4.5 is Anthropic's most capable model. Use it for complex multi-step problems, heavy MCP usage, and tasks requiring autonomous reasoning through ambiguity.
Announcements
A call for contribution to establish reproducible, practical reinforcement learning environments sourced from real open source development work — with a $1M commitment to support open source maintainers.
Models
Gemini 3 Pro extends what Cline can attempt as an autonomous coding agent while keeping you in control.
Announcements
Cline 3.38.0 introduces Gemini 3 Pro Preview for enhanced reasoning and multimodal capabilities. We've also added AquaVoice Avalon, a voice-to-text model that specifically understands technical terms
Models
After weeks with GPT-5.1, we discovered it's unlike any coding model we've seen. It investigates obsessively, follows structure religiously, and sustains focus across massive tasks. We adapted Cline to channel these traits into stable, long-running execution.
Updates
GPT-5.1 ships with Cline-optimized prompting. Plus Nous Research's Hermes 4 models, Avalon speech-to-text with Linux support, and critical bug fixes.
Updates
Hooks let you inject custom scripts at key workflow moments to validate operations, monitor usage, and shape AI decisions. Currently supported on macOS and Linux.