
Introducing Cline CLI 2.0: from sidebar to the terminal
An open-source coding agent rebuilt for the terminal, with free models to get started.
Complete archive of all blog posts from the Cline team

An open-source coding agent rebuilt for the terminal, with free models to get started.

MiniMax just released M2.5. It's available now in Cline across VS Code, JetBrains, Zed, Neovim, Emacs, and the Cline CLI. MiniMax is offering M2.5 for free for a limited time, so there's no barrier to trying it out.

Last week, hundreds of developers descended on Frontier Tower in San Francisco for ClawCon – and it was unlike any tech event I've been to. Laptop tattoos. Lobster merch flying off tables. The kind of energy that only happens when open source builders get together to celebrate something they actually care about. Cline co-hosted the event, and I was there representing us. Here's what happened. pic.twitter.com/5OC9tSZjhq — Dave Morin (@davemorin) February 5, 2026 What is ClawCon ClawCon is

Anthropic's most intelligent model is now in Cline. We've been testing Claude Opus 4.6 across the extension and the CLI. Here's why we're calling it The Deep Thinker.

I watched a developer waste $200 in API tokens one afternoon. Not because they were building something trivial – they were tackling important infrastructure work. Not because they were inexperienced – they had 15 years of backend development under their belt. The problem was simpler and more frustrating: they weren't wielding their tools effectively. Every few minutes, they'd hit revert. The AI would generate code that almost worked but missed the mark. They'd course-correct with another prompt

Redesigned terminal UI, better support for running parallel agents, ACP integration for Zed/Neovim/Emacs, and free Kimi K2.5 access (and more to come) during the release.

A premium car today contains over 100 million lines of code -- more than a fighter jet, more than Facebook's entire codebase. AI coding assistants promise to help close the productivity gap. But most get rejected before they reach a single developer's machine.

We surpassed five million installations of Cline across VS Code, JetBrains, Cursor, Windsurf, and other editors through OpenVSX.

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 zero tolerance for opaque SaaS dependencies. Whether you're building software that handles financial transactions, processe

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 for real-world software engineering: long-horizon work, big refactors/migrations, and reliable operation in terminal-heavy workflows. It also includes improvements in long-context understanding and tool-calling reliability, and stronger vis

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, but because the architecture was wrong from the start. Cline takes a different approach. Your code never leaves your environ

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 new team member. You wouldn't dump every document on them at once. You'd give them an overview, then point them to detailed guides when they're actually working on specific tasks. Skills work the same way. Each skill is 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 ideal when you want to stay focused on your own code in another file. Introducing Background Edits Background Edits is an experimental feature that lets Cline edit files without opening the diff view or stealing your cursor. You stay in your file; Cline works in th

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.

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.

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!

Understand AI-generated code before you ship it

A new agentic coding model built for Cline drops today with free access during alpha.

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.

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.

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.

Gemini 3 Pro extends what Cline can attempt as an autonomous coding agent while keeping you in control.

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

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.

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.

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.

GitHub's Octoverse 2025 report just crowned Cline the fastest-growing AI open source project by contributors, with 4,704% year-over-year growth.

The rise of intelligent, tool-enabled coding agents marks a turning point in how software is written.

Native tool calling reduces errors and enables parallel execution. Auto-approve menu redesigned for better workflow. MiniMax M2 brings continuous reasoning, free until November 7.

Open source models can rival the best—if we give them the ground to stand on.

The model-agnostic, IDE-agnostic, inference-agnostic, open-source coding agent that 3 million developers trust—now with enterprise security, governance, and observability at scale.

Cline CLI Preview is available. After months of work, Cline is now a standalone service powered by Cline Core, exposing a gRPC API for scriptable automation, multi-instance orchestration, and building custom interfaces. The agent loop that works anywhere.

The Cline CLI (Preview) completes our vision of full agnosticism. One agent loop, Cline Core, that can run on any model, any surface, and any inference. The primitive for AI coding that enables everyone to build their own interfaces. Now available for Linux and macOS.

Analysis of Plan/Act model usage patterns from the last 7 days

Cline’s real-world telemetry shows Sonnet 4.5 at 96.2% and GLM-4.6 at 94.9% diff-edit success. The open-source gap is down to basis points. Try both in Cline.

After extensive testing, AMD found only specific models work reliably with Cline. Here's your complete guide to choosing the right model for your RAM.

Anthropic’s Claude Sonnet 4.5 is now in Cline, bringing 200k context, test-first workflows, and autonomous docs — built for real software development.

The stealth model gets 5x more context. Code-supernova now handles 1 million tokens.

If you're typing the same instructions to your agent every week, you're the process. Write them once as a markdown workflow, invoke with a slash command, and watch the agent execute with verification.

In v3.31, we're making Cline feel more natural to interact with. Three features that reduce the friction between what you want to build and getting it built.

OpenAI's GPT-5-Codex, optimized for coding agents, is now available in Cline with adaptive reasoning that uses 93% fewer tokens on simple tasks and 2x more on complex ones.

A mysterious coding model built for agentic coding, "code-supernova", drops in Cline with free access during alpha

How zAI's GLM Coding Plans change the economics of AI development -- $3/month gets you what otherwise costs $200

Cline is model agnostic, inference agnostic, and now platform agnostic -- running natively in JetBrains alongside VS Code. Your models, your providers, your IDE, no lock-in at any layer.

With LLMs multiplying fast, our new Fundamentals module helps you master model selection, tradeoffs, and coding workflows.

We’re launching AI Coding University to help developers build the core skills for agentic coding.

xAI extends free Grok access while we ship GPT-5 optimizations that actually matter for real coding tasks.

Most developers clutter their context with rules when they should build workflows. Workflows inject instructions on-demand and consume tokens only when invoked, while clinerules append to every system prompt.

Two mysterious models with 2M context windows appeared on major AI gateways. We tracked their performance across thousands of real coding tasks to see if the hype matches reality.

Kimi K2-0905 doubles the context window to 256k tokens and delivers some of the highest reliability tool calling we've seen in an open-source model. Built for coding agents that actually work.

For the first time, local models are powerful enough to run Cline effectively on a laptop.

hello! Three major capabilities land in Cline v3.26.6, each offering a different path to free AI-powered coding. Whether you want cloud speed, local privacy, or generous daily limits, this release has you covered. Speed without the wait xAI's Grok Code Fast model is now available in Cline, delivering responses so quickly that waiting for the model stops being a bottleneck in your workflow. Built specifically for agentic coding workflows, it excels at the iterative development sessions that d

Say hello to Grok Code Fast – or as you've known it, Sonic.

In building AI agents at Cline, we've discovered that the most dangerous ideas aren't the obviously bad ones, they're the seductive ones that sound brilliant in theory but fail in practice.

Free stealth model is now available in Cline

The Cline Context Playbook: when to use Deep Planning, Focus Chain, Auto Compact, /smol, /newtask, and Memory Bank

Bigger context windows don’t stop coding agents from drifting. Cline’s new Focus Chain keeps every step anchored to the goal — so even the longest tasks finish exactly where they’re meant to.

In v3.25, Cline never lets go of the thread.

Claude Sonnet 4 now supports 1 million tokens of context – a 5x increase from the previous 200K limit.

The most intelligent and reliable coding model from OpenAI is now available in Cline – and it's half the price of Sonnet 4.

Every developer knows the feeling. You're in flow, building something complex, and then – you wait. The model thinks. You watch the tokens slowly stream in. Your mind wanders. By the time the response arrives, you've lost your train of thought. Today, that changes. We're partnering with Cerebras to deliver code generation at 2,000 tokens per second in Cline. That's 40x faster than typical providers. No more waiting. Your thoughts flow directly into working code. How They Do It Cerebras didn

Cline has raised $32M in combined Series A and Seed funding, led by Emergence Capital and Pace Capital, with participation from 1984 Ventures

The age of AI coding subscriptions is ending. Not because companies want it to, but because the economics force it. When you can arbitrage a subscription in a commodity market, the market will take full advantage. Direct usage-based pricing is the only market-efficient outcome.

Test Kimi K2, the open-source model achieving 65.8% on SWE-bench. Available now in Cline.

Whether it be an Anthropic API key or using the Cline provider for inference, you can expect to pay what the provider charges for their inference, and none more. Cline doesn't charge any platform fees.

Andrei fixed the terminal! Cline v3.18.1-4 is a patch release series that addresses the terminal output issues that have been affecting your smooth usage of Cline.

Why hitting the reset button will actually save you time instead of fighting an upstream context current.

By connecting Cline to specialized servers for search, documentation, browser control, and more, you can create a workflow that gives Cline access to context outside of your codebase and your model's knowledge cutoff.

Cline v3.18 is a focused release that introduces the Gemini CLI as a provider, delivers significant performance and reliability upgrades for the Claude 4 family, and ships several important core improvements.

Tap into your existing Claude Max or Pro subscription to use Cline without paying per-message pricing.

When it comes to modifying code, Cline has two primary methods in its toolkit: 1. write_to_file for creating or overwriting entire files, and 2. replace_in_file for making surgical, targeted changes (diff edits). We call these targeted changes "diff edits," and their reliability is fundamental to the agent's performance. As part of our push to optimize every core subsystem of the agent, we've been intensely focused on improving the success rate of these diff edits. The result? We recently

We're excited to announce that Amazon Web Services has officially contributed 35 new Model Context Protocol (MCP) servers to the Cline ecosystem. This is a major milestone that extends the power of AI to nearly every corner of the AWS platform, allowing developers to manage their entire cloud infrastructure using natural language. For a long time, managing a complex cloud environment meant juggling dozens of consoles, dashboards, and configuration files. With these new MCP servers, that complex

For some time, Cline offered two ways to provide persistent guidance: a simple "Custom Instructions" text box and the more robust, file-based .clinerules system. While the text box was a familiar starting point, it was always a stepping stone. Today, we're fully embracing the more powerful paradigm by deprecating the old Custom Instructions feature to focus entirely on .clinerules. The reason is simple: treating instructions as code is fundamentally better. A single, static text box doesn’t sca

Hello Cline community 🫡 v3.17.14 is focused on expanding provider support, refining the terminal experience, and shipping a handful of important stability improvements. New Provider Integrations We're committed to making Cline as flexible as possible, and that means letting you plug in the tools you already use. This release adds support for two new API providers. * SAP AI Core: We've also added support for SAP AI Core, enabling users to connect to both Claude and GPT models through the s

It feels like every month there's a new "must-have" AI coding tool. The FOMO is real; but so is the fatigue of constantly switching, learning new workflows, and migrating settings. It’s exhausting, but that's the price for developers who want to be armed with the greatest leverage powered by AI. The magic of AI coding isn't just in the tool itself; it's in the power of the underlying model. And the "best" model is a moving target. One year ago, GPT-4o led the way. Then Anthropic's Claude 3.5 So

We really appreciate all our contributors who have submitted code, ideas, and other improvement to Cline. For me it's honestly been one of the coolest parts of being involved with this project. The creativity, expertise, and dedication I've see from our community has always blown me away. Thank you so much! Current state We've been working hard to merge as many community contributions as possible, but let's be real, our existing system isn't working. Our PR backlog keeps growing, and that's o

Remember when AI coding meant tab autocomplete? The human did 95% of the work: navigating the codebase, finding the right files, locating the exact spot to edit, beginning to type, and only then could AI offer a helpful suggestion. The human was the driver, AI was barely a passenger. Today's agentic AI can search codebases, read files, write entire modules, refactor systems, and orchestrate complex changes across multiple files. With tools like Cline, AI has eaten up nearly the entire coding pi

When developers first encounter Cline, they often describe it as their "AGI moment" – that pivotal instant when they realize AI has crossed from helpful suggestion tool to genuine coding partner. But what exactly separates a true coding agent from the growing crowd of AI-powered development tools? The answer lies in understanding what the word "agent" actually means. Defining the Agent OpenAI defines an agent as "a system that independently accomplishes tasks on your behalf." Anthropic takes

Yesterday, Windsurf users lost access to Claude 3.x models with five days' notice. OpenAI's acquisition of Windsurf created competitive tensions with Anthropic, and developers got caught in the crossfire. Picture this: you're deep into a critical project, and suddenly your AI coding assistant is crippled by corporate politics. Free tier users lost access entirely; paid subscribers face severe capacity constraints. This validates why we built Cline differently from day one. When Corporate War

Hello Cline community 🫡 We've been burning the candle at both ends to make Cline work as well as possible with the new Claude 4 family of models, and we're excited to share that Cline 3.17.9 includes experimental Claude 4 support that addresses reliability issues, an upgraded task timeline with scrolling navigation, and expanded file upload capabilities for data analysis. Experimental Claude 4 Support If you've been using Claude 4 with Cline, you've probably noticed some frustrating edit fai

Here's a common question we get from prospective Cline users: "How does Cline handle large codebases? Do you use RAG to index everything?" It's a reasonable question. Retrieval Augmented Generation (RAG) has become the go-to solution for giving AI systems access to large knowledge bases. But for Cline, we've taken a deliberately different path. We don't index your codebase, and this choice isn't an oversight, it's a fundamental design decision that delivers better code quality, stronger securit

Cline v3.17 brings several solid improvements to enhance your development workflow. The highlight is Global Workflows – a feature many of you have been requesting – along with a redesigned settings interface and expanded provider support. Global Workflows The standout feature in this release is global workflows. If you've built a workflow that works brilliantly in one project, you can now share it across all your workspaces. Here's how it works: * Global workflows live in ~/Documents/Cline

Welcome to Cline v3.16! We're really excited about this release, especially a new feature that's already making a big difference for our own team: Workflows. It's already saving our team countless hours and we know it can do the same for you. Let's get to it! → Workflows → Your Personal Automation Powerhouse You know those repetitive sequences you find yourself doing all the time? Setting up a new project module, running through a pre-commit checklist, or even the detailed steps for a PR revi

When you first dive into a powerful tool like Cline, it's natural to wonder, "What's the best way to set this up?" The beauty of Cline is that it's designed to adapt and grow with you. There isn't a one-size-fits-all answer, but rather a spectrum of configurations that can match your immediate needs and the complexity of the tasks you're tackling. This post will walk you through three common setup approaches – Beginner, Intermediate, and Advanced. My goal is to help you find what works best for

If you've been in tech for a while, you've seen the cycles. Skepticism greets nearly every major shift. We've certainly observed some resistance from engineers, a common echo of the "pessimistic streak" that often surfaces in tech hubs when new technologies emerge. It's reminiscent of the doubts that once surrounded Linux, the cloud, and even JavaScript on the server. History tends to rhyme, and the current wave of AI in software development is no different. But here’s the thing: while some deb

Explore open-source, affordable Claude Code alternatives with local model support, no usage limits, and seamless VS Code compatibility for true agentic coding.

Welcome to Cline v3.15! This update is all about refining the experience of Cline as your daily driver. Let's get right into it. Task Timeline = Story board of your conversation Ever wished you could instantly see the "story" of how Cline tackled a complex task? With v3.15, we're introducing the Task Timeline, a sleek, visual "storyboard" integrated directly into your task header. This isn't just a log; it's an intuitive series of blocks charting every key step Cline takes – from tool calls t

A practical, step-by-step guide to selecting and deploying open-source Cursor alternatives in VS Code—including self-hosted setups and local-model workflows. This guide introduces Cline, an open-source AI coding agent designed for privacy, flexibility, and zero vendor lock-in.

The allure of AI in development often conjures images of instant solutions: a quick prompt, a flash of code, and on to the next task. But as many developers have discovered, this path can quickly become a frustrating loop of near-misses, endless re-prompting, and AI-generated code that feels strangely disconnected from the project's core. This isn't merely inefficient; it represents a fundamental misunderstanding of how to truly harness the power of coding agents. At Cline, we see a more robust

I've heard it said that "patterns are what companies talk about when they're dying". This may be true, but it is also what companies talk about once they've hit PMF. Don't fool yourself, do you really need scale? If you haven't experienced a hyper growth startup before, it can be easy to dismiss things like composability, scalability, security, testability, redundancy, CI/CD, and the like as a needless waste of time. It's true that most startups think about these things way too early. Until y

We're excited to announce Cline v3.14, bringing significant improvements to Gemini caching and cost transparency, more flexible checkpoints, a new command for rule creation, LaTeX support, and a host of quality-of-life updates driven by community feedback. Let's dive into the highlights: Improved Gemini Caching & Transparency We know accurate cost tracking and efficient model usage are crucial. While Gemini's context caching offers potential savings, ensuring its effectiveness and providing

In today's rapidly evolving technological landscape, artificial intelligence has transformed from a futuristic concept to an essential productivity tool for software engineers. However, many organizations find themselves at a crossroads: how to harness the power of AI while maintaining security, compliance, and control over sensitive code and data. The answer lies not in restricting AI access, but in strategically implementing secure, enterprise-ready AI solutions that empower development teams

One of the most common questions developers ask when getting started with Cline is: "Which AI model should I use?" With Cline's approach to supporting virtually all models from the top providers (Anthropic, Google Gemini, OpenAI, and others), the choices can be overwhelming. The truth is, there's no single "best" model for all situations. What works brilliantly for one development task might be overkill – or underpowered – for another. Let's break down how to think about model selection through

As Product Marketing Manager at Cline, I often experiment with ways to fine-tune Cline's behavior for different tasks. For a while, I relied on a system of .clinerules/ and clinerules-bank/ folders, manually dragging rule files back and forth to activate different instruction sets. Honestly? It was kind of annoying – difficult to keep track of which rules were active, easy to forget to switch them, and just generally cumbersome. But I did get tremendous value from the "modular" nature of these .