# cline.bot > AI-optimized mirror of cline.bot containing 50 pages totalling 36,074 words of clean markdown content, structured data, and semantic HTML. Original source: https://cline.bot/. Last updated: 2026-04-30T23:27:02.623Z. Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG). ## Homepage - [The Open Coding Agent](/site-root.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (612 words) ## Articles & Blog Posts - [Simple, transparent pricing](/pricing/index.html): Flexible pricing for Cline AI coding agent. Free for individual developers, Enterprise for organizations. BYO API keys or use our managed infrastructure. (310 words) - [blog/20-one-shot-prompts-that-turn-kanban-into-an-autonomous-coding-machine.html](/blog/20-one-shot-prompts-that-turn-kanban-into-an-autonomous-coding-machine.html) (1 words) - [blog/author/tony/index.html](/blog/author/tony/index.html) (1 words) - [blog/what-a-sigkill-race-reveals-about-inference-speed/index.html](/blog/what-a-sigkill-race-reveals-about-inference-speed/index.html) (1 words) - [privacy/index.html](/privacy/index.html) (1 words) - [blog/prompts-as-playbooks-how-infrastructure-teams-codify-operational-knowledge.html](/blog/prompts-as-playbooks-how-infrastructure-teams-codify-operational-knowledge.html) (1 words) - [blog/12-coding-agents-defining-the-future-of-ai-development.html](/blog/12-coding-agents-defining-the-future-of-ai-development.html) (1 words) - [blog/a-practical-guide-to-hill-climbing/index.html](/blog/a-practical-guide-to-hill-climbing/index.html) (1 words) - [blog/the-invisible-trap-the-decisions-quietly-transferring-control-of-your-stack-to-model-providers.html](/blog/the-invisible-trap-the-decisions-quietly-transferring-control-of-your-stack-to-model-providers.html) (1 words) - [Chapter 1: LLM Fundamentals](/blog/llm-fundamentals/index.html): Learn how to choose the right LLM in Cline by understanding trade-offs in speed, cost, reasoning, and multimodality. (1,379 words) - [blog/top-11-open-source-autonomous-agents-frameworks-in-2025.html](/blog/top-11-open-source-autonomous-agents-frameworks-in-2025.html) (1 words) - [Navigating AI coding tool adoption in automotive environments](/blog/navigating-ai-coding-tool-adoption-in-automotive-environments.html): 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. (1,223 words) - [Cline: The Fastest Growing AI Open Source Project on GitHub in 2025, Thanks to You](/blog/cline-the-fastest-growing-ai-open-source-project-on-github-in-2025-thanks-to-you.html): GitHub's Octoverse 2025 report just crowned Cline the fastest-growing AI open source project by contributors, with 4,704% year-over-year growth. (737 words) - [Cline v3.39 introduces Explain Changes: understand AI-generated code before you ship it](/blog/cline-v3-39-explain-changes/index.html): Understand AI-generated code before you ship it (1,248 words) - [Commit messages aren't just for humans](/blog/commit-messages-arent-just-for-humans/index.html): Every few years, something shifts in how we write code and our workflows quietly adapt. Version control changed how we think about saving work. Code review changed how we think about readability. CI/CD changed how we think about testing. Now AI coding agents are changing something we barely think about at all: commit messages. Your commit history has a new audience. And that audience is reading more carefully than most of your teammates ever did. Here's what that looks like day to day. You ask (998 words) - [Cline v3.25: The Coding Agent Built for Hard Problems](/blog/cline-v3-25/index.html): In v3.25, Cline never lets go of the thread. (1,070 words) - [Introducing Cline CLI 2.0: from sidebar to the terminal](/blog/introducing-cline-cli-2-0/index.html): An open-source coding agent rebuilt for the terminal, with free models to get started. (1,253 words) - [Chapter 2: Cline Rules](/blog/cline-rules/index.html): Learn how System Prompt Rules guide coding style, security, and workflow ensuring consistency, safety, and alignment in every task. (1,073 words) - [Chapter 2: LLM Benchmarks](/blog/llm-benchmarks/index.html): Learn how to interpret LLM benchmarks—coding, domain, and tool-use—to match scores with your development needs. (1,266 words) - [Caleb Eom](/blog/author/caleb/index.html): Posts by Caleb Eom (225 words) - [How I Learned to Stop Course-Correcting and Start Using Message Checkpoints](/blog/how-i-learned-to-stop-course-correcting-and-start-using-message-checkpoints.html): Why hitting the reset button will actually save you time instead of fighting an upstream context current. (1,011 words) - [Enterprise AI coding that uses your infrastructure, not ours](/blog/enterprise-ai-coding-that-uses-your-infrastructure-not-ours.html): 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 (1,266 words) - [The architecture that gets AI coding tools approved](/blog/the-architecture-that-gets-ai-coding-tools-approved.html): 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 (1,135 words) - [Devstral 2: The best open-weights model for Cline just dropped](/blog/devstral-2-release/index.html): 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! (565 words) - [Chapter 3: Choosing LLM for Cline](/blog/choosing-llm-for-cline/index.html): Learn to pick the best LLM in Cline by balancing speed, context, cost, and flexibility—matching models to your specific tasks (1,136 words) - [Architects or Tenants: Modern AI Stacks Are Being Built on Rented Foundations](/blog/architects-or-tenants-modern-ai-stacks-are-being-built-on-rented-foundations.html): You're building on infrastructure you don't control, can't audit, and can't see degrading in real time. The Invisible Dependency For engineers, the inference vendor problem starts with a deceptively simple question: what happens when the model changes and you don't know about it? Most engineering teams treat their inference provider like a stable API. It isn't. Model versions rotate. Performance characteristics drift. Context window handling changes. Output formats shift in subtle ways that (733 words) - [Frequently Asked Questions](/faq/index.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (1,225 words) - [Cline Raises $32M Building the Open-source AI Coding Agent that Enterprises Trust](/blog/cline-raises-32m-series-a-and-seed-funding-building-the-open-source-ai-coding-agent-that-enterprises-trust.html): Cline has raised $32M in combined Series A and Seed funding, led by Emergence Capital and Pace Capital, with participation from 1984 Ventures (1,144 words) - [Cline mobile: how to vibe code from your phone](/blog/index.html): Latest updates and insights from the Cline team (331 words) - [Cline v3.26.6: Three Ways to Code for Free](/blog/cline-v3-26-6-three-ways-to-code-for-free/index.html): 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 (421 words) - [Cline v3.31: Voice Mode, Task Header Redesign, YOLO Mode](/blog/cline-v3-31/index.html): 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. (425 words) - [Cline v3.12: Faster Diff Edits, Model Favorites, and More](/blog/cline-v3-12-faster-diff-edits-model-favorites-and-more.html): We're excited to announce the release of Cline v3.12, packed with diff edit improvements, model favorites, new auto-approve options, and more. Let's dive into the highlights: Faster Diff Application 0:00 /0:05 1× Applying code changes suggested by Cline is now significantly faster, especially in large files. v3.12 boosts diff edit performance for a smoother, more responsive experience, letting you iterate faster. We've also added an indicator in th (463 words) - [Cline v3.28: Free Grok Extended + GPT-5 Optimized](/blog/cline-v3-28-free-grok-extended-gpt-5-optimized/index.html): xAI extends free Grok access while we ship GPT-5 optimizations that actually matter for real coding tasks. (311 words) - [5 Recommended MCP Servers for Cline](/blog/5-tool-mcp-starter-pack-for-cline/index.html): 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. (661 words) - [Cline's Context Window Explained: Maximize Performance, Minimize Cost](/blog/clines-context-window-explained-maximize-performance-minimize-cost.html): Ever wondered why a simple "Hi" to Cline might seem to use more resources than expected? Or perhaps you've noticed performance subtly changing during a long coding session? The answer often lies in a crucial, yet sometimes misunderstood, concept: the context window. Understanding it is key to unlocking Cline's full potential while managing performance and cost effectively. Think of the context window as the AI's short-term memory. It's the space where all the information relevant to your curren (800 words) - [Multiple coding agents. One UI to orchestrate them.](/kanban/index.html): A kanban-style task manager for orchestrating coding agents in worktrees. Break down work, assign it to agents, and ship faster — all from your terminal. (261 words) - [zAI and Cline deliver frontier-level AI coding for just $3](/blog/zai-cline-3-dollar-ai-coding/index.html): How zAI's GLM Coding Plans change the economics of AI development -- $3/month gets you what otherwise costs $200 (471 words) - [Cline mobile: how to vibe code from your phone](/blog/cline-mobile-how-to-vibe-code-from-your-phone/index.html): An engineer at Cline told me he was vibe coding on a road trip from his phone. His Mac was at home running Cline agents; he was checking on them from the passenger seat. Here's the setup. What you need Your phone and your Mac both need Tailscale installed and signed in to the same tailnet. Tailscale is a free mesh VPN; once both devices are on it, your phone can reach your Mac's local services from anywhere. Step 1: Start Kanban on your Mac By default, Cline's Kanban board binds to 127.0.0 (405 words) - [Kimi K2-0905: Moonshot’s Latest Open-Source Model is Live in Cline](/blog/moonshot-kimi-k2-0905/index.html): 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. (399 words) - [Brand Guidelines](/brand/index.html): Download official Cline brand assets including logos, icons, and avatars. Learn about our brand guidelines and naming conventions. (81 words) - [Sidd Sant](/blog/author/sidd/index.html): Posts by Sidd Sant (313 words) - [Plugins for Cline](/mcp-marketplace/index.html): Explore the Model Context Protocol (MCP) marketplace - a collection of powerful tools and capabilities available in Cline. (4,878 words) - [Contact Us](/contact/index.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (141 words) - [Post Not Found](/blog/cline-v3-26-6-three-ways-to-code-for-free.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (47 words) - [Contact Sales](/contact-sales/index.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (118 words) - [Post Not Found](/blog/cline-rewrite/index.html): Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide. (47 words) - [sitemap-xml.html](/sitemap-xml.html) (456 words) - [Application error: a client-side exception has occurred (see the browser console for more information).](/enterprise/index.html): Enterprise-grade AI coding with BYO Infrastructure, on-premise deployment, SSO, audit logs, and centralized governance. Trusted by Fortune 500 companies. (44 words) - [All Posts](/blog/archive/index.html): Complete archive of all blog posts from the Cline team (5,383 words) ## Resources - [Full Page Index](/index.html): Browse all cached pages with rich metadata - [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines - [XML Sitemap](/content/sitemap.xml): Machine-readable sitemap for crawler discovery - [Robots.txt](/content/robots.txt): Crawler directives