Cline Bot · Tools

Cline

Visit website

At a glance

Price
Pricing on request
Vendor
Cline Bot

Specifications & properties

Key decision factors

Pricing model
Open source 1
Tool form
  • IDE plugin
1
Autonomy level
Supervised agent 1
Model choice
Bring your own key (BYO) 1

Pricing

Price from
Pricing on request 1
Free tier
Yes 1

Model

Available models
Claude, GPT, Gemini, local Ollama / LM Studio, or any OpenAI-compatible endpoint 1

Capabilities

Terminal/command execution
Yes 1

Integration

IDE integrations
  • VS Code
  • JetBrains
1
MCP support
Yes 1
Report data / suggest a correction

Cline is an open-source AI coding agent for VS Code and JetBrains with plan/act modes, terminal execution, and MCP support.

Profile

Cline is an open-source AI coding agent that lives inside VS Code, JetBrains, and the terminal, built by Cline Bot Inc. It plans and executes multi-file edits, runs shell commands, and reports back for review, rather than just autocompleting single lines, and it is model-agnostic so teams can bring their own AI provider instead of being locked into one vendor.

Who builds it

  • Cline is developed by Cline Bot Inc. as an open-source project with more than 250 contributors.
  • Its GitHub repository has passed 64,600 stars and the project reports over 8 million installs across its supported platforms.

Core features

  • Multi-file edits with coordinated changes across a project, plus terminal/bash command execution with real-time output monitoring.
  • "Plan and Act" mode that separates strategizing from execution so a developer can review an approach before Cline touches files.
  • Project-specific .clinerules files for custom rules and reusable skills.
  • Model Context Protocol (MCP) and plugin extensibility, including an MCP Marketplace.
  • Model-agnostic model access: Anthropic Claude, OpenAI GPT models, Google Gemini, OpenRouter's 200+ models, AWS Bedrock, Azure/GCP Vertex, Cerebras, Groq, and local models via Ollama or LM Studio.
  • Headless/CLI mode for CI pipelines and scripting, plus integrations with Slack, Linear, Telegram, and Discord.

Pricing

  • Cline the extension is free and open source (Apache 2.0). You install it at no cost and only pay for AI inference — either by bringing your own API key from a provider like OpenAI or Anthropic, or by buying inference credits at cost through Cline with no subscription or seat fee.
  • Enterprise is custom-priced (contact sales) and adds the JetBrains extension, SSO/OIDC, an SLA, dedicated support, centralized billing, a team management dashboard, role-based access control, and authentication logs.

Open source and self-hosting

Cline's core is fully open source under the Apache 2.0 license on GitHub, so it can be inspected, self-hosted in the sense of running entirely against your own infrastructure and model provider, and modified by the community. Because Cline is model-agnostic, an organization can route all AI calls through its own Bedrock, Vertex, or Azure OpenAI deployment, keeping inference inside its own cloud boundary rather than a third-party model host it doesn't control.

Who it's for

Individual developers who want a free, provider-flexible autonomous coding agent inside their existing editor will find the open-source tier sufficient, since there is no seat fee and API costs are pay-as-you-go. Larger engineering organizations that need SSO, audit logs, and centralized governance over which models and providers are allowed are the target for the Enterprise tier, which several large companies use according to Cline's own site.

Data handling

By default Cline collects only anonymized product-usage telemetry — which tools and modes were used, task start/finish events, rough token counts — and explicitly never collects source code, file contents, file paths, command arguments, conversation content, or credentials. Telemetry can be switched off at any time in Cline's settings and also follows VS Code's global telemetry preference, so teams that want zero analytics reporting can disable it entirely while still using the agent normally.

Frequently asked questions

Is Cline free?

Yes — Cline itself is completely free and open source; you only pay for the underlying AI model's token usage, either via your own API key or Cline's pay-as-you-go inference credits. There is no subscription or per-seat fee for the open-source version.

Is Cline open source?

Yes, Cline is released under the Apache 2.0 license and developed in the open on GitHub, where the project has passed 64,600 stars and over 250 contributors. The repository is a legitimate primary source for its install, licensing, and feature details.

What IDEs and platforms does Cline support?

Cline is available as a VS Code extension, a JetBrains plugin (early access), and works inside Cursor and Windsurf since those are VS Code-compatible; it also ships a cross-platform CLI/terminal tool for macOS, Windows, and Linux. Installation of the CLI is a single command via npm.

What AI models can Cline use?

Cline is model-agnostic and connects to providers including Anthropic Claude, OpenAI, Google Gemini, OpenRouter's 200+ models, AWS Bedrock, Azure/GCP Vertex, Cerebras, and Groq, plus local models through Ollama or LM Studio. Users choose their own provider rather than being locked to one model.

Does Cline collect my code or telemetry data?

Cline collects anonymized usage telemetry such as which tools and modes are used, but explicitly states it never collects code or file contents, file paths, command arguments, conversation content, or credentials. Telemetry is optional and can be toggled off at any time in settings, and it also respects VS Code's global telemetry setting.

What does Cline's Enterprise plan add over the free version?

Cline Enterprise is custom-priced and adds the JetBrains extension, SSO/OIDC, an SLA, dedicated support, centralized billing, a team management dashboard, role-based access control, and authentication logs on top of everything in the free open-source tier. It also supports routing all model traffic through an organization's own Bedrock, Vertex, or Azure OpenAI deployment for VPC, on-premises, or air-gapped setups.