LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Pluginofficial publisher

Cline

Plugin : A set of capabilities installed into an AI application or a host · requires vscode

Open source code agent in VS Code: plan then act mode, multi-file editing, terminal, native MCP client.

The best free agent with your own key; it executes commands, keep an eye on API costs.

Overall score
8.8 /10
Security: one caveat, see the card
Utility
9.0
Reliability
10.0
Security
One caveat
Ease
1 click · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Writing code across multiple files, running commands, and fixing compilation errors in real time are repetitive tasks that slow developers down. Cline is an open source coding agent that handles these operations directly in your editor or terminal, without forcing you to leave your working environment.

Cline works in two stages: in Plan mode, it explores your codebase, asks clarifying questions, and proposes a strategy; in Act mode, it executes changes file by file and command by command, asking for your approval at each step. Every edit appears as a diff you can accept, adjust, or revert. Checkpoints are saved automatically so you can undo the agent's work if needed.

Cline is aimed at developers who want to stay in control of their code while delegating repetitive tasks to an agent. It works with all major model providers (Anthropic, OpenAI, Google, AWS Bedrock, Azure, and more) as well as local models via Ollama or LM Studio. The VS Code extension and JetBrains plugin are free; you only pay for your API key or use a local model.

Cline is not suited for those looking for a ready-to-use tool with no configuration: you need to bring your own API key, monitor usage costs, and accept that your code is sent to the chosen model provider. Non-developer users or those unfamiliar with VS Code, JetBrains, or a terminal will find the learning curve steep.

What it offers

  • ·Plan then Act mode: Cline explores your code and proposes a strategy before acting, with human approval at each step or an activatable autopilot mode.
  • ·Coordinated multi-file editing: consistent changes across the entire project with automatic detection of type, import, and syntax errors.
  • ·Terminal command execution: package installation, test runs, deployments, and live dev server management.
  • ·Compatible with all major model providers: Anthropic, OpenAI, Google, AWS Bedrock, Azure, Ollama, LM Studio, and any OpenAI-compatible endpoint.
  • ·Native MCP client: connect to databases, APIs, and cloud infrastructure via community or custom MCP servers.
  • ·Project rules via .clinerules files: define your coding, architecture, and deployment conventions for the agent to follow automatically.
  • ·Available as a VS Code extension, JetBrains plugin, desktop app (macOS and Windows), and npm-installable CLI.
  • ·Multi-agent teams and scheduling: a coordinator agent delegates subtasks to specialist agents, with cron-based execution for recurring automations.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
vscode, windsurf
Host
vscode
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Your data
Local or cloud depending on use
Maintenance
Active
Last release
17 October 2026

Links and repository checked on 25 October 2026 · added on 1 July 2024

How to install Cline

1. Open VS Code and go to the Extensions tab (Ctrl+Shift+X). 2. Search for "Cline" and click Install (publisher: saoudrizwan.claude-dev). 3. Once installed, open the Cline panel in the sidebar. 4. Enter your API key (Anthropic, OpenAI, etc.) or configure a local model via Ollama. 5. Security note: your code is sent to the chosen model provider; do not use an API key with excessive permissions and review the provider's privacy policy.
npm i -g cline

In the same category

Whole category Code →