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

GitHub Copilot

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

Completion, chat, and agent mode from GitHub, inside your editor.

The simplest to activate; your code goes through GitHub and the model provider.

Overall score
7.5 /10
Security: one caveat, see the card
Utility
8.0
Reliability
6.0
Security
One caveat
Ease
1 click · Beginner

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 takes time: finding the right syntax, drafting repetitive functions, understanding an unfamiliar file. GitHub Copilot integrates directly into your editor to suggest completions, answer questions, and execute tasks autonomously.

In practice, the extension analyses the code around your cursor, other open files, and your repository context, then sends that information to a language model to generate a suggestion. In agent mode, Copilot can plan, explore, and modify files autonomously while you continue working.

GitHub Copilot is aimed at individual developers, students, and enterprise teams. The free plan offers 2,000 completions per month, which suits occasional use. Paid plans remove these limits and provide access to more powerful models as well as governance features for organisations.

The tool is less suitable for those working on highly sensitive codebases who cannot accept their code being sent to external servers, or for those who do not use any of the supported editors.

What it offers

  • ·Inline code completion: Copilot suggests the continuation of your code in real time inside the editor, with 2,000 completions per month on the free plan.
  • ·Agent mode: Copilot can plan and execute development tasks autonomously, modifying multiple files without manual intervention (paid).
  • ·Editor chat: ask questions about your code, request explanations or refactoring directly inside VS Code or JetBrains.
  • ·Language model selection: choose from several models based on your needs for speed, accuracy, or cost (paid).
  • ·Third-party agent access: connect Anthropic's Claude Code or OpenAI Codex to delegate tasks to these agents from within Copilot (paid).
  • ·CLI integration: use Copilot directly in the terminal via GitHub CLI to get help with commands.
  • ·Assisted code review: Copilot can analyse your changes and suggest improvements during code reviews (paid).
  • ·Organisation customisation: teams can create shared knowledge spaces from their repositories and documents to tailor Copilot's responses (paid).

In practice

Price
Freemium · from 10 €
Commercial use
Commercial use: yes
Available on
vscode, jetbrains, neovim, web
Host
vscode
FR interface
Yes

Security and data

Rating
Security: one caveat, see the card
Your data
Data with the vendor
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 June 2021

How to install GitHub Copilot

1. Open Visual Studio Code and go to the Extensions tab (Ctrl+Shift+X). 2. Search for "GitHub Copilot" and click Install. 3. Sign in with your GitHub account when prompted by the extension. 4. Choose a plan (the free plan requires no credit card). 5. Check the extension settings to see which file types are enabled, and disable Copilot for files containing sensitive data. 6. To opt out of having your data used for model training, go to your GitHub account settings and disable the corresponding option.

In the same category

Whole category Code →