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|
PluginRisingofficial publisher

Continue

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

Open-source code assistant, choice of models, autocompletion and chat on the codebase.

Established and solid, but the team has now moved on and the project is no longer maintained: worth watching for what comes next.

Official site GitHub · 36,314 ★
Overall score
7.9 /10
Security: one caveat, see the card
Utility
7.0
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

Developers working in VS Code or JetBrains lose time switching between their editor and an external assistant to get help with their code. Continue integrates directly into the editor to offer autocompletion, chat, and actions on the codebase without leaving the working environment.

The tool works as a plugin: it reads the context of the open project, sends the information to the model provider of your choice (OpenAI, Anthropic, a local model via Ollama, etc.) and displays suggestions or answers directly in the editor. You bring your own API key, meaning you choose the model and bear the associated costs.

Continue is aimed at developers familiar with VS Code or JetBrains who want a configurable, open-source coding assistant without a mandatory subscription. The Apache 2.0 licence also allows teams to self-host or adapt it to their needs.

However, the project has been acquired by Cursor and the GitHub repository is now read-only: there will be no new features or official fixes. Users looking for an actively maintained tool will need to turn to an alternative.

What it offers

  • ·Contextual code autocompletion directly inside the VS Code or JetBrains editor.
  • ·Built-in chat to ask questions about the codebase open in the editor.
  • ·Free choice of model provider: cloud services (OpenAI, Anthropic, etc.) or local models.
  • ·Also available as a command-line tool via the CLI published on npm.
  • ·Apache 2.0 licence: the source code is freely viewable, modifiable, and redistributable.
  • ·Final 2.0.0 release published with removal of anonymous telemetry and authentication.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
vscode, jetbrains, cli
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
Known incidents
Version 2.0 annoncée comme finale pour le plugin ; bascule vers le CLI.
Maintenance
Active
Last release
19 June 2026

Links and repository checked on 25 October 2026 · added on 1 July 2023

How to install Continue

1. Open VS Code and go to the Extensions tab. 2. Search for "Continue" and install the extension published by Continue. 3. Once installed, open the Continue panel in the sidebar. 4. Enter your API key for the model provider of your choice (or configure a local model to avoid sending data externally). 5. For the CLI, run the npm install command and follow the documentation at docs.continue.dev.
npm install -g @continuedev/cli

In the same category

Whole category Code →