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

JetBrains AI Assistant et Junie

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

AI assistant and autonomous Junie agent integrated into JetBrains IDEs.

The natural choice if you live in IntelliJ or PyCharm.

Overall score
7.1 /10
Security: one caveat, see the card
Utility
7.0
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

Developers working in a JetBrains IDE (IntelliJ IDEA, PyCharm, etc.) often have to switch between their editor and external AI tools, breaking their workflow. JetBrains AI Assistant and Junie solve this by embedding AI assistance and an autonomous agent directly into the development environment.

Junie acts as a coding agent capable of planning a task, writing code, modifying files, and running from the terminal, the IDE, GitHub, or GitLab. It supports more than ten models via a BYOK (bring your own key) approach, with no markup on provider pricing. A Plan mode lets the agent draft a structured roadmap before touching any code, which the user can approve or redirect.

The tool is aimed at individual developers and teams already using the JetBrains ecosystem who want to automate repetitive tasks such as migrations, adding test coverage, or framework upgrades. The custom guidelines feature lets you teach Junie your team's conventions, which are remembered across sessions.

However, if you do not use a JetBrains IDE or prefer a universal editor-agnostic tool, Junie may not be the best fit. The agent modifies project files directly, which requires careful oversight before entrusting it with sensitive codebases.

What it offers

  • ·Junie agent capable of planning, coding, and modifying files autonomously from the terminal or IDE.
  • ·Advanced Plan mode: Junie writes a structured plan (requirements, design, delivery stages) before touching any code, which you can approve or redirect. (paid)
  • ·Support for more than ten AI models via BYOK (bring your own key), with no markup on provider pricing.
  • ·Live Prompting: steer the agent mid-task without starting over.
  • ·GitHub and GitLab integration: Junie can be triggered directly from issues or pull requests.
  • ·Custom guidelines and skills: teach Junie your team's conventions, remembered across sessions.
  • ·Remote control: start a task from your laptop and monitor progress from another device via the web app.
  • ·SOC 2 certification: JetBrains tools meet recognised security standards for data protection.

In practice

Price
Freemium · from 10 €
Commercial use
Commercial use: yes
Available on
jetbrains
Host
jetbrains
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 April 2025

How to install JetBrains AI Assistant et Junie

1. Open your terminal (Mac or Linux) and paste the installation command provided by JetBrains. 2. Follow the on-screen instructions to complete the Junie CLI installation. 3. To use it inside a JetBrains IDE, install the AI Assistant plugin from your IDE's marketplace. 4. Log in with your JetBrains account to activate your free credits (no credit card required). 5. Before running a task on an existing project, make sure your code is versioned (Git) so you can review and revert any changes made by the agent.
curl -fsSL https://junie.jetbrains.com/install.sh | bash

In the same category

Whole category Code →