JetBrains AI
Also known as: Junie, JetBrains AI Assistant, Junie CLI
Junie is JetBrains' coding agent, working in the IDE and as a standalone CLI. It runs a plan execute verify loop with agentic debugging through the real IDE debugger, and offers model choice across frontier providers and bring your own key.
JetBrains AI centers on Junie, the company's coding agent, which autonomously plans and executes multi step tasks from a prompt. It makes large scale edits across files, runs tests and terminal commands, and uses external tools while reporting progress. Junie is generally available, following a preview, and runs both inside the JetBrains IDE family and as a standalone CLI in any terminal or CI/CD pipeline.
The agent runs a plan execute verify loop. The plan is an editable document the developer approves before code is written, and after each change Junie runs tests and IDE inspections to catch regressions, iterating when something fails. Debug mode, available in IntelliJ IDEA Ultimate, lets the agent attach to a live debugger session.
It sets breakpoints, steps through execution, inspects variables and call stacks across threads, and evaluates expressions in the paused frame, so it reasons over the program's observed runtime state. In the CLI, a /demo command runs the app in a virtual machine with a browser and a desktop, where a computer use model drives the interface and records the run, and each session keeps a transcript on disk.
Junie assembles context per task. It receives the open file and selection automatically, other files by @ mention, persistent project instructions from an AGENTS.md file under version control, and outside data through MCP servers. Broader project context is not added automatically, and an .aiignore file excludes files the agent may not process.
By default Junie asks permission before running commands, changing files or invoking external tools. The suggested diff or command can be reviewed before approval, and changes can be rolled back per file or wholesale afterwards. Brave mode is an explicit opt in that removes those prompts. Developers select the model and a reasoning level from frontier options across OpenAI, Anthropic, Google and xAI.
The CLI adds bring your own key, including OpenRouter, and local serving via Ollama, LiteLLM or LMStudio. Pricing is a separate AI subscription on top of an IDE license. For individuals there is a free tier with limited credits, AI Pro at $10 a month and AI Ultimate at $30 a month. Organization tiers are $20 for Pro and $60 for Ultimate and Enterprise, and credits are consumed per agentic task.
Vendor details
Canonical URL
https://jetbrains.com/junie
Category
Coding agent
Subcategory
Coding — IDE agent
Company status
first party product
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Junie acts through the IDE's own machinery. It edits across files, runs builds, tests and terminal commands, and drives the real IDE debugger through a bundled Debugger MCP Toolset. MCP client support spans the IDE and CLI with project and user scoped mcp.json configs, a registry of pre configured servers and an installation assistant, and the JetBrains IDE itself runs as an MCP server exposing IDE tools to external clients including Claude Code, Codex and GitHub Copilot CLI. The agent speaks ACP, so the same engine drives IDE chat, the tool window and the CLI.
In practice
You live in a JetBrains IDE and want an agent native to it. JetBrains AI centers on Junie, its coding agent, built into the tools your team already uses.
You want an agent that checks its own changes before handing them back. Junie runs a plan execute verify loop, running tests and IDE inspections after each change and iterating when something fails.
You want to use your own model keys and connect your own tools. JetBrains AI's CLI supports BYOK, MCP, and skills, so you control the model and the integrations.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
The agent acts through the IDE's own machinery. It edits across files, runs builds, tests and terminal commands, drives the real IDE debugger through a bundled Debugger MCP Toolset and reaches external systems through configured MCP servers, and the IDE itself is exposed as an MCP server to other clients. Sourcejetbrains.com/help/ai-assistant/junie-agent; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| Workflow Orchestration | Full |
|
Junie autonomously plans and executes complex multi step actions from a single prompt, making large scale edits across files, running tests and terminal commands and using external tools while reporting progress. It works in a plan, execute and verify loop where the plan is an editable document approved before code is written, and the agent iterates when tests fail. Sourcejetbrains.com/help/ai-assistant/junie-agent and junie.jetbrains.com/docs; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| Knowledge Grounding & RAG | Partial |
|
The open file and selection reach Junie as automatic IDE context, with other files attached by @ mention, AGENTS.md guidelines added to every task and MCP servers for outside data. The Junie plugin also has an opt in setting for embeddings based codebase indexing. How that index persists or stays current is not described, so context is assembled per task. Sourcejetbrains.com/help/ai-assistant/junie-agent and junie.jetbrains.com/docs/junie-plugin-project-settings; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-10-25 |
|
| Human Oversight & Guardrails | Full |
|
Junie asks permission by default before running bash commands, changing files, performing file operations or using external tools, with approve, reject or always allow per command, and the user can open the diff or the full command in the editor before deciding. Changes can be rolled back per file or all at once, and .aiignore restricts which files the agent may process. Brave mode is an explicit opt in that JetBrains warns can cause data loss. Sourcejetbrains.com/help/ai-assistant/junie-agent; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| Security, Identity & Governance | Partial |
|
User level controls cover .aiignore, which excludes files and directories from agent processing, AGENTS.md, which governs agent behavior under version control, and per command approval gates and .junie/mcp scoping, which limit what the agent may do. JetBrains offers an AI Enterprise tier but does not say what it adds. There is no SOC 2 or ISO attestation specific to the AI product, and no SSO, RBAC or admin governance surface. Sourcejetbrains.com/help/ai-assistant/junie-agent; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| Observability & Auditability | Full |
|
Junie CLI keeps each session's events log and a readable transcript on disk. It saves the full prompt, response and model usage history for resumable sessions and stores subagent transcripts, so a run can be reconstructed afterwards. These are local files rather than a central audit log. In the IDE, changes stay reviewable as diffs and can be rolled back one by one. Sourcejunie.jetbrains.com/docs/junie-cli; junie.jetbrains.com/docs/junie-cli.htmlread 2026-10-25 |
|
| Memory & State Persistence | Partial |
|
Persistent project context is carried in an AGENTS.md instructions file that Junie adds to every task and that can be version controlled, and sessions can be managed and their status checked through slash commands. There is no cross session agent memory or learned state store. Sourcejetbrains.com/help/ai-assistant/junie-agent; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| Deployment & Data Residency | Full |
|
Junie runs locally in the IDE or terminal, and Junie CLI can use Junie Local, a local inference engine for Apple Silicon, or a local Ollama, LM Studio or LiteLLM server, so code and inference stay on the customer's own machines. The Junie GitHub Action runs entirely on the customer's GitHub runners. JetBrains does not say what organization level hosting options AI Enterprise adds. Sourcejunie.jetbrains.com/docs/junie-local, custom-llm-ollama and junie-on-github; junie.jetbrains.com/docs/junie-local.htmlread 2026-09-29 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Several ready to use coding agents are selectable in AI Assistant chat, namely Junie, Claude Agent, Codex and the Copilot agent, and Junie ships a dedicated code review agent beside its coding agent. Most of these agents do the same job. Sourcejetbrains.com/help/ai-assistant/agents and junie.jetbrains.com/docs/junie-review-agent; jetbrains.com/help/ai-assistant/agents.htmlread 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
The same agent engine is invoked from IDE chat, the Junie tool window, a standalone CLI in any terminal, CI/CD pipelines via GitHub Actions and GitLab, and third party ACP clients. Remote and asynchronous runs let a long task started on a workstation be monitored elsewhere. Sourcejunie.jetbrains.com/docs and jetbrains.com/help/ai-assistant/junie-agentread 2026-08-30 |
|
| Model Flexibility & Routing | Full |
|
The model is selected from a list in the chat input with a configurable reasoning level, spanning frontier models from OpenAI, Anthropic, Google and xAI. The CLI adds bring your own key, including OpenRouter, and local models can be served through Ollama, LiteLLM or LMStudio. Sourcejetbrains.com/help/ai-assistant/junie-agent and junie.jetbrains.com/docs; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-08-30 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
MCP client support spans the IDE and CLI with project and user scoped mcp.json configs, a registry of pre configured servers and an MCP Installation Assistant. The IDE itself runs as an MCP server exposing IDE tools to external clients including Claude Code, Codex and Copilot CLI, a bundled Debugger MCP Toolset exposes debugger control, and the agent speaks ACP so the same engine drives IDE chat, the tool window and the CLI. Sourcejunie.jetbrains.com/docs/junie-cli-mcp-configuration and jetbrains.com/help/ai-assistant/mcp; junie.jetbrains.com/docs/junie-cli-mcp-configuration.htmlread 2026-08-30 |
|
| Testing, Debugging & Optimization | Partial |
|
Debug mode drives the IDE debugger against the customer's running program to inspect runtime state, and the agent runs tests and terminal commands as it works. That is debugging, with the agent checking its own changes against the customer's existing gates. There is no harness, scored test set or optimization loop for evaluating Junie's behavior, and the benchmark results JetBrains publishes are its own measurements. Sourcejetbrains.com/help/ai-assistant/junie-agent; jetbrains.com/help/ai-assistant/junie-agent.htmlread 2026-09-29 |
|
| Browser & Computer Use | Full |
|
Junie CLI's /demo command launches the app in a Docker virtual machine with Chromium and a desktop. A computer use model drives the interface and records screenshots and video. It is a demo workflow and needs Docker. In the IDE, the agent works through the IDE, terminal and debugger APIs instead. Sourcejunie.jetbrains.com/docs/junie-cli-demo; junie.jetbrains.com/docs/junie-cli-demo.htmlread 2026-10-25 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Junie Local, the fully on device version of the Junie coding agent, moved from experimental to stable on Windows PCs with NVIDIA RTX GPUs of at least 24 GB and added native support for NVIDIA RTX Spark PCs on Windows on Arm. The rebuilt installer checks the GPU and driver, sizes the context window to available GPU memory, and offers Qwen3.6-27B or a JetBrains blend of it.
Bears on: Agent capability
View sourceJunie Lite is a new free tier for the Junie coding agent, running on a free model in every JetBrains account with no trial or card required. Paid credit plans and bring your own key remain alongside it.
Bears on: Pricing / packaging
View sourceJetBrains updated its AI Assistant to natively integrate Claude Agent, powered by Anthropic's Agent SDK, directly into the IDE chat. The release also adds new spend management features, enabling users to track quota consumption and top up AI credits from within the interface.
Bears on: Integrations
View sourcePricing
AI Free at $0, then AI Pro from $10 a month.
A monthly subscription per tier that carries a quota of AI credits, each worth $1, with extra credits bought beyond the quota.
Included quota
AI Pro, the entry paid tier at $10 a month, includes 10 AI credits every 30 days, the Junie agent, Claude Agent, switching between models and context aware chat, on top of unlimited local completion. AI Free includes 3 credits every 30 days.
What is public
JetBrains AI (AI Assistant and the Junie agent) is a subscription on top of a JetBrains IDE license. Individuals choose AI Free ($0, 3 AI Credits per 30 days), AI Pro at $10 a month (10 credits, about $100 a year) or AI Ultimate at $30 a month (35 credits, $300 a year). Organization tiers are Pro at $20, Ultimate at $60 and Enterprise at $60. AI Pro is included free with the All Products Pack and dotUltimate.
Billing mechanics
Each tier bundles a monthly quota of AI credits, with one credit worth $1. Cloud chat, Junie and Claude Agent consume credits, while local code completion is unlimited and free. The quota scales with price, 10 credits on Pro and 35 plus a small bonus on Ultimate. Agent mode and pricier models, such as Claude Sonnet against Gemini Flash, use credits much faster. Use beyond the quota is covered by top-up credits, valid for 12 months.
Cost watchouts
JetBrains AI is billed on top of the IDE license. Credit consumption is not estimated before a task runs, and agent mode with premium models can use a month's credits in days, after which extra credits cost more. The IDE plugin does not accept the customer's own model key, which only the Junie CLI supports.
Variable cost rationale
AI credits are what is metered. Each tier includes a monthly quota (3 credits on AI Free, 10 on AI Pro, 35 on AI Ultimate, each credit worth $1), and cloud chat, the Junie agent and Claude Agent draw it down while local code completion is unlimited and free. Agent mode and premium models burn credits fast, and no estimate is shown before a task runs, so heavy users' spend is hard to predict. Once the quota is spent, extra credits cost $1 each and stay valid for 12 months, or the user moves up a tier. Organizations can set monthly spending limits per subscription.
Additional watchouts
JetBrains AI is an added cost on top of the IDE, and its credits run down fast on agentic work.
Overage / add-ons
Once the monthly credit quota is spent, top-up AI credits cost $1 each and stay valid for 12 months, or the user moves up a tier. Local completion keeps working without credits.
Sales call required
No, self serve available
Free / trial
AI Free with 3 AI credits every 30 days, Junie Lite free on an open model in Air and the Junie CLI with no card, and an AI Trial with 10 credits
Lowest paid plan
AI Pro at $10 per month for individuals, with 10 AI credits every 30 days
Commercial notes
AI Pro is bundled free with the All Products Pack and dotUltimate. Ultimate includes $35 a month in credits plus a $5 bonus that rolls over for 12 months. The Junie CLI accepts the customer's own API key from Anthropic, OpenAI, Google, xAI or OpenRouter. Models include GPT-5, Claude 4.5 Sonnet, Gemini 3 Flash and Gemini 2.5 Pro.
Key ambiguities
One credit buys roughly 10 code generation requests in AI Chat, 40 editor generation requests, 25 code explanations, 280 documentation requests or 140 commit messages. Nothing states what an agent task in Junie or Claude Agent costs in credits, so burn on agentic work is hard to predict.
Cancellation / refund
Monthly or annual billing, with annual saving about 17%. Subscriptions cancel at any time, and top-up credits stay valid for 12 months.
Support SLA / resale
Ultimate adds priority model access and a larger quota. Enterprise adds private deployment and data handling controls, and is sold only through JetBrains IDE Services.
Missing data
Exact credit costs per agent task are not documented.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
Alternatives to JetBrains AI
The closest documented capability profiles to JetBrains AI among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Cline12.0 / 14Matches JetBrains AI across all 14 documented capabilities
- Capy12.5 / 14Fuller documented coverage on Security, Identity & Governance
- Cursor12.5 / 14Fuller documented coverage on Security, Identity & GovernanceJetBrains AI vs Cursor →
- Google Antigravity12.5 / 14Fuller documented coverage on Security, Identity & Governance
- Base4413.0 / 14Fuller documented coverage on Security, Identity & Governance and Memory & State Persistence
- Factory13.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Security, Identity & Governance
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded