Loading tool details…
JetBrains' official autonomous coding agent, built into every JetBrains IDE and Rider — plans, edits, tests, and iterates end-to-end.
JetBrains' first-party autonomous coding agent, shipped inside IntelliJ, PyCharm, GoLand, WebStorm, and every other JetBrains IDE.
Junie is JetBrains' first-party autonomous coding agent, shipped inside every JetBrains IDE — IntelliJ IDEA, PyCharm, GoLand, WebStorm, RubyMine, PhpStorm, CLion, Rider — as an integrated 'Ask / Code / Agent' panel next to the standard AI Assistant. Where the AI Assistant handles line-level completion and short refactors, Junie is the multi-step agent: give it a task like 'add pagination to this endpoint and update the tests', and it plans, edits across files, runs the tests, reads failures, and iterates until green (or asks for help). It uses JetBrains' deep project models — inspections, refactoring engine, code index, run configurations, VCS — so edits respect language semantics rather than treating source as text.
Junie supports frontier models from Anthropic (Claude Sonnet/Opus 4.6), OpenAI (GPT-5, 5.4, 5.3-codex), Google (Gemini 3.1 Pro, 3 Flash), and xAI (Grok 4.1). You can switch models per task or per project, optimizing for cost or capability. This avoids the vendor lock-in common in competing agents.
One agent runs in your terminal, JetBrains IDEs, Zed, Air, GitHub Actions, and GitLab CI/CD. Trigger Junie from GitHub issues and PRs or GitLab issues and MRs, or invoke it locally during development. The shared agent state means context follows you between local and CI environments.
Planning Mode decomposes complex tasks into a reviewable, editable plan before any code is written, while Live Prompting lets you update instructions mid-execution without restarting. Together, these give granular Human-in-the-Loop control. This reduces credit waste on misunderstood tasks compared to fire-and-forget agents.
Connect your own API keys from OpenAI, Anthropic, Gemini, xAI, or OpenRouter to use Junie without JetBrains-side credits. This puts cost control, rate limits, and data routing in the user's hands. It's especially valuable for teams with existing enterprise contracts or strict data residency requirements.
Define your own subagents for recurring task types, apply Agent Skills for domain-specific rules, and write Custom Guidelines that encode team conventions. Combined with one-click MCP server installation, Junie can be tailored to specific codebases without rebuilding integrations from scratch. This makes it adaptable to enterprise environments with strong style or compliance requirements.
$0
$10/month or $100/year
$20/month or $200/year per user
Higher tier
Ready to get started with Junie?
View Pricing Options →We believe in transparent reviews. Here's what Junie doesn't handle well:
Junie supports the latest 2026 frontier models including Claude Sonnet and Opus 4.6, GPT-5/5.4/5.3-codex, Gemini 3.1 Pro and 3 Flash, and Grok 4.1. The platform launched expanded toolchain integrations covering Zed and Air editors, GitHub Actions, and GitLab CI/CD, plus a new Planning Mode, Live Prompting, Custom Subagents, Agent Skills, and one-click MCP server configuration. AI Enterprise tier with maximum credits and custom integrations is announced as 'Soon'. Junie remains in Beta as of 2026.
AI coding assistants
Agentic AI coding IDE for developers who want autocomplete, chat, codebase context, and multi-file editing workflows.
AI Coding
Open-source AI pair-programmer that lives in your terminal, uses Git for every change, and works with GPT, Claude, Gemini, DeepSeek, and local models.
Pricing and features change often. If anything on this Junie page is wrong or missing, tell us and include a link to the source. We review every correction.
I ran a six-week evaluation of 15 AI developer tools across four workloads: a Flask-to-FastAPI refactor, a Next.js dashboard built from scratch, 23 bug-fix issues sampled from SWE-bench Verified, and a Rust-to-Go port of a 600-line CLI. **Rankings reflect what shipped working cod
Hidden gems in the AI agent tooling space — from browser infrastructure to memory platforms to observability tools. These production-ready tools solve real problems that most developers haven't discovered yet.