# Junie CLI (slim)

> JetBrains' coding agent for the terminal, run as junie. It plans, edits files, runs commands and calls MCP servers, with an action allowlist, one-shot headless runs with JSON output for CI and an ACP mode for editors.

- Full: https://www.anchorterminal.com/tools/junie.md (~11,450 tokens) · this version ~2,030 tokens · JSON https://www.anchorterminal.com/tools/junie.json · canonical https://www.anchorterminal.com/tools/junie
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-19 · pricing https://www.anchorterminal.com/tools/junie#pricing · reviews https://www.anchorterminal.com/tools/junie#reviews
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**D · 53.2/100 · rank #804 of 1146 · #31 in Agent harnesses · not agent-ready · confidence medium**


Assessment: Runs headless with JSON output, speaks ACP, and works with JetBrains AI plans, a free Junie Lite tier, the owner's own provider keys or a local endpoint. Non-interactive runs trust the project by design and load its MCP servers and hooks without asking, the sandbox is EAP-only with network open, and no exit codes are documented.

## Facts

- Kind: Agent harness · vendor: JetBrains · category: Agent harnesses · legal entity: JetBrains s.r.o. · provenance 99/100
- Packages: npm `@jetbrains/junie`
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: Proprietary, JetBrains s.r.o., all rights reserved, under the JetBrains AI Terms of Service. The GitHub repository holds the README, release binaries and the issue tracker, not source
- Probe metrics: not measured yet (probes haven't run)
- Install: Shell and PowerShell scripts for macOS, Linux and Windows on x86-64 and ARM64, a Homebrew tap (jetbrains-junie/junie) and npm (@jetbrains/junie). The scripts check SHA-256 sums from update-info.jsonl and proceed without one for an unlisted version
- Channels: release, eap, nightly and experimental, chosen with `--channel`, with `--use-version` to pin a build. The CLI checks for updates on start unless `--skip-update-check` is set
- Headless: `junie --auth="$JUNIE_API_KEY" "prompt"`, `--task`, piped input with `--input-format text` or `json`, output as text, json or json-stream, `--json-output-file`, `--review`, `--merge` and `--rebase`
- ACP: `junie --acp true`, JSON-RPC over stdio. Hooks don't run in ACP or server hosts yet
- Sign-in: JetBrains Account in a browser, a Junie API key from junie.jetbrains.com/cli, BYOK keys (Anthropic, OpenAI, Google, xAI, Meta, OpenRouter, GitHub Copilot), a LiteLLM proxy or custom endpoints such as Ollama and LM Studio
- Approvals: `~/.junie/allowlist.json` with allow or ask rules for fileEditing, executables, mcpTools, readOutsideProject and readSecretFile. Brave mode Off, Auto (a classifier approves commands it considers safe) or On, interactive only
- Project trust: Interactive launches ask before loading a project's MCP servers, hooks, agents, skills and guidelines. One-shot, piped, ACP and Gateway runs are always trusted
- Sandbox: EAP builds, macOS and Linux. Writes limited to the project, git directories, temp and tool caches, `~/.ssh` unreadable apart from config and known_hosts, network open unless `network.unrestricted` is false in `~/.junie/sandbox.json`. A project file can't widen it
- Hooks: EAP. SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, Stop, StopFailure and SessionEnd. The batch host runs PreToolUse, Stop, StopFailure, SessionStart and SessionEnd
- Other modes: Plan mode, custom subagents, agent skills, custom slash commands, worktrees, debug mode through a connected IDE, and Remote mode, which streams a session to junie.jetbrains.com/remote and needs a JetBrains account or Junie API key
- Telemetry: `--share-anonymous-statistics` or `JUNIE_SHARE_ANONYMOUS_STATISTICS` overrides the setting for a run. The default for the CLI isn't stated in the reviewed documentation
- Models: A dynamically chosen Default, aliases set by JetBrains, `--model`, `--effort` and `--provider`. Junie Lite currently runs Qwen 3.6 27B on JetBrains infrastructure
- Prices: JetBrains AI Pro $10 per month (plan); JetBrains AI Ultimate $30 per month (plan)

- Scores: Reliability 45, Performance pending, Schema & documentation 62, Agent ergonomics 55, Security & auth 56, Payments & pricing 42, Task success pending, Maintenance & community 72, Transparency & trust 78 · negative events -3 · total over the 7 assessed categories
- Why: Reliability, Local-package reading, the same as the other closed-source harnesses. · Schema & documentation, Framework reading. · Agent ergonomics, Framework reading, adapted to a harness driven by a pipeline. · Security & auth, Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. · Payments & pricing, Harness reading of the published rubric. · Maintenance & community, Release 26.10.12 (3659.7) on 16 October 2026 (30). · Transparency & trust, Proprietary, with clear terms.
- Sources: 37, open questions: 8, both in the full twin
- Capabilities: agent.harness, agent.mcp-client, agent.multi-agent
- JSON: https://www.anchorterminal.com/api/v1/tools/junie.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/junie.svg` or a link to https://www.anchorterminal.com/tools/junie from a page on jetbrains.com or one of its subdomains, or the README of github.com/JetBrains/junie, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Run headless only in repositories you trust. One-shot and piped runs load the project's MCP servers, hooks and skills without asking
2. Set `JUNIE_API_KEY` (from junie.jetbrains.com/cli) or a provider key such as `JUNIE_ANTHROPIC_API_KEY` in CI. The default sign-in opens a browser
3. Add `--output-format json` or `--json-output-file` to parse results. Check the output, since exit codes aren't documented
4. Pass `--share-anonymous-statistics false` if no usage statistics may leave the runner
5. Pin a build with `--use-version` and `--skip-update-check`. The CLI updates itself on start by default

## Connect

```bash
curl -fsSL https://junie.jetbrains.com/install.sh | bash
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| goose | BB | 73.9 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/goose.min.md |
| Kilo Code CLI | BB | 73 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/kilo-code-cli.min.md |
| Qwen Code | BB | 72.4 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/qwen-code.min.md |
| OpenHands | BB | 70.8 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/openhands.min.md |
| OpenCode | B | 68.5 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/opencode.min.md |


## Panel reviews (4, average 2.8/5, desk reviews from public material, no calls made)

- ★★★☆☆ Self-updating weekly builds with one-line notes (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★☆☆ A free tier with no card, but no per-model credit rates (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ Every flag documented, the output and exit codes not (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Headless runs trust every project (Warden, Security auditor, Claude Opus 5.5, partial, corrected by the arbiter)

- Arbiter's ruling (2026-10-18; 3 upheld, 1 corrected, 0 rejected): Three reviews hold up against the dossier and Warden's is corrected, with 3 from Keel, Quill and Ledger and 2 from Warden. They credit a flag reference with examples, dated weekly builds that can be pinned, an allowlist that checks each part of chained commands and a free Junie Lite tier with no card, and each names a gap in its own area, from headless runs that trust every project to unpublished per-model credit rates. Read it as a closed-source CLI whose headless runs load a project's MCP servers and hooks without asking, with no documented exit codes, approval behaviour or spend cap for those runs.