jbai-cli

Use AI coding tools with your JetBrains AI subscription — no separate API keys needed.

One token, all tools: Claude Code, Codex, Aider, Gemini CLI, OpenCode.

Install

npm install -g jbai-cli

Setup (2 minutes)

Step 1: Get your token

1. Go to platform.jetbrains.ai (or staging)
2. Click your Profile icon (top right)
3. Click "Copy Developer Token"

Step 2: Save your token

jbai token set
# Paste your token when prompted

Step 3: Verify it works

jbai test

Expected output:

Testing JetBrains AI Platform (staging)

1. OpenAI Proxy (Chat): ✅ Working
2. OpenAI Proxy (Codex /responses): ✅ Working
3. Anthropic Proxy (Claude): ✅ Working
4. Google Proxy (Gemini): ✅ Working

Usage

Claude Code

jbai-claude

Codex CLI

# Interactive mode
jbai-codex

# One-shot task
jbai-codex exec "explain this codebase"

Aider

jbai-aider

# Use Gemini models with Aider
jbai-aider --model gemini/gemini-2.5-pro

OpenCode

jbai-opencode

Handoff to Orca Lab (local)

# Continue a task in Orca Lab via local facade
jbai handoff --task "continue this work in orca-lab"

In-session handoff (interactive tools)

While running jbai-codex, jbai-claude, jbai-gemini, or jbai-opencode:

• Press Ctrl+] to trigger a handoff to Orca Lab.
• The last prompt you typed is used as the task.

Optional environment variables:

• ORCA_LAB_URL (default: http://localhost:3000)
• FACADE_JWT_TOKEN (local facade auth)
• GITHUB_TOKEN / GH_TOKEN (private repos)
• JBAI_HANDOFF_TASK (fallback task if no prompt captured)
• JBAI_HANDOFF_REPO (override repo URL)
• JBAI_HANDOFF_REF (override git ref)
• JBAI_HANDOFF_BRANCH (override working branch)
• JBAI_HANDOFF_ENV (STAGING | PREPROD | PRODUCTION)
• JBAI_HANDOFF_MODEL (Claude model for Orca Lab agent)
• JBAI_HANDOFF_OPEN (set to false to avoid opening a browser)

Super Mode (Skip Confirmations)

Add --super (or --yolo or -s) to any command to enable maximum permissions:

# Claude Code - skips all permission prompts
jbai-claude --super

# Codex - full auto mode
jbai-codex --super exec "refactor this code"

# Aider - auto-confirm all changes
jbai-aider --super

| Tool | Super Mode Flag | |------|-----------------| | Claude Code | --dangerously-skip-permissions | | Codex | --full-auto | | Aider | --yes | | Gemini CLI | --yolo | | OpenCode | N/A (run mode is already non-interactive) |

⚠️ Use with caution - super mode allows the AI to make changes without confirmation.

Using Different Models

Each tool has a sensible default, but you can specify any available model:

# Claude with Opus
jbai-claude --model claude-opus-4-1-20250805

# Codex with GPT-5
jbai-codex --model gpt-5.2-codex

# Aider with Gemini Pro
jbai-aider --model gemini/gemini-2.5-pro

Available Models

Claude (Anthropic) | Model | Notes | |-------|-------| | claude-sonnet-4-5-20250929 | Default, recommended | | claude-opus-4-1-20250805 | Most capable | | claude-sonnet-4-20250514 | | | claude-3-7-sonnet-20250219 | | | claude-3-5-haiku-20241022 | Fast |

GPT (OpenAI) | Model | Notes | |-------|-------| | gpt-4o-2024-11-20 | Default | | gpt-5-2025-08-07 | Latest | | gpt-5.1-2025-11-13 | | | gpt-5.2-2025-12-11 | | | gpt-5-mini-2025-08-07 | Fast | | o3-2025-04-16 | Reasoning | | o3-mini-2025-01-31 | |

Codex (OpenAI Responses) - Use with Codex CLI: jbai-codex --model <model> | Model | Notes | |-------|-------| | gpt-5.2-codex | Default, coding-optimized | | gpt-5.1-codex | | | gpt-5.1-codex-mini | Faster | | gpt-5.1-codex-max | |

Gemini (Google) - Use with Aider: jbai-aider --model gemini/<model> | Model | Notes | |-------|-------| | gemini-2.5-flash | Fast | | gemini-2.5-pro | More capable | | gemini-3-pro-preview | Preview | | gemini-3-flash-preview | Preview |

Commands Reference

| Command | Description | |---------|-------------| | jbai help | Show help | | jbai token | Show token status | | jbai token set | Set/update token | | jbai test | Test API connections | | jbai models | List all models | | jbai handoff | Continue a task in Orca Lab | | jbai install | Install all AI tools | | jbai install claude | Install specific tool | | jbai doctor | Check tool installation status | | jbai env staging | Use staging environment | | jbai env production | Use production environment |

Installing AI Tools

jbai-cli can install the underlying tools for you:

# Install all tools at once
jbai install

# Install specific tool
jbai install claude
jbai install codex
jbai install aider

# Check what's installed
jbai doctor

Manual Installation

| Tool | Install Command | |------|-----------------| | Claude Code | npm i -g @anthropic-ai/claude-code | | Codex | npm i -g @openai/codex | | Aider | pipx install aider-chat | | OpenCode | go install github.com/opencode-ai/opencode@latest |

Token Management

# Check token status (shows expiry date)
jbai token

# Update expired token
jbai token set

Tokens are stored securely at ~/.jbai/token

Switching Environments

# Staging (default) - for testing
jbai env staging

# Production - for real work
jbai env production

Note: Staging and production use different tokens. Get the right one from the corresponding platform URL.

How It Works

jbai-cli uses JetBrains AI Platform's Guarded Proxy, which provides API-compatible endpoints:

• OpenAI API → api.jetbrains.ai/user/v5/llm/openai/v1
• Anthropic API → api.jetbrains.ai/user/v5/llm/anthropic/v1
• Google Vertex → api.jetbrains.ai/user/v5/llm/google/v1/vertex

Your JetBrains AI token authenticates all requests via the Grazie-Authenticate-JWT header.

Troubleshooting

"Token expired"

jbai token set
# Get fresh token from platform.jetbrains.ai

"Claude Code not found"

npm install -g @anthropic-ai/claude-code

"Connection failed"

# Test which endpoints work
jbai test

# Check your environment
jbai token

Wrong environment

# Staging token won't work with production
jbai env staging   # if using staging token
jbai env production  # if using production token

License

MIT