Quick Start
Go from zero to your first AI-assisted coding session in under 2 minutes.
Install the CLI
If you haven't already, install OpenAnalyst CLI for your platform.
npm install -g @openanalystinc/openanalyst-cli@latest
See the Installation page for Homebrew, winget, and direct binary downloads.
Sign in to Your Account
Create a free account at https://10x.in if you don't have one, then sign in via email + OTP:
openanalyst account login
Enter your email, then paste the 6-digit code we send you. Signing in unlocks credits-based access to the full OpenAnalyst-routed catalog on one balance — Beta, Max, GPT-5, Claude Opus, Gemini Pro, and Grok — with free credits granted on signup.
openanalyst account status to see the signed-in email and current credit balance.
Alternative: bring your own provider key
If you prefer to use your own provider keys (Anthropic, OpenAI, Gemini, xAI, OpenRouter, Bedrock, Stability), run the interactive provider picker:
openanalyst login
Or set keys directly in your environment:
# Edit ~/.openanalyst/.env
OPENANALYST_API_KEY=sk-oa-...
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
GEMINI_API_KEY=AIza...
Launch the TUI
Start OpenAnalyst in its default full-screen terminal UI:
openanalyst
You'll see the startup banner, account status, and an empty chat ready for input.
--notui to skip Ink entirely and run the backend CLI directly: openanalyst --notui
Ask a Question
Type a natural language prompt and press Enter:
explain the architecture of this codebase
The agent reads your project files, understands the structure, and streams a response with syntax-highlighted code blocks.
Use Slash Commands
Type / to see autocomplete suggestions. Try these:
# See session status and token usage
/status
# Switch to a different model mid-conversation
/model gpt-4o
# Generate a git commit message from staged changes
/commit
# Run a deep bug analysis
/bughunter
Try One-Shot Mode
For quick tasks, pass the prompt directly:
# Backend-only one-shot prompt
openanalyst --notui -p "summarize the README"
# Prompt subcommand
openanalyst prompt "review this code for bugs"
# Hosted session API server
openanalyst --serve 3080
Usage Modes
| Mode | Command | Description |
|---|---|---|
| TUI (default) | openanalyst |
Full-screen terminal UI with sidebar, chat panel, status bar |
| Backend CLI | openanalyst --notui |
Skip the TUI and run the backend runtime directly |
| One-shot | openanalyst prompt "prompt" |
Single prompt → response → exit |
| Hosted API | openanalyst --serve 3080 |
Expose persistent agent sessions over HTTP and SSE |
Common Flags
| Flag | Description |
|---|---|
--model <name> | Use a specific model (e.g., opus, gpt-4o, gemini-3-pro) |
--notui | Disable the TUI and run the backend CLI directly |
--serve [port] | Expose hosted HTTP session endpoints for remote users |
--permission-mode <mode> | Set permission level: read-only, workspace-write, danger-full-access |
--resume | Resume the last conversation session |
--version | Print version and exit |