ORA

The AI CLI for Agents & Humans.

One command to query, compare, and reason across OpenAI, Claude, and any models. Built for your terminal and browser.

> ora compare -q "analyze TSLA risks" --model gpt-4o,claude-opus-4-5

[GPT-4o]   Revenue up 8%, margins compressed...
[Claude]  Regulatory risk in China, FSD liability...

 Best answer selected  conf: 0.94
$0.0120 | 3.2s | 2 models

Use it your way

Same engine. Choose your interface.

Terminal

Run queries, chain workflows, pipe data, automate with scripts. Full power in your terminal.

$ ora -q "analyze this"

Web Chat

Visual interface with themes, history, docs panel. Same engine, browser-based.

$ ora chat

See it in action

Click any command to see what ora does.

Launch a web-based chat interface with themes, history, and docs.

ora v0.4
$ ora chat
ora chat running at http://localhost:3737  ┌─ Chat ──────────────────────────────┐  │  [Chat] [CLI] [Dashboard]  📖 💡 ⧉  │  │                                     │  │  You: explain microservices          │  │                                     │  │  ora: Microservices architecture    │  │  breaks an application into small,  │  │  independent services...            │  │  ✓ 93% | $0.004 | gpt-4o | 2 iter  │  │                                     │  │  [Strategy▾] [Model▾] [Budget▾]     │  │  $ ora -q "..." --model gpt-4o     │  └─────────────────────────────────────┘

Built for the terminal. Built for agents.

Everything you need to get better answers from AI — from a single binary that works everywhere.

🌐

Multi-Provider

Claude, GPT, Gemini, Grok, Ollama, or any OpenAI-compatible API. One interface for every model.

$ ora --model claude-opus-4-5
$ ora --model gpt-4o
🔄

Autonomous Reasoning Loops

Not one answer — the best answer. ora iterates: answer, critique, refine, repeat. Three strategies: critique, debate, research.

$ ora -q "best DB for time series?" --strategy research
   v4 confidence: 0.91 — stopped
💰

Budget & Cost Control

Set a budget per run. ora tracks every token, warns at 80%, and stops at your limit. Never overspend.

$ ora -q "analyze codebase" --budget 0.50
   $0.41 / $0.50 (82%) — warning
✏️

Prompt Crafting

Describe what you want in English. ora builds the optimal prompt, recommends flags, and generates ready-to-run commands.

$ ora --craft "weekly EV market report"
   Crafted prompt + 3 command variants
🧠

Memory & Continuations

Chain runs together. Feed previous answers as context. Pick up where you left off with --continue.

$ ora -q "go deeper on point 3" --continue last
   Inherited context from ora-7
📊

Terminal Dashboard

Live TUI showing all processes and cost breakdown. No browser needed — everything in your terminal.

$ ora dashboard
  Processes | Cost | History
🤖

Agent-Ready JSON Output

Stable JSON schema for pipelines, scripts, and AI agents. Pipe into jq, feed into other tools, automate everything.

$ ora -q "analyze" --output json --quiet | jq .answer
💬

Web Chat Interface

Run ora chat to launch a browser-based chat UI. Same engine, visual interface. Light & dark themes.

$ ora chat
  Running at http://localhost:3737

For every workflow

Whether you are exploring an idea or automating a pipeline — ora meets you where you are.

Ask questions in plain English

No prompt engineering needed. Just ask your question and ora handles the rest. Use --guide for interactive workflows.

# Simple question — ora iterates automatically
$ ora -q "explain what a reverse proxy does"
# Interactive guide builds the command for you
$ ora --guide "how do database indexes work?"
# Craft an optimized prompt from vague intent
$ ora --craft "I need to understand Kubernetes"

Works everywhere you work

ora is a CLI binary — it plugs into anything that runs a command.

💬

Web Chat

Browser-based chat interface with themes, history, and built-in docs. Run ora chat to launch.

>_

Terminal

Bash, Zsh, Fish, PowerShell. Any terminal on any OS. ora is a single binary — just run it.

$

Shell Scripts

Pipe data in, get JSON out. Use ora in bash scripts, Makefiles, and CI/CD pipelines.

Claude

Anthropic Claude

Claude Opus, Sonnet, Haiku — all supported out of the box. Auto-detected from model name.

GPT

OpenAI

GPT-4o, o3, and any OpenAI model. Same interface, same flags, same output format.

OC

OpenClaw

Connect ora to OpenClaw workflows. Use ora as the reasoning engine behind your agents.

🦜

Ollama

Run local models with zero API keys. ora auto-detects Ollama on localhost. Fully offline.

G

Google Gemini

Gemini Pro, Flash — native integration. One flag to switch: --model gemini-2.0-pro

🔗

Any OpenAI-Compatible API

Groq, Together, Fireworks, self-hosted — anything with an OpenAI-compatible endpoint works with --endpoint.

Up and running in 20 seconds

From download to first answer — nothing else to configure.

1

Install

One command. Detects your platform automatically.

curl -sSL https://oracommand.com/install.sh | sh

Works on macOS and Linux. Detects your platform automatically.
View all releases on GitHub

2

Ask anything

ora drafts, critiques, refines — and returns the best answer within your budget.

$ ora -q "explain quantum tunneling"
   Answer v3 (confidence: 0.92)
3

Open the web chat

Visual interface with themes, history, and built-in docs.

$ ora chat
  Running at http://localhost:3737
Download ora

Packages

Download ora for free with core reasoning features. Unlock the full power with Pro.

Free

$0

forever

Founder Price

Pro

$5/mo

locked in forever

FeatureFreePro
Unlimited queries
Unlimited models & providers
Reasoning loops — critique, debate, research
Custom endpoints — any OpenAI-compatible API
Cost tracking & per-run budgets
JSON output for agents & pipelines
Context injection — files & URLs
Self-update
Web chat interface (ora chat)
History, search, export
Unlimited memory & continuations
Prompt crafting & interactive guide
Terminal dashboard (TUI)
Multi-model compare (ora compare)

About Us

Built by an ex-Bloomberg team

We spent years building real-time data systems at Bloomberg — where every millisecond matters and every answer has to be right. We saw how teams use AI today: paste a question into a chat window, get a mediocre first draft, manually rephrase, try again. Repeat until you give up or get lucky.

That is not how quality works. At Bloomberg, you do not ship the first draft. You iterate, critique, validate, and refine until the answer is actually correct. We built ora to bring that same discipline to AI.

The problem we are solving

One-shot answers are not good enough

Chat UIs give you one response. Quality depends entirely on how well you prompt. Most people accept a mediocre first draft.

Manual iteration is slow and expensive

Rephrasing, re-prompting, copy-pasting context back in — you are doing the work the machine should be doing.

No cost visibility or control

API calls add up. Most tools have no budget controls — you find out what you spent when the invoice arrives.

Locked into one provider

Every AI tool picks a model for you. Switch providers? Learn a new tool. ora works with any model from any provider.

ora is the answer

One static binary that runs an autonomous reasoning loop against any model. You define the intent, the budget, and the iteration depth. ora does the rest — asks, critiques, refines, and returns the best possible answer within your constraints.