> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mira-app.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> MIRA is a multi-step intelligent reasoning agent for professionals who need answers that are verifiably correct — not just plausible.

<div
  style={{
display: 'flex',
gap: '8px',
marginBottom: '24px',
flexWrap: 'wrap',
alignItems: 'center',
}}
>
  <span
    style={{
  display: 'inline-flex',
  alignItems: 'center',
  gap: '6px',
  padding: '4px 12px',
  borderRadius: '9999px',
  background: 'rgba(12, 144, 245, 0.1)',
  border: '1px solid rgba(12, 144, 245, 0.25)',
  color: '#0059aa',
  fontSize: '11px',
  fontWeight: 700,
  letterSpacing: '0.05em',
  fontFamily: 'monospace',
}}
  >
    v0.1.0-beta.1
  </span>

  <span
    style={{
  display: 'inline-flex',
  alignItems: 'center',
  padding: '4px 12px',
  borderRadius: '9999px',
  background: 'rgba(251, 191, 36, 0.1)',
  border: '1px solid rgba(251, 191, 36, 0.3)',
  color: '#d97706',
  fontSize: '11px',
  fontWeight: 600,
}}
  >
    Releasing soon
  </span>
</div>

<img className="block dark:hidden" src="https://mintcdn.com/opensource-dea4990c/2lp4A8JqqqejYZcN/_assets/hero-light.svg?fit=max&auto=format&n=2lp4A8JqqqejYZcN&q=85&s=1f803c43e9132ed3ee0fcb17d52e0ac5" alt="MIRA — Multi-Step Intelligent Reasoning Agent" style={{ width: '100%', borderRadius: '14px' }} width="1200" height="310" data-path="_assets/hero-light.svg" />

<img className="hidden dark:block" src="https://mintcdn.com/opensource-dea4990c/2lp4A8JqqqejYZcN/_assets/hero-dark.svg?fit=max&auto=format&n=2lp4A8JqqqejYZcN&q=85&s=df12ce1da83bfa44fdcb9d568377f37f" alt="MIRA — Multi-Step Intelligent Reasoning Agent" style={{ width: '100%', borderRadius: '14px' }} width="1200" height="310" data-path="_assets/hero-dark.svg" />

## What is MIRA?

MIRA (**M**ulti-Step **I**ntelligent **R**easoning **A**gent) is an open-source, cross-platform desktop application that gives professionals a reasoning tool with two modes:

* **Native Agent Engine (NAE)** — orchestrates sub-tasks using direct LLM API calls, manages token budgets, compacts long context automatically, and maintains episodic memory across a session
* **RLM Engine** — writes Python code, executes it in a local Python REPL, reads the actual output, and iterates until the answer is verifiably correct

Everything runs on your machine. No telemetry. No cloud storage. No exceptions.

## Who is MIRA for?

<CardGroup cols={2}>
  <Card title="Data Analysts & Scientists" icon="chart-bar">
    Ask questions about your data in plain language. MIRA computes the answer from your actual data
    — every number earned, every result auditable.
  </Card>

  <Card title="Researchers & Academics" icon="flask-conical">
    Upload papers, datasets, and reports. Run multi-step research pipelines that synthesise evidence
    and cite sources — not statistical plausibility.
  </Card>

  <Card title="Legal & Compliance" icon="scale">
    Cross-reference contracts, flag conflicting clauses, and surface jurisdiction risks. RLM runs
    the analysis in code so every finding is traceable, not inferred.
  </Card>

  <Card title="Financial & Business Analysts" icon="trending-up">
    Model, forecast, and cross-reference data with an engine that verifies its own calculations
    before reporting them — not an engine that guesses.
  </Card>

  <Card title="Security Professionals" icon="shield">
    Threat modelling, secure review, and CVE analysis with an engine that doesn't skip steps or
    paper over uncertainty.
  </Card>

  <Card title="Anyone Handling Sensitive Data" icon="lock">
    Everything runs on your machine. Documents, credentials, and conversations never leave — by
    design, not by policy.
  </Card>
</CardGroup>

<Warning>
  MIRA is **not** a general-purpose chatbot. It is a reasoning tool for professionals who need to be
  right.
</Warning>

## Key capabilities

| Capability                | Description                                                                           |
| ------------------------- | ------------------------------------------------------------------------------------- |
| **Two reasoning engines** | Switch between NAE (direct LLM, long-context) and RLM (code-executing) in Settings    |
| **Document intelligence** | Upload PDF, DOCX, CSV, MD, TXT, and code files — up to 50 MB each                     |
| **Skills**                | Saved instruction sets that give the AI a specialised reasoning persona               |
| **Workflows**             | Deterministic multi-step pipelines with per-step prompt templates and routing rules   |
| **MCP tools**             | Connect any Model Context Protocol server — web search, databases, custom APIs        |
| **Eval framework**        | Automatically evaluate every response with LLM judges, rules, similarity, and metrics |
| **REPL Console**          | Full real-time transparency into every RLM Engine reasoning step                      |
| **Zero telemetry**        | No analytics, no crash reports, no cloud sync — ever                                  |

## Open source

MIRA is MIT licensed. The full source is at [github.com/satyendra2013/mira-app](https://github.com/satyendra2013/mira-app).

<CardGroup cols={3}>
  <Card title="Quick Start" icon="rocket" href="/get-started/quick-start">
    Up and running in under 5 minutes
  </Card>

  <Card title="Contributing" icon="heart" href="/community/contributing">
    Help build MIRA
  </Card>

  <Card title="Developer Guide" icon="code" href="/developer-guide/architecture">
    Architecture, IPC, build from source
  </Card>
</CardGroup>