v0.1.0-beta.1Releasing soon
What is MIRA?
MIRA (Multi-Step Intelligent Reasoning Agent) 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
Who is MIRA for?
Data Analysts & Scientists
Ask questions about your data in plain language. MIRA computes the answer from your actual data
— every number earned, every result auditable.
Researchers & Academics
Upload papers, datasets, and reports. Run multi-step research pipelines that synthesise evidence
and cite sources — not statistical plausibility.
Legal & Compliance
Cross-reference contracts, flag conflicting clauses, and surface jurisdiction risks. RLM runs
the analysis in code so every finding is traceable, not inferred.
Financial & Business Analysts
Model, forecast, and cross-reference data with an engine that verifies its own calculations
before reporting them — not an engine that guesses.
Security Professionals
Threat modelling, secure review, and CVE analysis with an engine that doesn’t skip steps or
paper over uncertainty.
Anyone Handling Sensitive Data
Everything runs on your machine. Documents, credentials, and conversations never leave — by
design, not by policy.
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.Quick Start
Up and running in under 5 minutes
Contributing
Help build MIRA
Developer Guide
Architecture, IPC, build from source