How to Install Lawyer Assistant — Step-by-Step Guide

Step by step

Six steps. That's it.

Download the app

Pick your platform above — Windows .exe, macOS archive, or Linux AppImage — and download the file for your system (or use the buttons at the bottom of this page).

Extract the archive

Windows: right-click the file → Extract All…. macOS: double-click it. Move the extracted folder somewhere permanent, like Documents.

Run the launcher

Windows: double-click launch.bat. macOS / Linux: run launch.sh. A setup page opens in your browser — that's your control center.

Read the launcher guide →

Let it install everything

Click Install. The launcher sets up the Python environment, installs dependencies, downloads the AI models, and installs Ollama — automatically, with progress shown for every step.

What the launcher installs, in detail →

Launch the app

Once installation finishes, click Launch. The desktop app opens — usually in under a minute. From then on you can close the launcher anytime.

Ask your first question

Pick a folder of documents, click Ingest all files, then type a question in plain English. You'll get an answer with inline citations pointing to the exact passages.

See the quickstart guide →

Direct downloads

Works on your computer.

Three downloads, one app — grab the installer for your system, or the universal archive and run the launcher script.

Before downloading, ensure your device has 32 GB RAM and either an 8 GB+ VRAM GPU, an NPU, or AI-capable hardware.

New in v1.1.1: hotfixes for the white-screen crash and for updates not refreshing the installed app, plus the v1.1.0 features — automatic GPU-accelerated (CUDA) setup when an NVIDIA card is detected and fully-offline first-run PDF ingestion. See what’s new

Windows

Setup installer for Windows 10 & 11. If SmartScreen warns, click More info → Run anyway.

Download .exe ↓

macOS

Universal archive (no native build yet) — extract it and double-click launch.sh. If Gatekeeper warns, right-click → Open.

Download .zip ↓

Linux

AppImage — make it executable and run, or install from the tar.gz and use launch.sh.

Download .AppImage ↓ Linux installer (.tar.gz) ↓

The problem

Legal research shouldn't feel like Ctrl+F on a haystack.

Generic chatbots guess. Cloud legal tools hold your documents hostage. Lawyer Assistant sits between them: real retrieval over your files, with citations you can check.

Generic AI chatbot

Lawyer Assistant

✕ Hallucinates answers with no way to check them

✓ Answers cite the exact source passages — tap to verify

✕ Doesn't know what's in your documents until you paste them

✓ Searches your entire workspace: PDFs, scans, contracts, case files

✕ Sends your confidential work to someone else's servers

✓ Runs locally with a local model — or your own API key if you prefer

✕ No memory of your cases, no way to save what matters

✓ Starred messages, working sets, per-project history

✕ Can't tell you if a clause violates your compliance rules

✓ Playbook scan flags risky clauses against your own rules

Capability	Generic chatbot	Lawyer Assistant	Legal SaaS cloud
Runs 100% on your machine	✕	✓	✕
Works fully offline	✕	✓	✕
Answers cite exact source passages	✕	✓	Partial
Your documents stay private	✕	✓	✕
Compliance playbook scan	✕	✓	✕
Custom retrieval pipeline	✕	✓	✕
No per-document subscription fees	—	✓	✕

Confidentiality

Nothing leaves your chambers.

Ingestion, search, and answering all happen on your hardware. In local mode, no question, document, or answer ever touches a third-party server — a deliberate choice for attorney–client privilege.

Choose an API provider and only your question plus retrieved passages are sent to that provider — clearly shown in the app, never silently.

01Embeddings, index, and history stored in your project folder only.

02API keys stored locally; the launcher never displays them after setup.

03Works offline — no cloud, no lock-in.

Verified
Local
Only

Common questions

Install questions, answered.

Do I need to install Python, Node.js, or any technical tools?

No. The launcher does everything for you: it sets up the Python environment, installs all dependencies, downloads the AI models, and installs Ollama automatically. You only need to download the app and run the launcher.

Do I need a GPU or a powerful computer?

Yes for local mode. The app runs its AI models on your own hardware, so you need a machine built for AI inference: a dedicated GPU with at least 8 GB VRAM, an NPU, or a new AI-ready PC (Copilot+ PC or recent Apple Silicon), plus at least 32 GB of RAM. If your computer doesn't qualify, use cloud mode with your own API key — only your question and the retrieved passages go to the provider you choose.

Which new PCs are built for AI inference?

AI-ready PCs are purpose-built for running models locally: Microsoft Copilot+ PCs with a built-in NPU, Apple Silicon Macs (M-series), and NVIDIA RTX-powered Windows PCs. For local AI usage, pick one with a dedicated GPU with at least 8 GB VRAM or an NPU, plus at least 32 GB of RAM — it runs search, embeddings, and answers entirely on your machine, private and offline.

Do I need an internet connection to use it?

You need internet for the first install to download the models. After that, the app works fully offline with a local model.

Does installation cost anything?

No. Lawyer Assistant is free and open source under the MIT license. There are no subscriptions and no hidden fees.

What if the launcher fails partway through?

Each setup step can be retried on its own. Just click Retry on the failed step — you never need to restart the whole installation.

Up and running in under five minutes.