Roo Code Logo

YourAI-PoweredLegal Team — Inside Your Editor.

Supercharge your editor with AI that understands your documents, streamlines your work, and helps you research, write and edit with ease.

Autonomous legal agents that build with you.

Multi‑agent system with human‑in‑the‑loop controls, rich tools, and project‑wide context.

Orchestrator + Domain Experts

Plan multi-step work and delegate to Corporate, Employment, IP, Contract, Privacy, and Litigation modes. Agents hand off, request role switches, and reconcile outputs to one coherent result.

Autonomous with Human‑in‑the‑Loop

Agents execute plans end-to-end, ask targeted follow-ups when facts are missing, and pause at approval checkpoints. You can adjust scope, approve actions, and resume — always under your control.

Prompt Enhancement

No more manual prompt engineering. Click the wand and Lawkitt enhances your prompt.

Project Organization

Forget folder chaos and ad-hoc file naming. Lawkitt organizes your files with AI, creating a semantic index that agents can use to navigate and retrieve information.

Project Index & Semantic Search

Index your entire matter for fast retrieval. Agents cite and navigate real files across repos, link answers to sources, and surface prior deals, exhibits, and clauses in context.

Offline and Native

Runs locally as a standalone native application. Work offline with instant responses; your files never leave your machine unless you choose.

MCP Connectors & Knowledge Bases

Connect Model Context Protocol servers to query internal or external knowledge bases and APIs securely, with clear consent boundaries.

Checkpoints & History

Lawkitt creates checkpoints so all edits are safe and reversible.

Web & External Search

When enabled, agents search the internet and return citations. External results are reconciled with your indexed matter for grounded, verifiable outputs.

Empowering lawyers worldwide.

Join thousands of lawyers who are revolutionizing their workflow with AI-powered assistance.

"First drafts that took hours now take minutes. Our team stays in control with review steps and an audit trail for every suggestion."

Amelia Hart

Partner, Commercial Litigation at Am Law 100 Firm

"Lawkitt accelerates contract reviews without sacrificing risk checks. Clause libraries and playbooks keep outputs on our standard."

David Chen

Senior Associate at Global Law Firm

Frequently Asked Questions

Everything you need to know about Lawkitt for legal work—privacy, defensibility, and faster drafting.

Lawkitt is an AI system that lives in your editor and matter workspace. It plans work, delegates to specialist modes, drafts/redlines, researches with citations, and reconciles outputs—always with human-in-the-loop approval.
Orchestrator + specialist modes, project-wide indexing, MCP connectors to your knowledge bases, guarded web search, permission-gated actions, and exportable audit logs. Built for defensibility, not one-off chats.
Yes. Lawkitt runs locally by default. No files leave your machine unless you enable a provider. You control redaction and ignore lists, or run local models for maximum privacy.
Model-agnostic. Use OpenAI, Anthropic Claude or Gemini. For enterprise clients, Lawkitt provides local/on-prem LLMs (air-gapped or VPC).
Yes. Core modes (Research, Drafting, Review) pair with domain counsel (Corporate, Employment, IP, Contract, Privacy, Litigation and more). Connect company playbooks, clause banks, and templates.
Just install Lawkitt and sign in.
Yes. Lawkitt uses efficient context strategies (summarization, targeted retrieval) and links analyses back to source documents for verification. It scales to large document sets.
Designed for compliance workflows: bring‑your‑own model (including on‑prem), permission‑gated actions, and exportable audit logs of prompts, outputs, and approvals.
Yes. Agents can execute multi‑step plans. When information is missing or a decision is needed, they ask a follow‑up question and pause for your input (human‑in‑the‑loop).
The Orchestrator delegates tasks to the best mode and agents can request a role switch when it improves outcomes. You can oversee or approve switches as needed.
Purpose‑built tools to read files, edit files, and run search‑and‑replace; project indexing and semantic code search; connectors to MCP servers for internal/external knowledge; and optional web search.
All popular text formats: Markdown/MDX, plain text, DOCX, XLSX, PDF, CSV/TSV. Agents operate directly on your files with precise diffs.
Yes. Your workspace is indexed for fast retrieval so agents can cite and navigate real files. Private by default—only shared externally when you explicitly allow it.
Yes. Through MCP connectors, agents can query internal wikis, databases, or APIs and merge those results with local project context — always under your control.
When enabled, agents can search the web and bring back sources with citations, combining external findings with your code and documents.
Human-in-the-loop by design: agents ask targeted follow-ups for critical decisions and pause at approval checkpoints. Every action is logged with inputs, sources, outputs, and approvals. Checkpoints let you safely apply edits and roll back. Use History to review past tasks and resume where you left off. All changes are transparent and auditable.

Install Lawkitt

Download the AI-native legal editor for your desktop.

macOS

Download for Mac

Windows

Download for Windows