Meet Lexora
Lexora is a personal AI agent that evolves through hands-on work on your desktop. Beyond coding, it helps you organize research, refine creative projects, and plan everyday activities. Tell it what you want to accomplish, and it keeps working toward that goal, making words the starting point for work, creativity, and everyday life.
This guide is for people using Lexora for the first time. You do not need to know how to code. Bring a small goal and start with your first task.
Choose where to begin
If you have not connected a model, follow the getting-started sequence first. If you already use Lexora, jump to the operation you need.
| What you want to do | Start here |
|---|---|
| Install Lexora and finish a small task | Your first task |
| Connect a provider or local model service | Connect a model |
| Add instructions, quote content, or try a branch | Tasks and conversations |
| Organize local materials and split the workspace | Files and spaces |
| Bring in other companions and recruit NPCs | Companions and collaboration |
| Install a plugin or make your own tool | Using and creating plugins |
| Add methods, external tools, or recurring work | Skills and MCP · Automations |
| Choose permissions, back up data, or resolve a problem | Execution permissions · Data and backups · Troubleshooting |
Three concepts to know
A task is where work toward one goal continues. It can contain multiple conversation turns, tool operations, references, and files. For a weekend route, you might choose places today and return tomorrow to add transport details in the same task.
A space groups related tasks and connects them to working directories. A travel space might contain separate tasks for a route, packing list, and travel journal. The directory stores files; the space organizes the work around them.
A companion is an AI role that handles work. Lexora is the default companion. You can configure other companions with names, instructions, models, and capabilities. A model is the service a companion uses; changing it does not require starting your workspace over.
How work continues
Describe the goal, then provide the materials. Lexora responds or uses tools to read files, edit content, and perform operations. You can inspect progress, add requirements, quote a passage for revision, or stop execution.
Conversations and execution records remain in the task. Return to build on that progress. Save a useful method as a Skill, or turn a recurring need into a plugin.
Leave a useful handoff
Before finishing for the day, ask: “Summarize what is done, where the results are saved, and what remains.” It makes returning to the task easier.
What you need
Install Lexora and connect at least one usable model. No Lexora account is required. Model credits and charges come from your chosen provider.
Tasks, companions, and settings are stored locally. When you use an online model, the relevant conversation and file context goes to your configured service. See data and backups for details.
Curious about what runs underneath?
Vue and Electron provide the desktop workspace, while an independent TypeScript runtime hosts the local agent. Pi provides the agent loop, and Rust handles native capabilities. Lexora organizes tasks, context, permissions, and outputs. Explore the source on GitHub for implementation details.
Ready? Complete your first task.