llms.txt
# Lloyal
> Lloyal (`lloyal-ai`) is a platform for building and shipping self-contained, offline-first AI apps in TypeScript.
Start a project with `npx lloyal-ai new` (Node 24+). The model runs in-process with your code, so there's no API key and no HTTP boundary on the path that thinks. The CLI is MIT-licensed; apps you generate with it are yours to license as you choose.
## Getting started
- [GitHub](https://github.com/lloyal-ai/lloyal-ai): source, commands, and both templates; start here
- [npm](https://www.npmjs.com/package/lloyal-ai): the `lloyal-ai` package
- `npx lloyal-ai new my-app` scaffolds the default `basic` template, a small wiki app
- `npx lloyal-ai new my-app --template research` scaffolds the research template: a multi-agent harness that reads documents and answers with page-level citations, model running locally
- `npx lloyal-ai@latest new --help` lists the current commands and templates
## Docs
- [Docs index](https://docs.lloyal.ai/llms.txt): full docs site map for AI assistants
- [Build with Lloyal](https://docs.lloyal.ai/): docs home
- [Build your first harness](https://docs.lloyal.ai/build-your-first-harness): use lloyal-ai to create an application, begin a Session, inspect its procedure, change its topology, and continue from accepted state
- [Thinking in Lloyal](https://docs.lloyal.ai/thinking-in-lloyal): how owned lifetimes, live inference state, Agents, Tools, orchestration, finality, and continuity fit together
- [Continuous Context](https://docs.lloyal.ai/continuous-context): why live inference state changes the application boundary
- [Abilities](https://docs.lloyal.ai/abilities): a packaged capability — manifest, source, tools, skill — that any harness can enable; how it's built, distributed, signed, and why it runs in-process
- [Where a harness runs](https://docs.lloyal.ai/where-a-harness-runs): how one harness contract spans application surfaces, local and shared-residency execution, process boundaries, transports, hardware, and operators
- [Lookup](https://docs.lloyal.ai/lookup): signatures, enumerations, and floors — the facts you look up mid-task
## Site
- [Home](https://lloyal.ai/): what Lloyal is and why it exists
- [Blog](https://lloyal.ai/blog/): engineering and product posts
## Optional
- [YouTube](https://www.youtube.com/@lloyallabs): Lloyal Labs channel
