Scaffolds OpenUI agent apps, mints Cloud API keys and turns component libraries into model prompts.
Lloyal AI
lloyalty · Template
Lloyal AI scaffolds a TypeScript application in which agents run as processes inside your app, each owning a fork of the model's working memory. The embedded runtime provisions models, composes specialist models, enforces policy during inference and includes DevTools for inspecting live inference. The starting app has agents that research the web, process local files and understand documents. About 4.5 GB of models download on first launch, then inference works offline with no API key. It recommends 16 GB of memory.
Written by ooruby from the README of lloyal-ai 1.15.2.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Your agents think on a model you own inside the app, so the path that does the thinking needs no API key.
What you could do with it
- Start a TypeScript app whose built-in agents research the web, process local files and understand documents.
- Pin a catalogue model, or point the app at a local GGUF file, to choose the model your agents run on.
- Package the finished app as a macOS DMG, or add a desktop or web target to the project.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (templates/research/bin/ensure-electron.js:18)
- synchronous shell execution (templates/research/bin/ensure-electron.js:45)
- node child_process (templates/basic/bin/ensure-electron.js:18)
- synchronous shell execution (templates/basic/bin/ensure-electron.js:45)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Corrected after a reading by hand on 2026-10-10
- No shipped credentials: the automated note “The scan matched 1 credential-shaped string in the published files. Location withheld pending disclosure to the maker.” was withdrawn. A test value in a template's test that checks a secret never reaches its output.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Scaffold a private, multi-agent AI application in TypeScript that runs on a model you own — resident in the process, no API key on the path that thinks.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 1.15.2, the file with digest sha512-JirJYOXkLRN1BF+pKLkI2mK0CiYINaGrgWVKEc9wLCrLQ9lUErHZKsNML0RZstRHHNBKOwLnExpQe4FVYZEhxw==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y lloyal-ai@1.15.2Pinned to 1.15.2, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- lloyal-ai
- Version read
- 1.15.2
- Resolved
- 2026-10-10
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/lloyal-ai/lloyal-ai
- Commit
- 1edc48d38d72
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/lloyal-ai)About this listing
- Kind
- Template
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
Similar templates
All templatesCreates a new Mastra app with one command and helps you set up example agents and a model provider.
Scaffolds a new Tangle agent application with either a tool loop or a complete chat interface.
Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.