Official build Installer
With Alelyon’s closed plug-ins: receipt replay on the lab’s engine, voice, and later Sinai’s own mind.
An AI code editor with an agent, local and cloud LLMs, a research assistant and friends. Works offline. Zero telemetry.

Chat, edit and run in one IDE. Every change waits for your review.



Run open models on your own GPU, bring your own key, or use the plans you already pay for.
Collect a subject’s papers from OpenAlex and arXiv, follow the citations, see what is missing.
Talk to Sinai through any model you choose while its own mind is in training.


Add friends, see who is online and chat, in the app and on the web.
Friends: who is online, requests, and one-to-one chat. This panel needs JavaScript.
Keep or undo the agent’s edits by part, by file or all at once.
Commands, tools, posts and purchases ask you first.
Ctrl+Alt+End stops every running turn, from any program.
Local models, your files, the IDE and saved research.
No usage analytics, no tracking.
API keys live in Windows Credential Manager.
“Stay signed in” is sealed to your Windows user.
A model never types in your terminal or presses Save.
The assistant model at the centre of the lab’s work. Its face ships today; its mind is not in any build yet.
Large models in consumer GPU memory. Quality is not yet measured, so no claim is made.
The app shell, Lattice, Sinai’s face and the simulator, as public mirrors, piece by piece.

With Alelyon’s closed plug-ins: receipt replay on the lab’s engine, voice, and later Sinai’s own mind.
Only what is public. It checks a receipt’s signature, data and records, and never marks one verified without the replay engine.
An AI lab, and the Windows app it builds for working with AI: Lattice (an AI code editor with an agent), local and cloud models, a research assistant, the assistant Sinai, and friends.
Nothing on this site asks for payment: the app and an Alelyon account cost nothing today, and no price has been set for later releases. This page will say so before one applies.
Models you bring can cost money through their providers, or through your Claude or ChatGPT plan when you use Claude Code or Codex.
No account is needed. Choose “Use offline” at sign-in and everything on your computer works: your models, files, the IDE and saved research. An account adds friends and Alelyon’s hosted preview; sign in with GitHub, Google, Hugging Face or LinkedIn.
Only what you send to a service you chose: a prompt to a hosted model, a search to OpenAlex or arXiv, a message to a friend, a sign-in to Alelyon. On its own, the app only asks Alelyon’s sign-in service whether it is up, with no account details. There is no analytics or telemetry, and with a local model through llama.cpp your prompts never leave your computer.