ADI

Agents that run on your machine and keep what they learn

5 followers

Agents that run on your machine and keep what they learn

5 followers

ADI runs agents on your own machine. You define one — its tools, its secrets, the way it works — and it keeps a memory of its own. Projects, services, dashboards, a task tree and a store you own, in one control panel. macOS, Linux, Windows.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team

Customer.ioAutomate Messaging Everywhere — Startups Get 12 Months Free

Promoted

Maker

📌

I built ADI because I was doing every job in my company myself, and nothing I handed work to kept what I told it. ADI runs agents on your own machine. You define one once — the model, the prompt, the tools it may run, the secrets it may reach — and it keeps a memory of its own. Come back on Friday and it is still holding what you told it on Tuesday. It isn't a wrapper around a coding agent. What installs is an environment: projects, agents, tools, knowledge, facts, goals, a code index, a task tree, triggers, an event bus, supervised services, dashboards, encrypted secrets, a database, an app marketplace and a mesh. Sixteen parts, one directory on your disk, one control panel. No account. And you don't have to learn any of it — a default agent operates ADI on request: it writes the tool, files the project, puts the service up. Two things I would rather you heard from me. It is early — I wrote every line of it, and the only people using it are me and my co-founder. And it is proprietary and source-available — free for personal use, free commercially under $1M and ten people, a licence past either. The source is on GitHub and the LICENSE file says exactly that. I'm here all day. Ask me the hard ones

Report

2mo ago

Forum Threads

p/adi

•

2mo ago

"Runs locally" is not the same as "private"

"Runs locally" is not the same as "private," and I say this as someone shipping a thing that runs locally.
Your projects, agents, notes, database, secrets: they're in a directory on your disk. Unplug the network and they're still there, still readable, still yours.
Inference is a different story. Unless you're running a local model, your prompts leave your machine for your provider. Local storage doesn't change that.
An updater that checks for a new build is a network call.
A peer-to-peer mesh is not end-to-end encryption. Those are two different claims.
Open Wireshark, run the thing, watch what connections it makes. A packet capture won't tell you everything, but it can test some of those claims.
What else do you see people fold into "runs locally" that doesn't belong there?

p/adi

•

2mo ago

What does your agent forget between conversations?

A question for anyone running agents in a day job rather than in a demo.
Mine used to lose things between conversations, and I only noticed because I kept retyping them. None of it was hard for the model. It was just gone by the next morning.
What I ended up doing was making the memory a file rather than a habit a title and a body, on disk, that the job opens already holding, and every other job can read.
The harder half is what happens when two of those notes disagree. Facts go in a base of their own, one plain sentence each. A new one is compared by meaning against everything already in there, and every near pair stops and asks for a ruling both true, merge them, one wins, or drop the new one. Nothing commits while a pair is open.
What's the thing you re-supply most? I'm collecting them, because I want to know whether they're the same for everyone or just mine.

View all