In this quick video, we're going to go

over LM Studio Bionic, which is

essentially a agentic harness for open

weights models. In my opinion, this is

more important than ever with everything

going on in AI. I do believe open source

and open weights is something that

everybody should become familiar with.

And today, it's not really about LLMs

anymore, it's about running LLMs within

agents. ChatGPT is now ChatGPT work and

Codex, Claude is now co-work and Claude

code, and that is essentially what LM

Studio is doing. But the promise of LM

Studio is you could run it with local

models where you're technically not

paying a third-party provider.

Everything is staying local on your

computer, it's private, and you have all

these models you can choose from that

are optimized to work on your computer.

Bionic is an AI agent for getting real

work done with open models, including

coding, research, and complex work with

documents and files. We commit to zero

data retention and never training on

your data. You could run it either

locally or use the largest frontier open

source models through LM Studio secure

cloud. So, essentially, this is a soft

launch for their own cloud model

services. Bionic works with powerful

open source models like GLM 5.2, Kimiko

2.7 code. I'm sure Kimiko 3 is going to

come soon. You can have it organize

local folders, edit files, summarize

materials, all running locally on your

computer with those open models. So, the

difference between this and previous LM

Studio is LM Studio was able to run LLMs

and use tools, but not make edits, not

really take big actions. But Bionic is

able to do that. You create multiple

projects. We'll create a new one now.

We'll call this for video, and you can

see down here it could either be code or

work. Now, by default, it starts in

work, and if you do that, it won't have

shell access. So, in my case, I like to

use code. Here we have my three models I

have installed at the moment. But this

release makes it kind of clear of what's

really going on in AI right now.

Frontier models are getting too

expensive, and people want to run and

probably will need to run open source in

the near future. Now, the biggest caveat

here is that open weights models that

you're running locally on your computer

will not compare with Claude code or

Codex or any of these frontier models.

They're running on huge infrastructure

that you just won't have on your

computer. That means you have to adjust

your approach. The approach in how much

context you want to use, the approach in

how much you're going to trust your

agent. Because even last week, there

were plenty of reports of GPT-5.6

deleting files off of people's computer.

My point is, these agents still make

mistakes. You have to understand this is

a smaller model. It has less

instructions, has less reasoning

capabilities, and it still has access to

your full file system. With that being

said, if we go into settings, one thing

that's missing is skills. And in coding

agents specifically, skills are so

important because they're reusable

prompts. The fact that skills are

missing here means that the CLI tools

I'm using are less powerful or less

capable because the Bionic Agent can't

read the skills that go with the CLI

tools. So, now I'm just going to have it

use Bright Data CLI to tell me about the

current situation with Gable 5. And And

if it's going to subscription plans. So,

I'm going to send it off. I also like,

by the way, how we could actually see

the thinking. The reasoning has been

hidden or truncated on Claude and also

on ChatGPT on Codex. And there we go.

Emerging reports suggest that it's being

reintegrated into subscription plans

with a usage cap. So, overall, I think

this is really cool. You have to manage

your expectations, manage how you expect

to work and get work done. It's all

possible. It's a workflow shift. And I

suggest at least playing with this

understanding, getting to know Open

Weights.