Product launch · XiaoHu explains

LM Studio launches Bionic: a Codex for open-source models, and you decide whether it runs locally or in the cloud

An agent built for open models — run it locally for free with your data never leaving the device, or switch to the cloud only when you need more horsepower (zero data retention by default). The preview is live today on Mac and Windows.
60-second rundown
  • LM Studio has launched Bionic, an AI agent built for open-source models — a standalone new app, separate from the original LM Studio.
  • It actually gets things done: Work projects handle research, writing, and document tasks, while Code projects search files, edit code, and run commands right in your local codebase.
  • Its signature move: you choose where the model runs — locally (free, data stays on-device), in the cloud for frontier open models (zero data retention by default), or via LM Link, borrowing another computer's model over your local network.
  • It supports real-time local voice transcription — speech converts to text entirely on-device, and no audio ever gets uploaded.
  • Local and LM Link models are free with no billing setup required; only cloud models draw down credits based on usage. The preview is out today for Mac and Windows.
This piece is based on LM Studio's official launch materials and documentation. Claims about capabilities, privacy, and pricing reflect the vendor's own account and haven't been independently verified by a third party.
What it is

LM Studio just built an assistant that actually gets to work

LM Studio, the local large-model tool, has just released Bionic — an AI agent built specifically for open-source models.

For the past few years, LM Studio has been the first thing anyone running open-source models on their own machine installs. It wrapped up the hassle of downloading models and running local inference into one easy-to-use desktop app. But it always felt more like a chat window bolted onto a model manager — you could talk to a model, but you couldn't really count on it to carry a real task through from start to finish.

If you've used Codex, Claude Code, or similar AI assistants that write documents and edit code for you, Bionic is chasing the same goal — except it's built specifically for open-source models and runs on your own machine by default. It can create and edit documents, slides, and PDFs, and it can search your codebase, edit files, and run commands, all without handing your material over to someone else's cloud first.
🔑Why it matters: most AI assistants capable of doing real work require sending your files, code, or even your voice to the vendor's cloud servers first. Bionic flips that — it hands the choice of where the model runs back to you, and the local route is free, with your data staying on-device the whole time.
Bionic's official launch demo. Source: LM Studio
The old catch-22

Getting AI to really do your work used to mean picking a side

Getting an AI assistant that could actually roll up its sleeves used to mean facing an unavoidable trade-off.

Say you want AI to read through a stack of research notes and write up a comparison, or hunt down a timeout bug in a project's codebase and fix it. For it to actually read your files and edit your code, it needs access to that material first. The most capable assistants today process that material by shipping it off to the vendor's cloud. The work gets done beautifully, but your contracts, code, and recordings all pass through someone else's servers along the way.

The other route is running an open-source model locally yourself. Privacy is preserved, but these tools mostly stop at chat — you ask, it answers, and when it actually needs to touch files, run a string of commands, and save the results, it usually falls short.

Cloud AI assistants

Great at heavy lifting and effective, but your files, code, and voice have to be uploaded to the vendor's cloud to be processed.

Local open-source tools

Your data stays on your own machine and privacy holds up, but most can only chat — they can't carry out a full real task.

Bionic wants to have it both ways: doing real work while letting you decide whether your data ever leaves the device.

What it can do

Two project types: one for documents, one for code

Bionic splits work into two project types, and you pick whichever fits the task at hand.

Work projects
For research, writing, analysis, and document tasks
  • Create and edit documents, slides, and PDFs
  • Drag files and folders in as reference material
  • Everything it generates is filed under the project and saved automatically
Example: "Read through the options in these notes, summarize the trade-offs for each, and save the recommendation as recommendation.md."
Code projects
For development work in your local codebase
  • Comes with file, search, Git, and command-line tools built in
  • Can dig through the whole repo and edit multiple files at once
  • Runs commands locally and shows you a diff before any change is kept
Example: "Find where request timeouts are handled, explain the current logic, fix that broken edge case, and rerun the relevant tests."

Within a single project you can open several independent sessions, each working its own task, and you can run multiple projects at once to push several jobs forward in parallel. Any files it generates or changes land in the project's shared file area, visible to every session in that project. In code projects, when it runs commands or edits files, it shows you the diff and command output first and lets you decide whether to keep the change.

Bionic handling document and code tasks
Bionic can create and edit documents, slides, and PDFs, and it also handles coding tasks — every change saves automatically. Source: LM Studio
The core difference

Where the model runs is entirely up to you

This is where Bionic diverges most from other AI assistants: for the same task, you get to decide where the model behind it actually runs.

Every Bionic session has three possible destinations, and privacy and cost split along those same three paths.

One task What you hand Bionic Run locally Free Runs open models on your machine Data never leaves your device Run in the cloud Paid Runs top open models: GLM, Kimi Zero retention, wiped after use LM Link remote Free Borrows a model over your LAN Model and data stay with you
One taskWhat you hand Bionic
↓ You choose where it runs ↓
Run locallyFree
Runs an open model on your machine — data never leaves the device.
Run in the cloud
Secure cloud runs frontier open models like GLM and Kimi — zero data retention by default, deleted after processing.
LM Link remoteFree
Borrows a model from another computer on your LAN — model and data stay in your hands.
Key innovation

Two of the three routes are completely free and never let your data leave your own turf: local models use your own machine's compute, and LM Link uses another machine's compute on your LAN. Only when you need the strongest frontier open models for the heaviest jobs do you take the paid cloud route — and even that one defaults to zero data retention. Privacy and cost both come broken down into options you can see at a glance and switch between at will.

Before going further, two new terms here are worth defining.

What zero data retention (ZDR) means

ZDR stands for Zero Data Retention. It means whatever you send to the cloud server gets discarded the instant the model finishes processing it — no copy of your data sits on the server. Cloud inference servers are all located in the US, and this policy is on by default across the board.

What LM Link is

LM Link lets Bionic borrow a model running on another computer on your local network. Say your desktop at home has a beefy GPU in it and your laptop doesn't have enough horsepower — the laptop connects over and uses the desktop's model instead. Both the model and the data stay within your own devices; nothing leaves the house. This route is free, just like running locally, and it doesn't draw down credits.

Cloud frontier open models GLM and Kimi, zero data retention by default
For the heaviest jobs, you can switch to the cloud to run frontier open models like GLM and Kimi — the entire cloud line defaults to zero data retention. Source: LM Studio
Downloading local open models directly in the app
Whether it's everyday chat or complex agentic tasks, you can download the latest open models straight in the app and run them locally. Source: LM Studio
Another privacy angle

Talk to it, and the words never leave your computer

Beyond typing, Bionic can listen too. It comes with local real-time voice transcription — talk to it naturally, and what you say gets converted to text on the fly.

What matters is where the processing happens: your voice and audio get transcribed entirely on-device and never leave your computer. It's the same logic as typing to a local model — keeping the most private slice of your data on your own side.

Bionic's local real-time voice transcription interface
Talk to Bionic naturally and your speech transcribes in real time — voice and audio data is processed locally and never leaves the device. Source: LM Studio
Under the hood, getting started

Still built on LM Studio, now available for Mac and Windows

Running open models smoothly on your own machine comes down to the inference stack Bionic is built on — technology LM Studio has spent a long time refining.

LM Studio runtimeLM Studio's own local model runtime
MLXApple's machine-learning framework for its own Apple Silicon chips
llama.cppA widely used open-source local inference engine

To be clear: Bionic is a standalone new app, separate from the original LM Studio. If you still want to dig into the more advanced, low-level configuration, the original LM Studio keeps working right alongside Bionic.

Does it cost money?

Local models and LM Link remote models are both free — no credits drawn, no billing setup required upfront. Credits only get deducted when a session uses a cloud model, and how much depends on the model you picked and how much text got processed. Accounts come in Personal and Organization (team) flavors. There's no published flat per-task price yet — you just see cumulative usage on the usage page.

3 options
Where the model runs: local / cloud / LM Link remote
2 types
Project types: Work for document research / Code for local codebases
Zero
Default cloud inference data retention (ZDR); servers located in the US
Mac + Win
Preview live today; no signup needed to run locally
🧰 Getting-started card · LM Studio Bionic
PricingLocal models + LM Link remote are free with no billing setup; cloud models draw credits based on usage (no flat price published — it depends on the model chosen and text processed), split into Personal / Team accounts
Barrier to entryDownload and go on Mac / Windows — no signup needed to run locally; only using cloud frontier models requires logging in and adding funds
Source: LM Studio's official tweet thread (July 17, 2026) and official documentation at lmstudio.ai/docs/bionic (including quick-start, credits and usage, etc.). Capability, privacy, and pricing claims reflect the vendor's own account and haven't been independently verified by a third party; Bionic is currently an initial preview.