[KongchangAI]
Product

Locally Uncensored

An open-source local AI desktop application that supports running chat, image generation, video, voice, and computer-control models on the user's own machine, with cross-platform support for Windows, Linux, and macOS.

Timeline (last 90 days)

Oct 19

In the desktop app, users can use it by turning on the Cloud switch and selecting DeepSeek V4.1 Flash 1017 in Chat; the app pulls the catalog from the server and no client update is needed.

Unverified50%
Oct 19

Using a rolling alias (such as deepseek-flash) cannot reproduce historical behavior, whereas a dated model ID (such as deepseek-v4.1-flash-1017) pins to a specific version and is suitable for change control and regression comparison in production.

Unverified50%
Oct 18

Locally Uncensored 3.0.6 adds computer control that lets local models operate user-approved apps with the mouse and keyboard, with screenshots and clicks staying on the local machine and not uploaded to the cloud.

Unverified50%
Oct 18

LU marks content read from the screen as untrusted, but the wording used to judge whether a button is sensitive comes from a list, and expressions the list does not recognize cannot be identified; the eight corrections and ten security fixes added after Windows verification have only been run in automated tests.

Unverified50%
Oct 18

LU has no background mode on any platform; it works in the foreground using the user's real pointer.

Unverified50%
Oct 18

On Linux and macOS, LU can only rely on screenshots and cannot determine what a click will press, so every click is asked about as a sensitive action; on Mac it also requires the two system permissions of Accessibility and Screen Recording, and the model must have image input capability.

Unverified50%
Oct 18

LU's computer control has only been verified point by point on Windows (a Windows 10 machine); Linux has not actually been run in the app and requires an X11 session; macOS is integrated but not sufficiently tested; the control list and autonomous mode exist only on Windows.

Unverified50%
Oct 18

Using voice commands, a local 9B model types notes in Notepad based on a control list, taking 11 to 22 seconds from the end of the voice command to the voice announcement of the result; this data was measured before the mechanism that asks on every new conversation went live.

Unverified50%
Oct 18

The dedicated screen model Holo 3.1 9B is marked Beta in the catalog, with 16GB VRAM recommended as a starting point; in the author's Windows tests it completed a simple typing task in only one of three runs, and cannot coexist with a 9B chat model on a 12GB graphics card.

Unverified50%
Oct 18

In the author's comparison of three runs each on two tasks, the runs with images totaled 497 seconds and the runs relying only on the control list totaled 381 seconds, all six completed, and relying on the list alone was actually faster.

Unverified50%

29 more timeline events

All Facts (20)

Unverified

In the desktop app, users can use it by turning on the Cloud switch and selecting DeepSeek V4.1 Flash 1017 in Chat; the app pulls the catalog from the server and no client update is needed.

50%
Unverified

Using a rolling alias (such as deepseek-flash) cannot reproduce historical behavior, whereas a dated model ID (such as deepseek-v4.1-flash-1017) pins to a specific version and is suitable for change control and regression comparison in production.

50%
Unverified

Locally Uncensored 3.0.6 adds computer control that lets local models operate user-approved apps with the mouse and keyboard, with screenshots and clicks staying on the local machine and not uploaded to the cloud.

50%
Unverified

LU marks content read from the screen as untrusted, but the wording used to judge whether a button is sensitive comes from a list, and expressions the list does not recognize cannot be identified; the eight corrections and ten security fixes added after Windows verification have only been run in automated tests.

50%
Unverified

LU has no background mode on any platform; it works in the foreground using the user's real pointer.

50%
Unverified

On Linux and macOS, LU can only rely on screenshots and cannot determine what a click will press, so every click is asked about as a sensitive action; on Mac it also requires the two system permissions of Accessibility and Screen Recording, and the model must have image input capability.

50%
Unverified

LU's computer control has only been verified point by point on Windows (a Windows 10 machine); Linux has not actually been run in the app and requires an X11 session; macOS is integrated but not sufficiently tested; the control list and autonomous mode exist only on Windows.

50%
Unverified

Using voice commands, a local 9B model types notes in Notepad based on a control list, taking 11 to 22 seconds from the end of the voice command to the voice announcement of the result; this data was measured before the mechanism that asks on every new conversation went live.

50%
Unverified

The dedicated screen model Holo 3.1 9B is marked Beta in the catalog, with 16GB VRAM recommended as a starting point; in the author's Windows tests it completed a simple typing task in only one of three runs, and cannot coexist with a 9B chat model on a 12GB graphics card.

50%
Unverified

In the author's comparison of three runs each on two tasks, the runs with images totaled 497 seconds and the runs relying only on the control list totaled 381 seconds, all six completed, and relying on the list alone was actually faster.

50%
Unverified

On Windows, LU reads the list of buttons and fields of the target window (UI Automation); models that can see images get screenshots plus the list, while models that cannot see images work from the list alone.

50%
Unverified

A screen task ends after at most 25 steps or 8 minutes, and the time the user spends answering questions counts toward it.

50%
Unverified

LU's pause shortcut is Ctrl+Alt+Space and its stop shortcut is Ctrl+Alt+Esc; on Mac these are Control+Option+Space and Control+Option+Esc; moving the mouse during an autonomous session also triggers a pause.

50%
Unverified

Actions such as sending, purchasing, deleting, and changing permissions, as well as clicking unnamed buttons, links or menu items, are all treated by LU as sensitive actions that must be asked about in any mode.

50%
Unverified

At no level can LU enter the terminal, password managers, system login and permission dialogs, security settings, the Run dialog, or windows with administrator privileges, nor will it type into password fields or accept pasting into password boxes.

50%
Unverified

The computer control permission for each new conversation is valid only for the current conversation; a new conversation or each conversation after an app restart asks again, and no setting can skip this confirmation card.

50%
Unverified

Computer control is off by default under Agent Permissions in settings; once enabled, it still asks at four points: each new conversation, the first operation of each app, every action (supervised mode asks by default), and sensitive actions (always asked in any mode).

50%
Unverified

In the Locally Uncensored app, image models require a minimum of 8GB of memory, and video models require a minimum of 16GB of memory.

50%
Unverified

The Mac version of Locally Uncensored is currently in beta and has only been tested on one M5 Pro (48GB memory).

50%
Unverified

The app marketplace catalog contains a total of 23 image models (10 of which are in the Unfiltered group) and 31 video models (14 of which are in the Unfiltered group).

50%

Source Articles