My favorite AI GUI for Linux works with local or cloud models – and it’s free

Askimo can handle just about everything I need from AI, with a little setup. Here’s how I use it.

Read full bio October 13, 2026, 3:39 pm ET

Jack Wallen/ZDNET ZDNET’s key takeaways Askimo is a flexible, all-in-one AI tool. The Plans feature alone makes Askimo worth using. You can connect Askimo to cloud or local AI. I’ve been on the hunt for a one-stop-shop AI tool that can handle most of the tasks I need, and I may have finally found it.

That tool is called Askimo, and it’s available for Linux, MacOS, and Windows. It’s free (as long as you use local AI, which is what I do), and it includes features like projects, agents and skills, resource collections, plans, the ability to connect to local AI, MCP servers, voice input, notifications, keyboard shortcuts, web searches, RAG configuration, and more.

Also: How I built the writing app I needed in 2 hours for free

I’ve used Askimo for general AI chat, crafting resumes and cover letters, and early-stage app development. I’ve found Askimo to be quite flexible, so long as I’m willing to do a bit of extra work.

OK, it’s not as bad as you might think (at least for certain features), and the reason I’m doing a bit of extra work is that I’m sticking with local AI. If you’re using Askimo with a third-party AI service, you’ll find that it does a lot of what I have to do manually without the extra effort. The extra work is isolated to the Agents and Projects feature, where you might have to copy-and-paste the contents of, say, a resume into a chat, because local AI doesn’t have the ability to access folders (which is odd to me, but it’s how Askimo works), or connect the tool to a third-party AI service.

What I have found, however, is that Askimo aligns more with how I tend to work. I want to be part of the process, not have the technology do everything for me.

I’m going to walk you through how I built a project to create a cover letter based on a tech-writing resume for the freelance writer position at Company X.

Also: How I feed my files to a local AI for better, more relevant responses

Before I could do that, I had to first connect Askimo to my locally installed Ollama AI instance, which is configured within Settings. After opening Settings, I had to add a new AI Provider. I first had to have a working instance of Ollama running, with the models I wanted to use pulled, since Askimo can’t automatically pull models.

For instance, if I wanted to use the model llama3.3:3b, I would pull it with Ollama using the command:

ollama pull llama3.2:3b After that, it will be available to Askimo.

Within the Add AI Provider window, I selected Ollama and then clicked Connect.

In the resulting window, all I had to do was click Next.

I then had to select the model I wanted to use and click Save. That’s it. Askimo is now ready to use Ollama.

Now that Askimo is connected to Ollama, it’s time to create a Project. Let me first warn you: Projects can be a tad frustrating because you have to do a bit of extra work.

To create a project, I clicked Projects in the left sidebar and then clicked New Project.

In the Create New Project pop-up, I gave it a name (Cover Letters), clicked Add Source, and selected the resume file. Next, I clicked the Default Directory drop-down, selected Formal Writing, and clicked Save.

Now that the file has been added to the project, all I had to do was select the project from the project listing, and then type what I wanted in the chat, such as:

Write a cover letter for the position of freelance writer for Company X using the contents of the resume added to the RAG sources Unfortunately, Axios failed in this task.

Also: Stop local AI from crashing your Linux PC – 4 tips

Here’s what I discovered. Due to permission issues that prevent Askimo from reading the files on your drive, your best bet is to attach the file to the chat, whether it’s a standard chat or a Projects chat. This is frustrating, as Projects cannot use Resource Attachments Gathering (RAG) sources because they can’t access or process their contents. When I asked why Askimo was unable to read the contents of files added to RAG sources, it responded with three reasons:

“Files can be extremely large, which might cause technical issues during retrieval; some files contain sensitive information that cannot be accessed or shared for security or privacy reasons, or file formats may not be optimized for text-based interaction.”

What Askimo neglected to tell me was that my local model, Ollama, can’t access the content of files. To do that, I have to use an API key for a third-party AI service.

Fortunately, there’s an even better tool within Askimo, one that comes in very handy and avoids having to pay for an API key.

Plans are one of my favorite features in Askimo. Plans are essential AI-powered, multi-step workflows that you can create and use whenever you need them. Plans prevent you from having to create and recreate long, complicated chats that could take extensive time and effort and wind up confusing the AI in use.

As the name implies, Plans allow you to divide the work into steps that run, then pass the results of each step to the next.

Also: Someone made a free Photoshop clone – so I had to try it on Linux

You’ll find six pre-built plans in Askimo: Blog Post Writer, Job Application Writer, Research Report, Competitor Analysis, Meeting Notes Processor, and System Design.

Let’s use the Job Application Writer plan to do the same thing we did earlier, only this time we’ll find that it generates results much faster.

To do this task, I clicked Plans in the left sidebar and then selected Job Application Writer. In the resulting window, the first thing I did was select a good model for this job (such as llama3.2:3b). Once I did that, I had to do the following:

I hopped over to LinkedIn, found a job to use as an example, filled out the necessary information, and clicked Run Plan. Askimo set out to do its thing, and I watched it happen. Within less than two minutes, I had a Professional Summary I could then use for follow-up questions, such as writing a cover letter for this position (which I did, and it turned out quite well).

You can also create your own Plans, which are written in YAML. Yes, they are complicated at first, but once you have the hang of writing them, the sky’s the limit. The YAML files are laid out like this:

inputs: - key: topic # referenced in steps as {{topic}} label: Topic # caption shown in the UI type: text # text | multiline | toggle | number required: true # plan will not run if blank default: "" # pre-filled value hint: Enter a topic # placeholder / helper text You create sections for inputs, steps, and workflow. Your best bet is to select a pre-built plan, open the three-dot menu, then select Copy and Edit. Then, the Plan editor will open, so you can see how they are laid out. You can edit a copy and use it as a template to build your own plans.

Plans is that game-changing feature I plan on using quite a bit.

Askimo is one of those tools that can do much more than you think, but it does take a bit of effort to get to understand how it all works. The beauty of this app is that the second you learn one thing about it, it opens more doors to other features and aspects.

Even if I only ever used the Plan feature, it would allow me to create automated workflows for just about anything. That feature alone is worth the time and effort of getting up to speed with this tool.

I will also keep working to try and make it possible to use Projects so that Askimo can actually read the contents of RAG files so they can be used as input sources. Until then, I’ll keep using the Chat and Plans features and won’t have to rely on more than one app for anything AI-related (except maybe vibe coding, which VS Code does quite well).