pickfit

BrowseLocal AI tools

LocaLM

Offline CLI tool to run local LLMs for chat, coding, image/music/video, RAG, memory and voice.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.12,<3.13
  • A GPU is optional
  1. Install localm via uv tool

    uv tool install localm
  2. Provision CPU llama backend

    export LOCALM_HOME="$HOME"/localm-data && localm setup-llama --backend cpu
Where the README and reality differ
  • README: docs say API served over HTTPS with built-in certificate
    What worked: plain `http://127.0.0.1:8642/health` and `/v1/models` work; `https://` fails with curl exit 35 SSL connect error
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

uv tool install localm 2>&1
export LOCALM_HOME=/home/sbx/localm-data && localm setup-llama --backend cpu 2>&1
localm --version 2>&1
export LOCALM_HOME=/home/sbx/localm-data && mkdir -p "$LOCALM_HOME" && localm doctor 2>&1

Check that it works

localm --version 2>&1

The output should contain “localm, version 0.3.2”.

First thing to try

export LOCALM_HOME="$HOME"/localm-data && mkdir -p "$LOCALM_HOME" && localm doctor 2>&1

Run localm doctor first to check your setup.

What it does

  • Chat with local models and see replies as they stream
    How to use it
    1. Add a downloaded GGUF model with localm add <model.gguf>.
    2. Chat with it using localm run <model> --prompt "<your text>".
    3. To serve it over an OpenAI-style API, run localm serve <model> --port <port> and send requests to http://127.0.0.1:<port>/v1/chat/completions.
    Tested
  • Run a coding agent that edits files
    Not tested
  • Generate images, video and music locally
    Not tested
  • Chat with your own files and get citations
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 1 of 4 features work
  4. Works offline

Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • chat with a local LLM offline in terminal
  • run autonomous coding agent to edit files and run tests
  • generate images, music and video locally
  • chat against local files and folders with citations
  • dictate with local speech-to-text and listen to replies

An alternative to LM Studio and Ollama.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

It produces model output

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.3.2

Differences the test machine hit

  • README: `pip install localm` then `localm setup-llama`
    In the test: use isolated `uv tool install localm`; set LOCALM_HOME=/home/sbx/localm-data and run `localm setup-llama --backend cpu` before any run/serve
  • README: SET LOCALM_HOME once in shell profile
    In the test: `export LOCALM_HOME=...` on every command or version/doctor warn about contained default inside the uv tool venv

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.