pickfit

BrowseLocal AI tools

InferBridge

Windows-first OpenAI-compatible local LLM server on Intel via OpenVINO GenAI with chat UI and model tools.

Tested on Linux

Use it

Linux x86_64

  1. Clone InferBridge source

    rm -rf /tmp/ib2 && git clone https://github.com/Quazmoz/InferBridge.git /tmp/ib2 && cp -r /tmp/ib2/. ./
  2. Install with pip editable dev dependencies

    pip install -e .[dev]
Where the README and reality differ
  • README: `pip install -e .[dev]` then `.\start_server.bat --mock` / `.\start_server.bat --check-devices`
    What worked: On Linux use `OV_LLM_MOCK=1 python -m app.server --mock --host 127.0.0.1 --port 8123 --model tinyllama-1.1b-chat-fp16` (installed `inferbridge` CLI works the same); `start_server.sh --mock` requires a `.venv` created by `./setup.sh --minimal` and `start_server.bat` is Windows-only.

Check that it works

inferbridge --help

The output should contain “usage: inferbridge”.

First thing to try

OV_LLM_MOCK=1 python -m app.server --mock --host 127.0.0.1 --port 8123 --model tinyllama-1.1b-chat-fp16
curl -sf http://127.0.0.1:8123/health/ready

Once the server is running, check that it is ready with curl -sf http://127.0.0.1:8123/health/ready.

What it does

These come from the README; pickfit didn’t check them one by one.

  • Serve local LLMs through an OpenAI-compatible API
    Not tested
  • Chat with streaming replies in the browser
    Not tested
  • Chat with local vision-language models
    Not tested
  • Generate text embeddings locally
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

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

Good for

  • chat with local LLM via OpenAI-compatible chat completions
  • generate text embeddings locally
  • chat with local vision-language models using images
  • diagnose runtime, devices and NPU readiness via System Doctor
  • run local hardware benchmarks for inference

How pickfit tested it

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

Linux x86_64

Its service answers requests

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

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.