pickfit

BrowseLocal AI tools

Ori

Offline-capable agentic IoT runtime that reasons about sensor data and acts under tiered authority.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.11
  1. clone ori-runtime source

    rm -rf ori-src && git clone https://github.com/ori-platform/ori-runtime.git ori-src
  2. pip install editable with runtime and dev extras

    cd ori-src && python3 -m pip install -e ".[runtime,dev]"
  3. install missing aiomqtt needed by tests

    python3 -m pip install aiomqtt
Where the README and reality differ
  • README: python -m pip install "ori-runtime[eval] @ git+https://github.com/ori-platform/ori-runtime.git@<commit-or-tag>" with literal <commit-or-tag> placeholder
    What worked: use concrete tag/checkout or clone then pip install -e ".[runtime,dev]"; candidate 2 was used
  • README: python -m pip install -e ".[runtime,dev]" then pytest tests/ -v works
    What worked: python3 -m pip install aiomqtt before pytest

Check that it works

python -m ori.runtime --help

The output should contain “Ori Runtime”.

First thing to try

cd ori-src && python -m pytest tests/test_rule_engine.py -v

What it does

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

  • Reason about sensor data in tiers
    Not tested
  • Act on equipment under graded authority levels
    Not tested
  • Keep working without an internet connection
    Not tested
  • Keep a record of actions you can reconstruct
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Main function works
  4. Works offline

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

Good for

  • switch to inverter power on grid instability
  • propose opening safety circuit on critical fault
  • monitor PC system health on a laptop via psutil

An alternative to Grafana and AWS IoT Core.

How pickfit tested it

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

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 2.5.0

Differences the test machine hit

  • README: pytest tests/ -v as full-suite smoke test
    In the test: run pytest tests/test_rule_engine.py -v (143 passed) or scripts/pc_health_report.py; full suite did not finish in 600s (killed at ~77%)
  • README: bash scripts/smoke-runtime-local.sh
    In the test: scripts/smoke-runtime-local.sh requires a .venv directory and a local-SLM config; verified with system python via scripts/pc_health_report.py instead

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.