pickfit

BrowseDeveloper CLIs

Mercury CLI

Terminal environment for running parallel AI coding agents that edit files and run tests.

Tested on Linux

Use it

Linux x86_64

You need first

  • System packages: git
  1. npm global install of mercury-tech-cli shim

    npm install -g mercury-tech-cli
  2. forced first-run payload install plus version check

    MERCURY_INSTALL_ARGS=--force mercury --version
Where the README and reality differ
  • README: npm install -g mercury-tech-cli then check mercury --version
    What worked: Prefix the first run with MERCURY_INSTALL_ARGS=--force (i.e. MERCURY_INSTALL_ARGS=--force mercury --version) so the product installer overwrites the npm shim at ~/.local/bin/mercury; without it the installer refuses ('stable command NOT written: an existing non-Mercury-managed command is already at…

Check that it works

mercury --version 2>&1

The output should contain “Mercury 1.0.1”.

Run mercury --version to confirm the install, then run mercury to start.

What it does

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

  • Run several AI coding sessions at once
    Not tested
  • Use both provider and local models
    Not tested
  • Start agents and workflows across companies
    Not tested
  • Step through tests and debuggers
    Not tested

How far pickfit got

Linux x86_64

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

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

Good for

  • read and edit files and run shell commands via agent
  • run parallel coding sessions
  • run one-shot prompts headlessly

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 1.0.1

Differences the test machine hit

  • README: check mercury --version after opening a new terminal
    In the test: First invocation of mercury downloads the ~27MB linux-x64 release archive (v1.0.1), verifies checksum, and stages ~/.mercury/versions/1.0.1 before printing the version; allow ~20s. Direct versioned launcher ~/.mercury/versions/1.0.1/mercury --version answers instantly.
  • README: run `mercury` inside a repository; headless via mercury run
    In the test: Interactive `mercury` needs a TTY/repository and `mercury run "<prompt>"` needs a signed-in model provider, so neither was runnable with no API keys; verified function with `mercury --help` and `mercury update --check` (no sign-in needed) 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.