pickfit

BrowseDeveloper CLIs

milk

Terminal host routing each prompt between a cheap primary agent and stronger escalation agent.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Go 1.26.2 or newer
  1. Download milk install script to read before running

    curl -fsSL https://raw.githubusercontent.com/scoutme/milk/main/install.sh -o /tmp/milk-install.sh
  2. Download verify and install milk binary

    mkdir -p "$HOME/.local/bin" /tmp/milkdl && curl -fsSL https://github.com/scoutme/milk/releases/download/v0.8.5/milk-linux-amd64 -o /tmp/milkdl/milk-linux-amd64 && curl -fsSL https://github.com/scoutme/milk/releases/download/v0.8.5/milk-linux-amd64.sha256 -o /tmp/milkdl/milk-linux-amd64.sha256 && cd /tmp/milkdl && sha256sum -c milk-linux-amd64.sha256 && install -m 755 /tmp/milkdl/milk-linux-amd64 "$HOME/.local/bin/milk"
Where the README and reality differ
  • README: curl -fsSL https://raw.githubusercontent.com/scoutme/milk/main/install.sh | sh
    What worked: install.sh exits 1 on Linux before downloading: detect_platform() ends with `[ "$GOOS" = "windows" ] && EXT=".exe"`, so the function returns 1 on Linux and `set -e` aborts in main(). Worked around by downloading milk-linux-amd64 + .sha256 for v0.8.5 directly, verifying with sha256sum -c, and instal…

Check that it works

milk --version

The output should contain “milk version v0.8.5”.

Run milk in a terminal inside your project directory to start an interactive session.

What it does

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

  • Route prompts between a cheap and a stronger agent
    Not tested
  • Use built-in tools and MCP servers
    Not tested
  • Run multi-agent workflows with checkpoint and resume
    Not tested
  • Compare agents side by side with milk eval
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Not used yet
  4. Works offline

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

Good for

  • list the Go files in this directory
  • review the routing design with escalation agent
  • summarize repository in one-shot mode

An alternative to Claude Code, MiMo-Code, OpenCode and Aider.

How pickfit tested it

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

Linux x86_64

Installs and starts

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version v0.8.5

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.