pickfit

BrowseDeveloper CLIs

akm — Agent Knowledge Manager

CLI tool to manage AI agent knowledge, memories, skills and bundles across assistants.

Tested on Linux and Windows

Use it

Linux x86_64

You need first

  • Runtimes: Node.js >= 22
  1. Install akm via npm

    npm install -g akm-cli

Check that it works

akm --version

The output should contain “0.10.261021”.

First thing to try

akm setup --yes

Run akm setup --yes first to set up your library, then akm index to build the search index.

Windows x86_64

You need first

  • Runtimes: Node.js >= 22
  1. install akm-cli via npm install -g

    node --version && npm --version && npm install -g akm-cli
    

Check that it works

akm --version

The output should contain “0.10.261022”.

First thing to try

akm setup --yes

Run akm setup --yes first to set up your library, then akm index to build the search index.

What it does

  • Manage agent knowledge, memories and skills
    How to use it
    1. Run akm index to build the search index.
    2. Run akm curate "<your task>" to get a shortlist of matching items for a task.
    3. Run akm show <ref> to load a matched item, for example akm show facts/conventions/domains.
    Tested
  • Use the same library from any coding agent
    Not shown working
  • Install and share capability bundles
    Not shown working
  • Run multi-step workflows you can resume
    Not shown working

How far pickfit got

Linux x86_64

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

Windows x86_64

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

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

Good for

  • build the search index
  • get a curated shortlist for a task
  • load a matched capability by ref
  • install capability bundles
  • run persisted multi-step workflows with resume

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 0.10.261021

Windows x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.10.261022

Differences the test machine hit

  • README: (Windows steps)
    In the test: pickfit ran these steps in PowerShell 7 (pwsh 7.6.9) as a standard user; the built-in Windows PowerShell 5.1 is not verified and does not run `&&`.

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.