pickfit

BrowseDeveloper CLIs

AtMem

Local-first auditable memory control plane giving AI agents governed retrieval and verifiable execution evidence.

Use it

Before you install: known vulnerabilities

pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • pypi:cryptography 48.0.1 cryptography: PKCS#7 EnvelopedData decryption exposes a Bleichenbacher oracle through distinguishable errors and timing (GHSA-g6cj-pr64-35w5, high, fixed in 50.0.0)
See 1 more

Linux x86_64

You need first

  • Runtimes: Python 3.10 or newer
  1. install atmem via uv tool

    uv tool install atmem==2.3.10
  2. initialize atmem home and private Bun runtime

    atmem init
Where the README and reality differ
  • README: `atmem control verify` and `atmem blackbox runs` as standalone examples
    What worked: run `atmem init` first; it creates ~/.atmem/config/control-plane.json and downloads/verifies pinned Bun 1.4.2 to ~/.atmem/runtime/bun

Check that it works

atmem --version

The output should contain “atmem 2.3.10”.

First thing to try

atmem status --json

Run atmem init to set up, then atmem status --json to check the current state.

What it does

  • Give agents governed long-term memory
    How to use it
    1. In Python, create a store with from atmem import Memory; m = Memory("<db file>").
    2. Save a fact with m.remember("<user id>", "<your text>", session_id="<session id>").
    3. Look it up with m.recall("<user id>", "<query>", limit=5) and check the store with m.verify("<user id>").
    Tested
  • Record verifiable evidence of agent runs
    How to use it
    1. Run atmem control verify to check the recorded control chain.
    2. Look for a PASS line for each check, such as control_transition_chain.
    Tested
  • Pass delegated context to agents
    Not shown working
  • Record model and tool events in Black Box
    Not shown working

How far pickfit got

Linux x86_64

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

Good for

  • give OpenClaw or Pydantic AI agents governed long-term memory
  • share project memory across coding agents
  • record model and tool events in agent black box

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 2.3.10

Differences the test machine hit

  • README: README `Memory.recall` example without field names
    In the test: recalled record exposes text under key `content` (e.g. "User's preferred editor is Vim.")

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.