pickfit

BrowseDeveloper CLIs

Cortex

Local-first memory engine giving AI agents persistent cross-session memory on-device.

Use it

Before you install: known vulnerabilities

pickfit found 7 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:openssl 0.10.75 rust-openssl has incorrect bounds assertion in aes key wrap (GHSA-8c75-8mhr-p7r9, high, fixed in 0.10.78)
  • crates:pyo3 0.23.5 PyO3 has an Out-of-bounds Read in `nth` / `nth_back` for `PyList` and `PyTuple` iterators (GHSA-36hh-v3qg-5jq4, high, fixed in 0.29.0)
See 5 more

Linux x86_64

You need first

  • Runtimes: Rust toolchain (provides cargo)
  1. Download and install release binary

    mkdir -p ~/.local/bin ~/.cortex /tmp/cortex-dl && curl -sL -o /tmp/cortex-dl/cortex.tar.gz https://github.com/gambletan/cortex/releases/download/v2.4.0/cortex-mcp-server-linux-x86_64.tar.gz && tar xzf /tmp/cortex-dl/cortex.tar.gz -C /tmp/cortex-dl && cp /tmp/cortex-dl/cortex-mcp-server ~/.local/bin/ && chmod +x ~/.local/bin/cortex-mcp-server && ~/.local/bin/cortex-mcp-server --version

Check that it works

cortex-mcp-server --help

The output should contain “Cortex memory engine — MCP server & CLI tools”.

First thing to try

CORTEX_NO_EMBEDDINGS=1 cortex-mcp-server ~/.cortex/memory.db stats

Run cortex-mcp-server <database file> stats to open a memory database and see its statistics.

What it does

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

  • Give AI agents memory that lasts across sessions
    Not tested
  • Sync memories across devices with encryption
    Not tested
  • Share approved excerpts with Meta Muse
    Not tested
  • Track people across channels by matching identities
    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

  • store a new memory via CLI
  • search stored memories
  • export all data as JSON backup
  • show weekly memory digest

An alternative to Mem0 and OpenAI Memory.

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 2.4.0

Differences the test machine hit

  • README: pip install cortex-ai-memory (Python bindings)
    In the test: On Python 3.12 Linux there is no manylinux cp312 wheel (only cp39 linux + cp312 macOS), so `uv tool install cortex-ai-memory` falls back to the sdist and fails building via maturin/cargo with `linker cc not found`; cargo builds need a Rust toolchain plus C linker, which this box must not install. U…
  • README: Official packages table: PyPI cortex-ai-memory vs binary via Releases/brew
    In the test: The PyPI wheel contains only the `cortex_ai_memory` Python module (native .so), no `cortex-mcp-server` binary; the CLI in the README examples comes from the GitHub Releases tarball `cortex-mcp-server-linux-x86_64.tar.gz` (installed to ~/.local/bin).
  • README: Binary install from GitHub Releases
    In the test: Release tarball is a prebuilt binary that cannot be read/audited before running; installed without a readable install script.

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.