pickfit

BrowseDeveloper CLIs

Eidetic Engine (`ee`)

Rust CLI providing durable local-first searchable memory for coding agents.

Tested on LinuxKnown vulnerabilities

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.

  • crates:pulldown-cmark 0.13.4 Exponential event growth with `ENABLE_WIKILINKS` (RUSTSEC-2026-0414, high, fixed in 0.13.5)
See 1 more

Linux x86_64

You need first

  • Runtimes: nightly Rust toolchain
  1. Download release installer script only

    curl -fsSL https://github.com/Dicklesworthstone/eidetic_engine_cli/releases/download/v0.18.0/install.sh -o /tmp/install-ee.sh
  2. Run release installer easy-mode verify for v0.18.0

    export EE_VERSION=v0.18.0 && bash /tmp/install-ee.sh --easy-mode --verify --no-gum

Check that it works

ee --version

The output should contain “ee 0.18.0”.

First thing to try

mkdir -p /tmp/ee-demo && ee init --workspace /tmp/ee-demo --json
ee remember "This project treats clippy warnings as errors with pedantic and nursery enabled." --workspace /tmp/ee-demo --level procedural --kind rule --tags rust,ci --json

Run ee init --workspace <dir> --json to set up a memory workspace in your project folder.

What it does

  • Store searchable memories for coding agents
    How to use it
    1. Set up a workspace with ee init --workspace <dir> --json.
    2. Save a memory with ee remember "<your text>" --workspace <dir> --level procedural --kind rule --tags <tags> --json.
    Tested
  • Build context packs with provenance
    How to use it
    1. Store memories in a workspace with ee remember.
    2. Create a pack for a task with ee pack "<your task>" --workspace <dir> --max-tokens <number> --format markdown.
    Tested
  • Connect memories with graph analytics
    How to use it
    1. Store two or more memories in a workspace with ee remember.
    2. Rank memories by importance with ee graph pagerank --workspace <dir> --json.
    Tested
  • Search with lexical and semantic retrieval
    Not shown working

How far pickfit got

Linux x86_64

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

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

Good for

  • pack durable memories into context for a task
  • search memories with explainable scores
  • store durable procedural rules
  • import cass session history as evidence
  • inspect provenance for a memory

An alternative to Chroma, Qdrant, MCP memory server and Plain notes / CLAUDE.md.

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 0.18.0

Differences the test machine hit

  • README: cargo +nightly install eidetic-engine --version 0.18.0 --locked
    In the test: skipped cargo candidate because box has no Rust toolchain and rules forbid installing Rust/Go; used release install.sh script instead
  • README: install.sh --easy-mode --verify verifies checksum and Sigstore bundle
    In the test: installer fetches prebuilt binary tarball ee-x86_64-unknown-linux-musl.tar.xz at runtime which cannot be read as a script; SHA-256 verified, Sigstore bundle absent so signature check skipped
  • README: ee search hybrid retrieval works after ee remember
    In the test: run ee index rebuild --workspace <dir> after first remember/model download before hybrid search returns full results; first search reported index_incompatible, pack still worked via lexical fallback

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.