pickfit

BrowseMCP servers

sessionmem

Local-first MCP server that stores project memories across AI coding sessions in SQLite.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Node.js 20.19+ or 22.13+
  1. install sessionmem via npm install -g sessionmem

    npm install -g sessionmem

Check that it works

sessionmem ping

The output should contain “sessionmem is operational”.

First thing to try

sessionmem ping

Add it to your agent

claude mcp add sessionmem -- sessionmem run
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "sessionmem": {
      "command": "sessionmem",
      "args": [
        "run"
      ]
    }
  }
}

Add sessionmem run as an MCP server command in your AI coding client, then call its tools from there.

Linux x86_64

You need first

  • Runtimes: Node.js 20.19+ or 22.13+
  1. install sessionmem via npm

    npm install -g sessionmem
Where the README and reality differ
  • README: storeMemory importance as float example 0.8 implied
    What worked: importance must be int (schema expects int, e.g. 1) - probe error -32602 invalid number at importance

Check that it works

sessionmem --version

The output should contain “1.10.1”.

Add it to your agent

claude mcp add sessionmem -- sessionmem run
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "sessionmem": {
      "command": "sessionmem",
      "args": [
        "run"
      ]
    }
  }
}

Add sessionmem run as an MCP server command in your AI coding client, then call its tools from there.

What it does

  • Store project decisions across sessions
    How to use it
    1. Run sessionmem run as an MCP server in your client.
    2. Call the storeMemory tool with a session ID, kind set to decision, and the decision text as content.
    Tested
  • Capture session events while you work
    How to use it
    1. Run sessionmem run as an MCP server in your client.
    2. Call the ingestSessionEvents tool with a session ID and a list of events, each with an ID, event type and payload.
    Tested
  • Load relevant memories when a session starts
    How to use it
    1. Run sessionmem run as an MCP server in your client.
    2. Call the startup_inject_memories tool with no arguments at the start of a session.
    Tested
  • Search stored memories by text
    How to use it
    1. Run sessionmem run as an MCP server in your client.
    2. Call the searchMemoryIndex tool with your search text as query.
    Tested

How far pickfit got

macOS arm64

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

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 4 features work
  4. Works offline

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

Good for

  • capture session events while you work
  • summarize decisions and warnings into stored memories
  • load relevant memories at next session start

An alternative to claude-mem.

How pickfit tested it

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

macOS arm64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 1.10.1

An MCP client handshake over stdio listed 15 tools, and a call to storeMemory returned a result.

Differences the test machine hit

  • README: npm install -g sessionmem without allowScripts warning
    In the test: better-sqlite3 prebuild warning appears but install still succeeds and sessionmem --version works
  • README: sessionmem doctor expects PASS
    In the test: doctor fails on auto-start, store and checkpoint until sessionmem ping initializes DB and autostart enabled
  • README: ingestSessionEvents example informal
    In the test: tool requires events with id, eventType, payloadJson (JSON string) not tool/input shape

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 1.10.1

An MCP client handshake over stdio listed 15 tools, and a call to startup_inject_memories returned a result.

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.