pickfit

BrowseMCP servers

Agent Memory Bridge

Local MCP memory layer that stores confirmed project decisions for recall across sessions.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python 3.11+
  • System packages: Git
  1. Install via uv tool install agent-memory-bridge==0.38.2

    uv tool install agent-memory-bridge==0.38.2
Where the README and reality differ
  • README: pip install agent-memory-bridge==0.38.0 (README current version 0.38.0)
    What worked: 0.38.2 is latest available; use uv tool install agent-memory-bridge==0.38.2 to avoid PEP 668
  • README: store example implies kind decision
    What worked: store tool validates kind literal 'memory' or 'signal' – use kind=memory and embed reason in content

Check that it works

agent-memory-bridge --version

The output should contain “0.38.2”.

Add it to your agent

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

Add agent-memory-bridge as an MCP server in your MCP client, then call its tools such as store and recall from your agent.

What it does

  • Store project decisions with their reasons
    How to use it
    1. From your MCP client, call the store tool with a namespace such as project:<name>, kind set to memory, and content holding the decision and its reason.
    Tested
  • Recall decisions and reasons in later sessions
    How to use it
    1. In a new session, call the recall tool with the same namespace and a query in plain words, such as <your question>.
    Tested
  • See why a piece of information came up
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • store a confirmed project decision with reason
  • recall stored decisions at start of next session

How pickfit tested it

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

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.38.2

An MCP client handshake over stdio listed 17 tools, and a call to store returned a result.

Differences the test machine hit

  • README: Launch with <venv-python> -m agent_mem_bridge
    In the test: uv tool provides executable agent-memory-bridge which speaks stdio MCP directly; use AGENT_MEMORY_BRIDGE_HOME to isolate state

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.