PMB AI

listing.by

Give AI coding agents persistent local memory for decisions, lessons and facts, stored in a single SQLite file on your disk.

state.local.long (state.local.title)listing.badge.runs_with

listing.install

listing.local.explain

uvx pmb-ai

listing.local.needs listing.local.note

act.add_to a11y.new_tabact.add_to a11y.new_tab

listing.share.h

listing.share.p_local

mcp.tc/i/pmb-ai

listing.about

PMB stores decisions, lessons, personal facts, project structure and indexed PDFs in a local workspace, with SQLite as the source of truth and LanceDB search indexes beside it. Agents such as Claude Code, Cursor and Codex read it back over MCP. The prepare tool returns project context, lessons, recent activity and open goals for a message, and recall runs hybrid search (BM25, vector, graph, rerank). The README mentions 27 other tools.

It runs locally over stdio as the PyPI package pmb-ai, started with uvx. No account, API key or cloud service is needed, and the README says nothing leaves your machine. A pmb setup command detects your agent and writes the MCP entry, and a local dashboard is available on 127.0.0.1.

listing.can

  • Recall past decisions and lessons across agent sessions
  • Fetch project context, open goals and recent activity with prepare
  • Hybrid search over memory with recall
  • Record keyed personal facts that keep old values archived
  • Index project code structure and PDFs for later retrieval
  • Browse memory in a local dashboard on 127.0.0.1
  • Export all stored memory to Markdown or JSON

listing.tools

listing.notools.local

listing.prompts

  • Fix that pricing bug we hit last Tuesday, using what you remember about it.

  • Recall our earlier decision about the auth approach.

  • Remember that this project must never lower the threshold under 25%.

  • Index the PDF paper.pdf so you can answer questions about it later.

listing.setup.h

listing.setup.local

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio pmb-ai -- uvx pmb-ai
  1. Start Claude Code and type /mcp. pmb-ai should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Add to Cursor a11y.new_tab

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}

Needs uv (Python) on your computer.

VS Code

Install in VS Code a11y.new_tab

Or from a terminal:

code --add-mcp '{"name":"pmb-ai","type":"stdio","command":"uvx","args":["pmb-ai"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "pmb-ai": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add pmb-ai -- uvx pmb-ai

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.pmb-ai]
command = "uvx"
args = ["pmb-ai"]

Needs uv (Python) on your computer.

Gemini CLI

gemini mcp add pmb-ai uvx pmb-ai

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer.

listing.faq

Can I paste mcp.tc/i/pmb-ai into my MCP client?

No. PMB AI runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx pmb-ai.

Does PMB AI need an API key?

No. It doesn't declare any keys or environment variables. It runs with your user account's permissions, so check what its tools can reach.

Is PMB AI a remote or a local server?

Local. Your client starts it as a process on your computer with uvx pmb-ai, which needs uv (Python).

What can PMB AI do?

You can recall past decisions and lessons across agent sessions, fetch project context, open goals and recent activity with prepare and hybrid search over memory with recall.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc's robot read PMB AI's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead_local listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![PMB AI on mcp.tc](https://mcp.tc/i/pmb-ai/badge.svg)](https://mcp.tc/i/pmb-ai)
HTML
<a href="https://mcp.tc/i/pmb-ai"><img src="https://mcp.tc/i/pmb-ai/badge.svg" alt="PMB AI on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/pmb-ai.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/pmb-ai" title="PMB AI on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json_local

https://mcp.tc/i/pmb-ai.json

listing.em.fields

listing.related

listing.more_in

  • memo

    jagoff

    state.local.label (state.local.title)

    Keep persistent, searchable memory for coding agents, stored as Markdown and run entirely on your own machine.

    mcp.tc/i/memo

  • screenpipe

    AI & Machine Learning

    state.local.label (state.local.title)

    Search your local screen recordings, audio transcripts and computer activity captured by screenpipe.

    mcp.tc/i/screenpipe

  • MCP Memory Service

    doobidoo

    state.local.label (state.local.title)

    Store and search persistent semantic memory with a knowledge graph, shared across agents, sessions and AI clients.

    mcp.tc/i/mcp-memory-service

  • MiniMax

    AI & Machine Learning

    state.local.label (state.local.title)

    Generate speech, clone voices, and create images and videos with MiniMax models from your AI assistant.

    mcp.tc/i/minimax

  • Sequential Thinkingvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Work through problems as a sequence of thoughts that can be revised, branched and extended as understanding grows.

    mcp.tc/i/sequential-thinking

  • Memoryvf.sr

    MCP reference servers

    state.local.label (state.local.title)

    Store and recall persistent memory across sessions using a local knowledge graph.

    mcp.tc/i/memory

listing.disclaimer_checked