OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Pmb

Pmb is a Python command-line tool that stores persistent memory for AI coding agents in a local SQLite database and exposes it through MCP.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pmb — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pmb when you want a coding agent to carry project context between sessions using memory stored on your machine.

Who it is for

  • Developers who want coding-agent decisions, lessons and facts to persist between sessions.
  • Users of MCP-aware agents, including the named environments Claude Code, Cursor and Codex.

Documented uses

  • Keep project decisions and lessons available after an agent restart.
  • Let an MCP-connected coding agent retrieve relevant project context.
  • Check or search stored memory from the terminal.
Before you choose

Requirements & limits

The README describes a pip installation and states that the workflow requires no account or API keys. The project is licensed under Apache-2.0.

  • Pmb uses a local SQLite file as its durable source of truth.
  • Agent access is through MCP; the README names Claude Code, Cursor and Codex.
  • The documented quickstart uses Python packaging and a command-line setup step.
  • The README documents terminal memory search and a local dashboard.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Pmb and configure an MCP connection

Install the package and use Pmb's setup command to detect an agent and wire its MCP entry.

Before you start

  • Python package installer, as the documented installation uses pip
  • An MCP-aware coding agent; Claude Code, Cursor and Codex are named examples

Steps

  1. Install the package with the command below.

    Documented command
    pip install pmb-ai

  2. Run pmb setup to detect an agent and configure the MCP entry.

  3. Restart the agent.

Expected outcome

Pmb is installed and the agent can use the configured MCP connection to access local memory.

Guide limitations

  • The quickstart does not give agent-specific configuration instructions.
  • The source names supported agent environments but does not include an integration test.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
PmbKeep project decisions and lessons available after an agent restart.CLI, Self-hostedThe README describes a pip installation and states that the workflow requires no account or API keys. The project is licensed under Apache-2.0.
Continuum — pouyahasanamrejiStore project lessons so coding agents can retrieve them across conversations.CLI, Self-hosted, ServerThe repository documents local Docker Compose and bare-metal development setups. Bare-metal startup requires Node 22.12.0 or later and pnpm 10.33 or later; the Compose path skips these host prerequisites.
HaftRecord the problem a project is solving and the options considered.CLI, Self-hosted
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
oleksiijko/pmb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction