mcpField
O
OpenMem

OpenMem

Local
github.com/bcmyguestOther0Updated today
Repository

About OpenMem

OpenMem provides coding agents with a stable memory API backed by pluggable providers such as Hindsight, mem0, or Cognee. A shared wizard, indexer, and PMM import/export format support setup and portability.

Key features

  1. 01Unified `memory_*` interface
  2. 02Pluggable memory providers
  3. 03Shared setup wizard and indexer
  4. 04PMM memory import and export
  5. 05CLI commands for provider management

Use cases

  1. 01Give coding agents access to project memory
  2. 02Switch memory providers while managing content separately
  3. 03Import or export portable memory

MCP support

OpenMem runs an MCP server that exposes its unified `memory_*` interface to coding agents. Optional native or NotebookLM servers are also noted.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "bcmyguest-openmem": {
      "command": "npx",
      "args": [
        "-y",
        "@bcmyguest/openmem"
      ],
      "env": {
        "MEMORY_PROVIDER": "<MEMORY_PROVIDER>",
        "PM_STACK_ROOT": "<PM_STACK_ROOT>"
      }
    }
  }
}
Run commandnpx -y @bcmyguest/openmem
Environment variables to set
MEMORY_PROVIDERActive backend: hindsight (default), mem0, or cognee
PM_STACK_ROOTOpenMem stack directory (compose project, .env)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@bcmyguest/openmem0.6.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

OpenMem

npm version License openmem-mcp GitHub

openmem-mcp

OpenMem is a memory interface for coding agents: a stable memory_* API over pluggable memory providers, with a shared wizard, indexer, and import/export format (PMM first).

Docs: bcmyguest.github.io/openmem/

MCP: npx -y -p @bcmyguest/openmem openmem-mcp

Start here: Concepts · Quickstart

Quickstart

StepCommand
1. Wizardnpx @bcmyguest/openmem
2. Checknpx @bcmyguest/openmem doctor
3. Coding agentsnpx @bcmyguest/openmem install-coding-agent --yes

Checkout instead of npx:

git clone https://github.com/bcmyguest/openmem.git && cd openmem
npm install && npx . setup

Needs: Docker Compose v2, Node ≥ 20.12, and an LLM route if you use Hindsight (lemond, Ollama, or OpenAI-compatible — set in the wizard).

Later: npx @bcmyguest/openmem up / down / switch <provider> --yes / doctor.

Wizard dry-run (what first setup plans — no writes):

Setup dry-run: npx @bcmyguest/openmem setup --dry-run

Full guide: Quickstart · Concepts · Architecture

Architecture

flowchart LR
  S[Git repos · notes · feeds] --> I[OpenMem indexer]
  I --> P[(One active memory provider)]
  A[Coding agents] <--> M["OpenMem MCP · memory_*"]
  M <--> P

The indexer and coding agents share one active memory provider. Session hooks use the same memory_* MCP. See the full architecture for setup, optional integrations, and provider-specific behavior.

Providers and portability

  • Providers — Provider status lists every provider and its support level from the manifests. Contributor details: adding a provider.
  • MCP — unified memory_* plus optional native/NotebookLM servers: MCP setup.
  • Portable memory — memory_export / memory_import speak PMM: Portable memory.
  • Switch — npx @bcmyguest/openmem switch <provider> does not migrate data by itself; export/import (or re-index) moves content.

Default Hindsight compose: litellm, hindsight (127.0.0.1:8888), indexer. mem0/Cognee stacks omit LiteLLM unless you add them separately.

Inspiration and related

OpenMem is not affiliated with these projects; they shape the problem or the pattern.

OpenFeatureInspiration for a vendor-agnostic interface + pluggable providers (there: feature flags; here: coding-agent memory).
mise / asdfOne CLI over many backends; declarative config and tasks without replacing each tool’s own settings.
LiteLLMModel proxy used on Hindsight stacks.

More setup analogues: Pluggable memory providers.

Formerly personal-memory. Use the openmem CLI and MCP server name; installers drop the old personal-memory MCP entry.

License

Apache License 2.0 — see LICENSE (Copyright 2026 B Guest).

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.