Memroam

Your memory shouldn't be locked to one model. Memroam gives every AI agent you use — Claude Code, Codex, Cursor, ChatGPT, and friends — one shared, portable memory: teach a convention in one harness, switch to another mid-task, and it picks up exactly where you stopped. No database, no embeddings: plain Markdown files you own, wired to every agent over MCP with one command. Your memory roams with you.

Memroam stores facts as ordinary Markdown files. Each project gets an isolated memory space, while shared/ holds facts that apply across projects. The files stay on your machine (or in your own GitHub repository with the hosted tier) and remain fully usable if you change models or agent harnesses — that's the point.

How it works

The MCP server gives an agent six file operations — view, create, str_replace, insert, delete, and rename — plus search, a vault-wide keyword search over frontmatter and bodies.

The agent writes small memory files; each space's MEMORY.md index is generated by the server from the files' frontmatter after every change (editing it directly is refused). Every new memory gets an immutable UUIDv7 id: stamped at creation, and create refuses to replace an existing file unless told to overwrite. There is no database or embedding model. The Markdown files are the source of truth, so you can read, edit, grep, or version them yourself.

memory/
  MEMORY.md          # index of project spaces
  shared/
    MEMORY.md        # cross-project facts
    *.md
  <project>/
    MEMORY.md        # project index
    *.md

A project connection reads and writes its own space by default, but the whole vault stays visible — other spaces are addressable by path, and the root listing shows every space. Scope is a routing default, not a wall. An unscoped connection starts at the vault root for cross-project maintenance.

Related MCP server: auxly-memory-cli

Requirements

• Node.js 18 or newer

• An MCP client that supports stdio (global install) or Streamable HTTP (per-repo install)

Memroam has no runtime dependencies.

Install globally (recommended)

Wire every harness on your machine once:

npx -y memroam install --global

For each detected harness this writes a user-level stdio MCP registration and the memory ritual in its global rules file — Claude Code (~/.claude.json + ~/.claude/CLAUDE.md), Cursor (~/.cursor/mcp.json), Codex (~/.codex/config.toml + ~/.codex/AGENTS.md), DeepSeek Harness (~/.dsh/AGENTS.md + a stdio mount in every profile's cordis.patch.yml), OpenCode (~/.config/opencode/opencode.json + AGENTS.md), Gemini CLI (~/.gemini/settings.json + ~/.gemini/GEMINI.md), and Antigravity (~/.gemini/config/mcp_config.json + an always-on rule in ~/.gemini/config/rules/). After that, every session in every repository gets the vault with no per-repo setup: the harness spawns memroam stdio in the session's directory, and the server derives the project space from that directory automatically (the nearest .git, else the shallowest package manifest; no marker means the default space). The rule is the same for every harness: a MEMORY_SPACE env var on the server entry pins the space explicitly, else the client's MCP workspace roots name it (for harnesses that spawn MCP servers outside the session directory), else the directory decides. Detected spaces are recorded in ~/.memory-vault-connections.json so they stay stable.

npx -y memroam install --global --dry-run        # preview changes
npx -y memroam install --global --store <dir>    # choose the store (default ~/.memroam)
npx -y memroam uninstall --global                # undo exactly what install wrote

Restart your sessions after installing. Per-repo install (below) remains for team-shared, committed configs or a custom space name. Existing ~/.memory-vault stores from earlier releases are detected and kept — nothing moves without you.

Install into a repository

Run this from the repository you want to connect:

npx -y memroam install

This command:

1. Starts the local server if it is not already running.

2. Asks which harnesses to wire up, with the detected ones pre-selected (interactive terminals only — everywhere else the detected set is used as is).

3. Writes each chosen harness's MCP config and the shared rules files.

By default, install stores memory in ~/.memroam (an existing ~/.memory-vault is honored) and derives the project name from the current directory. connect is an alias for install.

npx -y memroam install --dry-run                # preview changes
npx -y memroam install --project my-app         # choose the project name
npx -y memroam install --harness claude,codex   # skip the prompt, pick explicitly
npx -y memroam install --yes                    # skip the prompt, accept detected

Restart your agent session after installing and approve the vault MCP server if prompted.

Uninstall from a repository

npx -y memroam uninstall

Removes everything install wrote to the repository — the MCP entries, the rules sections, the dsh patch — deleting a file only when it held nothing else. Your memories are never touched, and the server keeps running for other projects. disconnect is an alias for uninstall.

Check the wiring

npx -y memroam status

Shows whether the server is up and which store it serves, how the current repository is wired per harness, and every repository recorded by install (kept in ~/.memory-vault-connections.json). If the server is up and the repo is wired but your agent session has no vault tools, the remaining cause is session attachment — status prints how to fix it.

Import native memory, project to memoryless harnesses

npx -y memroam import     # Claude Code auto-memory + Codex sqlite → candidates/
npx -y memroam project    # regenerate the read-only shared/ block in dsh's AGENTS.md

import copies each harness's native memory into the matching space's candidates/ directory — searchable and labeled [candidate], excluded from the index, never written into canonical memory automatically. The Codex reader is read-only and refuses unknown database schema versions. Both commands print a capability report of what they can and cannot move, and take --dry-run / --json.

Supported harnesses

For DSH, start a session with the generated patch:

dsh --patch ./dsh-cordis.patch.yml --profile headless "your task"

Hosted tier

The hosted tier is the same server run for you: a remote MCP endpoint secured with OAuth 2.1, storing your memories as commits in a private GitHub repository you own. Connect it to Claude (claude.ai custom connector), ChatGPT (custom connector via the OpenAI search/fetch contract), Codex, or any remote-MCP client:

https://memroam.com/mcp

Every memory is a markdown file in your repo — clone it, grep it, take it anywhere. Losing access to the hosted tier never means losing your memory.

Run the server directly

MEMORY_DIR=~/.memroam npx memroam

The server listens on 127.0.0.1:8787 by default.

From a cloned repository, npm start runs the same server.

MCP endpoints

POST /mcp/<project>  project memory plus shared memory
POST /mcp            whole-vault access

For example, a manual Claude Code connection is:

claude mcp add --transport http --scope project vault http://localhost:8787/mcp/my-project

Memory format

Store one durable fact per Markdown file:

---
name: preferred-language
description: The project's preferred implementation language
---

Use TypeScript for new application code.

The server stamps an id: and regenerates the space's MEMORY.md index line from the description: automatically. It instructs agents to check for an existing memory before creating one, update facts instead of duplicating them, and remove memories that become incorrect.

Current scope

The current release is a Markdown store (local folder or hosted GitHub-backed), an MCP interface with keyword search, OAuth 2.1 on the hosted tier, a cross-harness setup command, and one-shot import/projection adapters. There is no automatic extraction, semantic search, or automated deduplication.

Package

• npm: memroam (formerly memory-vault)

• MCP registry: com.memroam/memroam

• License: MIT