mcpField
P
purmemo

purmemo

Local
github.com/purmemo-aiMemory & Knowledge2Updated 4d ago

About purmemo

pūrmemo is a memory service for AI tools that carries user context and saved conversations across sessions. It offers MCP tools for saving, searching, and recalling memories, plus dated change history for people and projects.

Key features

  1. 01Save and search conversation memories
  2. 02Load user and project context
  3. 03View dated changes to people and projects
  4. 04Connect with MCP-compatible tools

Use cases

  1. 01Recall a decision from an earlier conversation
  2. 02Load ongoing work at the start of a session
  3. 03Check how details about a project changed over time

MCP support

The MCP server exposes tools to save conversations, recall memories, retrieve details, inspect changes, and load user context. It can be connected as a hosted Streamable HTTP server or run locally through the connector.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"purmemo-ai-purmemo": {
"command": "npx",
"args": [
"-y",
"purmemo-mcp"
]
}
}
}
Run commandnpx -y purmemo-mcp

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
npmpurmemo-mcp12.9.5

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
tagsarrayNoTags for categorization
titlestringNoTitle for this conversation memory
priorityenumNoPriority level for this memorylow | medium | high
conversationIdstringNoOptional unique identifier for living document pattern. If provided and memory exists with this conversationId, UPDATES that memory instead of creating new one. Use for maintaining single memory per conversation that updates over time.
conversationContentstringYesCOMPLETE conversation transcript - minimum 500 characters expected. Include EVERYTHING discussed.

Details

From the project README

pūrmemo

npm version npm downloads Tests License: MIT

Memory for your AI tools. Claude remembers who you are, what you're working on, and what you said last time — across every session, on every platform.

Just want it in ChatGPT or Claude.ai in your browser? Get the Chrome Extension instead.


Install in 30 seconds

1. Paste this into your terminal

Mac or Linux:

curl -fsSL https://app.purmemo.ai/install | sh

Windows (PowerShell):

irm https://app.purmemo.ai/install.ps1 | iex

That's it for installing. The script handles everything — it'll install Node if you don't have it, set up the purmemo command, and tell you when it's done.

2. Type purmemo
purmemo

Your browser opens. Sign in (or create a free account). Close the tab when it says you're done.

3. Restart Claude

Quit and reopen Claude Desktop (or Claude Code). pūrmemo is now connected.

You'll know it worked when your next Claude session opens with a header like:

pūrmemo v15.7.20 · [email protected] · Free · 0 memories

Try saying "save this" at the end of a conversation, or "what was I working on?" at the start of a new one.


If something goes wrong

purmemo command not found? Close and reopen your terminal, then try again. New commands sometimes need a fresh shell.

You see "Failed to read token" or "bad decrypt"? Run:

purmemo --update && purmemo init

This clears any stale credentials and signs you back in. (Fixed in v15.7.20+ — if you're on an older version, this is a one-time thing.)

Anything else? Open an issue at github.com/purmemo-ai/purmemo-mcp/issues — we read every one.


What it does

  • Remembers everything — save any conversation, recall it later by typing what you remember about it.
  • Knows who you are — your role, your projects, your stack — loaded automatically into every new session.
  • Tells you what changed — ask what_changed about a person, project, or thing and get its dated history: what used to be true, what replaced it, and when.
  • Works everywhere — Claude Code, Claude Desktop, Cursor, Windsurf, Zed, anything that speaks MCP.

Three slash commands you'll use most:

You typeWhat happens
/saveSaves this conversation. Use the same title later → updates the same memory.
/recall <topic>Search your memories in plain English.
/contextAt the start of a session — loads who you are and what you were last working on.

Other ways to install

I already have Node.js
npm install -g purmemo-mcp && purmemo

Or, run it once without installing globally:

npx purmemo-mcp@latest init
Claude Desktop — hosted (recommended, no setup)

Open Claude Desktop → Settings → Developer → Edit Config and add:

{
  "mcpServers": {
    "purmemo": {
      "url": "https://mcp.purmemo.ai/mcp/messages",
      "transport": "streamable-http"
    }
  }
}

Restart Claude Desktop. You'll be prompted to sign in via OAuth on first use.

Claude Desktop — local (advanced)

Get your API key from app.purmemo.ai → Settings → API Keys, then edit:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "purmemo": {
      "command": "npx",
      "args": ["-y", "purmemo-mcp"],
      "env": { "PURMEMO_API_KEY": "your-api-key-here" }
    }
  }
}

Restart Claude Desktop after saving.

Cursor / Windsurf / Zed

Cursor — edit ~/.cursor/mcp.json:

{ "mcpServers": { "purmemo": { "command": "npx", "args": ["-y", "purmemo-mcp"], "env": { "PURMEMO_API_KEY": "your-api-key" } } } }

Windsurf — edit ~/.codeium/windsurf/mcp_config.json (same shape as above).

Zed — edit ~/.config/zed/settings.json, add under context_servers:

{ "context_servers": { "purmemo": { "command": { "path": "npx", "args": ["-y", "purmemo-mcp"], "env": { "PURMEMO_API_KEY": "your-api-key" } } } } }

Pricing

PlanPriceRecallsSaves
Free$050/monthUnlimited
Pro$19/monthUnlimitedUnlimited

For developers

Looking for the technical stuff? It's all here:

  • Tools listed by default — five: save_conversation, recall_memories, get_memory_details, what_changed, get_user_context. A short list helps the assistant pick the right tool. Env flags add more:
    • PURMEMO_SESSIONS_BETA=1 — adds search_past_sessions (beta): searches the raw transcripts of your past AI sessions for what was actually said or decided. Served by purmemo-next at PURMEMO_READ_BASE_URL, else PURMEMO_SESSIONS_URL, else https://next.purmemo.ai.
    • PURMEMO_ADMIN=1 — adds the admin tools (get_acknowledged_errors, save_investigation_result, get_investigations).
    • PURMEMO_LEGACY_TOOLS=1 — brings back the paused tools (save_artifact, commit, the snapshot tools, list_clusters, discover_related_conversations, run_workflow, list_workflows, sharing, tasks, test results and the rest). Called while paused, they answer with what to use instead.
  • Several accounts on one machine (e.g. personal and work, each connected with purmemo-mcp-setup add). The server still starts on your active account, and that stays the default for every call, hook and auto-capture. When two or more accounts are signed in locally, the core tools gain an optional account argument (a choice among those signed-in accounts only; anything else is refused before any network call) and transfer_memory is listed, which moves one memory between your accounts. Calls on a non-default account are labelled with the account and logged, without content or keys, to ~/.purmemo/account-audit.jsonl. Programs use the same boundary through purmemo-ops (accounts, whoami, save, recall, transfer), which always requires an explicit account. Hosted (remote) mode never offers it; PURMEMO_MULTI_ACCOUNT=0 turns it off. See ADR-040.
  • Tools, resources, prompts reference — every MCP tool the server can expose, including the paused ones.
  • Living document semantics — mode='append' vs mode='replace', chunking behavior, ADR-036/038 details.
  • Identity layer — the cognitive fingerprint that loads into every session.
  • Architecture decisions (ADRs) — every design decision, with context and trade-offs.
  • Source for the install scripts — read before running, if you want.

Links


License

The MCP connector code in this repo is MIT licensed. The pūrmemo platform, API, and backend are proprietary.

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.