Install Project Memory

Pick your client, copy the command, done.

Add it to Claude Code

claude mcp add -e "HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN}" -e "GROQ_API_KEY=${GROQ_API_KEY}" project-memory -- docker exec -i project-memory-mcp python -m src.mcp_server.server

Required:HUGGINGFACE_TOKENGROQ_API_KEY+ 1 optional

Environment Variables

Set these before running Project Memory.

VariableDescriptionRequired

HUGGINGFACE_TOKENToken for pyannote diarization serviceYes

GROQ_API_KEYAPI key for Groq (Whisper and Qwen models)Yes

GOOGLE_API_KEYAPI key for Google AI Studio fallbackNo

Available Tools (5)

Once configured, Project Memory gives your AI agent access to:

get_contact_summaryProvides a complete summary of a specific contact.

contact_id

query_conversationsPerforms semantic search within the conversation history.

query

add_reminderCreates a new reminder.

reminder_textdue_date

get_pending_remindersRetrieves a list of upcoming reminders.

list_contactsLists all contacts in the CRM.

Try It Out

After setup, try these prompts with your AI agent:

→Summarize my recent conversations with John to see what we discussed about the project.

→Search my WhatsApp history for any mentions of meeting times or deadlines.

→What are my pending reminders for this week?

→List all my contacts currently stored in the CRM.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Docker installed and running
HUGGINGFACE_TOKEN — Token for pyannote diarization service
GROQ_API_KEY — API key for Groq (Whisper and Qwen models)

Conare · memory for coding agents

Keep this setup from going cold

Save the docs, env vars, and workflow around Project Memory in Conare so Claude Code, Codex, and Cursor remember it next time.

Remember this setup$npx conare@latest

← Project Memory overview Browse ai-tools servers →