Pi Agent

Add persistent memory to Pi Agent with @mem0/pi-agent-plugin. Your agent forgets everything between sessions. This plugin fixes that by automatically capturing knowledge from conversations, storing it in Mem0’s cloud memory layer, and retrieving relevant context before every response.

Current package version: 0.3.0.

Sidekick is available only in the Claude Code plugin.

Overview

The plugin provides:

Auto-capture: Extracts durable facts from both user and assistant messages automatically
Semantic recall: Automatically searches project memories before each agent turn; mem0_memory supports additional explicit searches
Monorepo-aware scoping: Uses git root for project detection, consistent across subdirectories
Confirmation dialogs: Destructive commands ask before acting via Pi’s built-in UI
6 skills + 6 commands: Essential memory management from slash commands and agent-guided workflows

Prerequisites

A Mem0 Platform account and API key:
- Sign up at app.mem0.ai
- Get your API key (starts with m0-)
Pi Agent installed (pi.dev)
Your API key added to your shell profile:

echo 'export MEM0_API_KEY="m0-your-api-key"' >> ~/.zshrc
source ~/.zshrc

echo 'export MEM0_API_KEY="m0-your-api-key"' >> ~/.bashrc
source ~/.bashrc

Installation

pi install npm:@mem0/pi-agent-plugin

That’s it. The extension loads automatically on every Pi session. No config files needed: MEM0_API_KEY from your environment is picked up automatically.

Start a new Pi session and run /mem0-status to verify the connection. You should see your user ID, detected project, and memory count.

Optional Configuration

For advanced settings, create ~/.pi/agent/mem0-config.json:

{
  "apiKey": "m0-your-key-here",
  "userId": "your-username",
  "autoCapture": true,
  "defaultScope": "project",
  "searchThreshold": 0.3
}

Key	Type	Default	Description
`apiKey`	`string`	`$MEM0_API_KEY`	Mem0 API key. Environment variable takes precedence.
`userId`	`string`	`$MEM0_USER_ID` or `"default"`	User identity for memory scoping
`autoCapture`	`boolean`	`true`	Store facts from conversations automatically
`defaultScope`	`string`	`"project"`	Default memory scope: `project`, `session`, or `global`
`searchThreshold`	`number`	`0.3`	Minimum similarity score (0–1) a memory must reach to count as a match for `/mem0-search` and `/mem0-forget`, enforced on each result’s relevance score. Raise it to be stricter; lower it if relevant results are missed.

What’s Included

Component	Description
`mem0_memory` tool	Agent-callable tool for search, add, get_all, delete, delete_all
6 slash commands	Essential memory management from the command line
6 skills	Guide the agent on how to use each capability
Auto-capture	Extracts and stores facts on every `agent_end` event
System prompt	Appends memory policy to every agent turn

Agent Tool

The mem0_memory tool is registered with Pi and callable by the agent during conversations:

Action	Required Params	Description
`search`	`query`	Semantic search across memories
`add`	`content`	Store a new memory
`get_all`	N/A	List all memories in scope
`delete`	`memory_id`	Delete a specific memory
`delete_all`	N/A	Delete all memories in scope

All actions accept an optional scope parameter: project (default), session, or global. Tool output is truncated to 200 lines / 50KB to prevent context overflow.

Commands

Command	Description
`/mem0-remember <text>`	Store a memory verbatim (no inference)
`/mem0-forget <query>`	Search and delete memories (with confirmation dialog)
`/mem0-search <query>`	Semantic search across memories
`/mem0-tour [scope]`	Browse all memories grouped by category
`/mem0-scope <scope>`	Change default scope for this session (project, session, global)
`/mem0-status`	Connection health, identity, and memory count

Memory Scopes

Memories are scoped using Mem0’s user_id, app_id, and run_id parameters:

Scope	Filters	Use Case
`project`	user_id + app_id (git root)	Default. Project-specific knowledge: decisions, architecture, config
`session`	user_id + app_id + run_id	Memories saved with the current session ID (no automatic expiration)
`global`	user_id only	All memories across all your projects

The app_id is auto-detected from the git repository root (git rev-parse --show-toplevel), so all subdirectories within a monorepo share the same memory pool. Falls back to the working directory name for non-git directories. The run_id is derived from Pi’s session file path. Automatic recall and capture use project scope, regardless of defaultScope; automatic writes do not include run_id. Use session-scoped tools or commands to save and recall session-specific memories. Captured user and assistant message text is redacted without a per-message character cutoff. Global tool operations require /mem0-scope global or defaultScope: "global" in plugin configuration. A model-supplied scope argument cannot enable cross-project access on its own. Empty or wildcard user, project, and session identities are rejected.

Confirmation Dialogs

Destructive and mutating commands use Pi’s built-in ctx.ui.confirm() dialog before acting:

/mem0-forget asks “Delete this memory?” before deleting a single match
Cancelling the operation is always safe. No changes are made.

Example Workflow

# Session 1
You: I prefer dark mode and concise answers.
# Mem0 auto-captures preferences

# Session 2 (days later)
You: What do you know about my preferences?
# Pi retrieves stored memories, no re-explaining needed

Troubleshooting

“No API key found”: Verify MEM0_API_KEY is set: echo $MEM0_API_KEY. If empty, add it to your shell profile (see Prerequisites)
Extension not loading: Check Pi startup output for errors. For a source checkout, run pnpm build, then pi -e ./dist/entry.js from the plugin directory
Memories not capturing: Verify autoCapture is true (default). Check /mem0-status for connection health
Wrong project detected: The plugin uses the git repository root as app_id. If not in a git repo, it falls back to the working directory name. Run /mem0-status to see the detected project

Claude Code Integration

Add Mem0 memory to Claude Code

OpenClaw Integration

Add Mem0 memory to OpenClaw agents

Using Mem0? Star us on GitHub to help more developers discover memory for AI apps.

Coding Agents

Agent Harness

Overview

Prerequisites

Installation

Optional Configuration

What’s Included

Agent Tool

Commands

Memory Scopes

Confirmation Dialogs

Example Workflow

Troubleshooting

Claude Code Integration

OpenClaw Integration

​Overview

​Prerequisites

​Installation

​Optional Configuration

​What’s Included

​Agent Tool

​Commands

​Memory Scopes

​Confirmation Dialogs

​Example Workflow

​Troubleshooting

Claude Code Integration

OpenClaw Integration

Overview

Prerequisites

Installation

Optional Configuration

What’s Included

Agent Tool

Commands

Memory Scopes

Confirmation Dialogs

Example Workflow

Troubleshooting