Skip to main content

Personal memory system for AI coding agents — offline, zero API keys, cross-agent handoffs, semantic search

Project description

myMem0ry

Personal memory for AI coding agents. Offline. Zero API keys. Works with any agent.

CI Publish PyPI Python License: MIT


Persistent memory that any AI agent can read and write. Quit Claude Code mid-task, open Codex in the same directory — it picks up where you left off.

Features

  • Scoped memory — session → context (branch) → project → global, resolved automatically from cwd
  • Cross-agent handoffs — typed records with summary, open questions, next steps
  • Semantic search — spaCy + sqlite-vec + BM25/FTS5/hybrid RRF fusion
  • Lifecycle hooks — fire-and-forget HTTP endpoint, payload sanitization, immutable observations
  • Zero LLM tokens for writes — bulk writes (conversation archiving, logging) via hooks only
  • Retention — salience-based decay with tiers (working/procedural/semantic), pin/unpin
  • Auth — Bearer token, host allowlisting, CORS
  • Web UI — dark mode read-only viewer (dashboard, projects, search, audit log)
  • Backup/restore — tarball CLI commands
  • Multi-agent — Claude Code, OpenCode, Codex, Cursor, Gemini CLI, VS Code, Docker

Install

pip install uv        # or: curl -LsSf https://astral.sh/uv/install.sh | sh
uv tool install mymem0ry
mymem0ry doctor       # checks + auto-installs spaCy model

For Portuguese: set SPACY_MODEL=pt_core_news_lg in .env before running mymem0ry doctor.

Zero config: after install, just add the MCP server + hooks to your agent config below. The HTTP server auto-starts when the MCP server runs — no separate serve command needed.

Agent Setup

Claude Code

claude mcp add --scope user mymem0ry -- mymem0ry-mcp

MCP + hooks in ~/.claude/settings.json:

{
  "mcpServers": {
    "mymem0ry": {
      "type": "stdio",
      "command": "mymem0ry-mcp"
    }
  },
  "hooks": {
    "SessionStart": [
      {
        "matcher": "",
        "hooks": [{"type": "command", "command": "~/.local/share/mymem0ry/hooks/claude-code/session-start.sh"}]
      }
    ],
    "SessionEnd": [
      {
        "matcher": "",
        "hooks": [{"type": "command", "command": "~/.local/share/mymem0ry/hooks/claude-code/session-end.sh"}]
      }
    ]
  }
}

OpenCode

Add to ~/.config/opencode/opencode.json (global) or ./opencode.json (project):

{
  "mcp": {
    "mymem0ry": {
      "type": "local",
      "command": ["mymem0ry-mcp"],
      "enabled": true
    }
  },
  "hooks": {
    "session-start": "curl -s -m 2 -X POST http://127.0.0.1:49374/hook -H 'Content-Type: application/json' -d '{\"kind\":\"session-start\",\"session_id\":\"'$OPENCODE_SESSION_ID'\",\"agent\":\"opencode\",\"cwd\":\"'$PWD'\"}' > /dev/null 2>&1",
    "session-end": "curl -s -m 2 -X POST http://127.0.0.1:49374/hook -H 'Content-Type: application/json' -d '{\"kind\":\"session-end\",\"session_id\":\"'$OPENCODE_SESSION_ID'\",\"agent\":\"opencode\",\"cwd\":\"'$PWD'\"}' > /dev/null 2>&1"
  }
}

Codex CLI

codex mcp add mymem0ry -- mymem0ry-mcp

VS Code

code --add-mcp '{"name":"mymem0ry","command":"mymem0ry-mcp"}'

Cursor

cursor --add-mcp '{"name":"mymem0ry","command":"mymem0ry-mcp"}'

Gemini CLI

Same stdio pattern. Add to Gemini CLI MCP config with command: mymem0ry-mcp.

Docker

docker compose -f docker/docker-compose.yml up -d
curl http://127.0.0.1:49374/health

For detailed per-agent instructions: docs/install.md

Lifecycle Hooks

Hooks POST lifecycle events to POST /hook on the myMem0ry HTTP server. The server auto-starts when the MCP server runs — no manual serve step needed.

Agent Hooks How
OpenCode Native hooks in opencode.json with $OPENCODE_SESSION_ID
Claude Code Native hooks in ~/.claude/settings.json — scripts receive full payload via stdin
Codex CLI Hook scripts codex hook add session-end ./hook-session-end.sh
Generic Manual curl -X POST http://127.0.0.1:49374/hook ...

Hook payload fields:

Field Required Description
kind yes session-start, session-end, log, user-prompt, post-tool-use, pre-compact
session_id yes Unique session identifier (max 64 chars)
agent no opencode, claude-code, codex, manual, hook
cwd no Working directory for context resolution
title no Short label (max 500 chars)
body no Content (max 10,000 chars)
messages no `[{"role": "user"

All payloads are sanitized: secrets redacted, home paths stripped, fields truncated.

Configuration

All via environment variables (or .env file in the project root):

Variable Default Description
CONVERSATIONS_DIR data/conversations Where .md conversation files are stored
DB_PATH data/memories.db SQLite memories database
VECTOR_DB_PATH data/conversations/.vec.db sqlite-vec index
SPACY_MODEL en_core_web_lg spaCy model for embeddings and search
MEM0RY_HOST 127.0.0.1 Host for HTTP transport
MEM0RY_PORT 49374 Port for HTTP transport
MEM0RY_TOKEN (empty) Bearer token for HTTP auth (skip = no auth)
MEM0RY_ALLOWED_HOSTS localhost,127.0.0.1 Host allowlist (DNS rebinding protection)
MEM0RY_CORS_ORIGINS (empty) CORS origins for web UI
# Custom storage location
export DB_PATH=/path/to/shared/memories.db
export CONVERSATIONS_DIR=/path/to/shared/conversations

# Portuguese language support
export SPACY_MODEL=pt_core_news_lg
mymem0ry doctor

Import Conversations

myMem0ry auto-detects the format. Supports ChatGPT, Gemini, and Claude exports.

mymem0ry split                                    # Auto-detect
mymem0ry split --source path/to/chatgpt-export    # Specific source
mymem0ry split --source path/to/data --type claude-code  # Force parser

mymem0ry index                                    # Build indexes
mymem0ry migrate                                  # Migrate to structured memory

CLI Commands

# Context & search
mymem0ry context --cwd .                          # Load context for current project
mymem0ry save "Title" "Content" --scope project   # Save a memory
mymem0ry log "message"                            # Quick session log
mymem0ry search "query"                           # ripgrep search
mymem0ry search "query" --backend hybrid --expand # BM25+vector RRF fusion

# Overview
mymem0ry stats                                    # Database overview
mymem0ry projects                                 # List projects with memories
mymem0ry doctor                                   # System health check

# Retention
mymem0ry decay --days 90 --dry-run                # Preview decay
mymem0ry pin <memory_id>                          # Pin memory (exempt from decay)
mymem0ry unpin <memory_id>
mymem0ry forget-sweep --dry-run                   # Preview salience-based sweep

# Handoffs
mymem0ry handoff begin --summary "..."            # Create handoff for next agent
mymem0ry handoff accept                           # Accept pending handoff
mymem0ry handoff status                           # Check server status

# Server & backup
mymem0ry serve                                    # Start HTTP server
mymem0ry serve --detach                           # Start in background
mymem0ry backup --to backup.tar.gz                # Backup DB + conversations
mymem0ry restore --from backup.tar.gz             # Restore from backup

Memory Scopes

Resolved automatically from cwd — no manual configuration needed:

Scope Identifier What it stores Example
session auto UUID Current session state "Trying to fix auth bug"
context git branch Decisions for a branch "On feat/auth, using JWT"
project git remote URL Project architecture "Uses FastAPI + SQLite"
global User preferences "Prefer conventional commits"

get_context() aggregates all 4 levels in priority order.

MCP Tools + Hook Writes

MCP Tools (low token cost — reads + selective writes)

Tool Description
get_context Aggregate context from all scopes
save_memory Save a memory with scope, type, and auto-resolved context
search_memory Search with semantic query expansion
memory_stats Database statistics
memory_handoff_begin Create handoff for next agent
memory_handoff_accept Accept pending handoff
memory_pin Pin a memory (exempt from decay)
memory_unpin Unpin a memory
memory_forget_sweep Sweep stale memories

Hook writes (zero LLM tokens)

Hook kind Description
session-end with messages Archives full conversation to .md + auto-handoff
log Quick session log (creates session-scoped memory)
session-start Records session start observation
user-prompt / post-tool-use / pre-compact Lifecycle observations

Web UI

When running in HTTP mode (MCP_TRANSPORT=streamable-http), a read-only web UI is available:

  • / — Dashboard with stats and recent memories
  • /projects — List of projects with memory counts
  • /project/{id} — Project detail with memories
  • /memory/{id} — Single memory detail
  • /search — Full-text search with scope/type filters
  • /audit — Audit log of all mutations

Documentation

Development

git clone https://github.com/cccadet/myMem0ry.git
cd myMem0ry
bin/setup
uv run python -m pytest
uv run ruff check .

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mymem0ry-0.13.0.tar.gz (237.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mymem0ry-0.13.0-py3-none-any.whl (74.3 kB view details)

Uploaded Python 3

File details

Details for the file mymem0ry-0.13.0.tar.gz.

File metadata

  • Download URL: mymem0ry-0.13.0.tar.gz
  • Upload date:
  • Size: 237.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mymem0ry-0.13.0.tar.gz
Algorithm Hash digest
SHA256 fcb8da352dc928e4186fcf44e21007f29974d726a48f41203f8120480b263258
MD5 d5bf18e974e12e759f4e3393cc73f6b1
BLAKE2b-256 6f3e4b75e48912493131338492857df46f886de0a010e239e681d4d400b7ff41

See more details on using hashes here.

Provenance

The following attestation bundles were made for mymem0ry-0.13.0.tar.gz:

Publisher: publish.yml on cccadet/myMem0ry

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mymem0ry-0.13.0-py3-none-any.whl.

File metadata

  • Download URL: mymem0ry-0.13.0-py3-none-any.whl
  • Upload date:
  • Size: 74.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mymem0ry-0.13.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1ee65c2c11c0043f2a2dcf80799df427d809646ea62dacbe5b8a43e0ae775be2
MD5 2ba15da63f9195e06460e5ed51183d0f
BLAKE2b-256 3e7ce12d794503dbf73675e043aa2e65a59892c31506447fd6b25464e9a04672

See more details on using hashes here.

Provenance

The following attestation bundles were made for mymem0ry-0.13.0-py3-none-any.whl:

Publisher: publish.yml on cccadet/myMem0ry

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page