Skip to content
Data
MCP

omega-memory

Ships with omega-memory: Cross-model memory for AI agents. Local-first. Works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client. Your agent's brain shouldn't live on someone else's server,…

From plugin
omega-memory
2261 skill1 MCP

Claude Code

$ pipx install "omega-memory[server]"

From the README

What can you do with omega-memory?

  • Memory & Learning

    Stores decisions, lessons, error patterns, and preferences with semantic search.

  • Multi-Agent Coordination (omega-pro)

    File and branch locking, session management, task queues with dependencies, intent broadcasting, and agent-to-agent messaging, so agents don't overwrite each other's work.

  • Intelligent LLM Routing (omega-pro)

    Classifies tasks and routes to the optimal model.

  • Knowledge Base (omega-pro)

    Ingest PDFs, markdown, web pages, and text files into a searchable knowledge base with semantic chunking.

  • Entity Registry (omega-pro)

    Multi-entity corporate memory with relationships, hierarchies, and entity-scoped memories/profiles/documents.

  • Secure Profile (omega-pro)

    AES-256 encrypted personal data storage with macOS Keychain integration.

Security report

Info

Not enough data

  • Known flaws

    Not published

  • Signed build

    Not published

  • Maintained

    Oct 9, 2026

    Last push

  • Licence

    Apache-2.0

  • Runs as

    Local process

    On your machine

  • Deprecated

    Not published

Signals from public registries, not an audit. Checked Nov 15, 2026.

omega-memory README

OMEGA

Cross-model memory for AI agents. Local-first. Works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client. Your agent's brain shouldn't live on someone else's server, or be locked to one provider.

Python 3.11+ PyPI License


The Problem

AI coding agents are stateless. Every new session starts from zero. The "solutions" either lock you into one model provider or send your codebase context to their cloud.

  • Context loss. Agents forget every decision, preference, and architectural choice between sessions. Developers spend 10-30 minutes per session re-explaining context that was already established.
  • Repeated mistakes. Without learning from past sessions, agents make the same errors over and over. They don't remember what worked, what failed, or why a particular approach was chosen.
  • Cloud memory = someone else's database. Services like Mem0 require API keys and send your data to their servers. When they change pricing, get acquired, or go down, your agent's accumulated intelligence disappears.
  • Vendor lock-in. Anthropic's Memory Tool only works with Claude. OpenAI's memory only works with GPT. Switch models, lose your memory.

OMEGA solves this. Memory, coordination, and learning that runs entirely on your machine. Works with every major LLM and coding agent. No cloud. No API keys. No vendor lock-in.

Quick Install

OMEGA needs Python 3.11 or newer. Check with python3 --version: macOS ships Python 3.9, which is too old. If pip answers No matching distribution found for omega-memory, that is the reason; install a newer Python first (for example brew install python@3.12, or from python.org).

Install OMEGA into its own environment. Homebrew's Python refuses a plain pip install (PEP 668), and an isolated install keeps OMEGA's dependencies away from your projects. Pick one:

# pipx
pipx install "omega-memory[server]"

# or uv
uv tool install "omega-memory[server]"

# or a virtual environment
python3.12 -m venv ~/.venvs/omega     # any Python 3.11 or newer
~/.venvs/omega/bin/pip install "omega-memory[server]"
export PATH="$HOME/.venvs/omega/bin:$PATH"

Keep the quotes around "omega-memory[server]": zsh, the default macOS shell, treats bare square brackets as a pattern and fails. The [server] extra installs the MCP server, which also runs the hook daemon; without it Claude Code gets no OMEGA tools and no hooks.

Then:

omega setup     # downloads the embedding model, registers the MCP server, installs hooks
omega doctor    # checks every step, and names the fix for anything that failed

omega setup --dry-run shows what setup would change without writing or downloading anything.

Claude Desktop

omega setup --client claude-desktop

This registers OMEGA as an MCP server in Claude Desktop's config. Restart Claude Desktop to activate.

Cursor, Windsurf, Cline, Codex, Antigravity

omega setup --client cursor      # or: windsurf, cline, codex, antigravity

Codex and Antigravity get their config file written; for the others setup prints the JSON block to paste. For any other MCP client, omega setup --client venv prints the command and arguments to use. Hooks (automatic capture and surfacing) are available with Claude Code only.

Library-only install (no MCP server)

If you only need OMEGA as a Python library for scripts, CI/CD, or automation, install it into your project's environment:

pip install omega-memory    # Core only, no MCP server
from omega import store, query, remember

store("Always use TypeScript strict mode", "user_preference")
results = query("TypeScript preferences")

This gives you the full storage and retrieval API without running an MCP server. Hooks need the MCP server (the hook daemon runs inside it), so a library-only install has no automatic capture or surfacing.

From Source

git clone https://github.com/omega-memory/omega-memory.git
cd omega-memory
python3.12 -m venv .venv && source .venv/bin/activate
pip install -e ".[server,dev]"
omega setup

omega setup will:

  1. Create ~/.omega/ (or $OMEGA_HOME if you set it)
  2. Download the ONNX embedding model, bge-small-en-v1.5 (~130 MB), and a reranker (~90 MB) to ~/.cache/omega/models/
  3. Register omega-memory as an MCP server (Claude Code auto-detected, or specify --client)
  4. Install session hooks into ~/.claude/settings.json
  5. Add an OMEGA block to ~/.claude/CLAUDE.md

If a step fails, the summary marks it [FAIL] with the reason and setup exits with an error.

60-Second Quickstart

OMEGA works through natural language — no API calls, no configuration. Just talk to Claude.

1. Tell Claude to remember something:

"Remember that the auth system uses JWT tokens, not session cookies"

Claude stores this as a permanent memory with semantic embeddings.

2. Close the session. Open a new one.

3. Ask about it:

"What did I decide about authentication?"

OMEGA surfaces the relevant memory automatically:

Found 1 relevant memory:
  [decision] "The auth system uses JWT tokens, not session cookies"
  Stored 2 days ago | accessed 3 times

That's it. Memories persist across sessions, accumulate over time, and are surfaced automatically when relevant — even if you don't explicitly ask.

Key Features

  • Memory & Learning — Stores decisions, lessons, error patterns, and preferences with semantic search. Claude recalls what matters without you re-explaining everything each session. Tools cover compaction, consolidation, timeline, graph traversal, and checkpoint/resume.

  • Multi-Agent Coordination (omega-pro) — File and branch locking, session management, task queues with dependencies, intent broadcasting, and agent-to-agent messaging, so agents don't overwrite each other's work.

  • Intelligent LLM Routing (omega-pro) — Classifies tasks and routes to the optimal model. Coding → Claude Sonnet. Quick edit → Llama 8b at 1/60th the cost. 1M token context → Gemini Flash. 5 providers, 4 priority modes, sub-2ms intent classification.

  • Knowledge Base (omega-pro) — Ingest PDFs, markdown, web pages, and text files into a searchable knowledge base with semantic chunking.

  • Entity Registry (omega-pro) — Multi-entity corporate memory with relationships, hierarchies, and entity-scoped memories/profiles/documents.

  • Secure Profile (omega-pro) — AES-256 encrypted personal data storage with macOS Keychain integration.

How OMEGA Compares

FeatureOMEGAAnthropic MemoryMem0Zep
Works with any LLM/agentYesClaude onlyYesYes
Your data stays on your machineYesPartial*NoNo
No cloud dependencyYesNo (needs API)NoNo
Semantic search + knowledge graphYesNo (file CRUD)$249/moYes
Multi-agent coordinationYes (pro)Research previewNoNo
Works with Claude Code, Cursor, Claw CodeYesClaude onlyPartialNo
Free & open sourceYes (Apache 2.0)NoFreemiumFreemium

Anthropic's Memory Tool stores data client-side but requires Claude API calls for all memory operations. OMEGA runs entirely on-device, including embeddings (ONNX).

Anthropic Memory is for Anthropic. OMEGA is for everyone.

Architecture

     Claude Code  ·  Cursor  ·  Claw Code  ·  Any MCP Client
               │         │         │              │
               └─────────┴─────┬───┴──────────────┘
                               │ stdio/MCP
               ┌───────────────▼─────────────┐
               │   OMEGA MCP Server   │
               │   core memory tools  │
               └──┬──────────────────┘
                  │
         ┌────────▼──────────────┐
         │ Core Memory Engine    │
         │ (semantic search,     │
         │  embeddings, graphs)  │
         └─────┬─────────────────┘
               │
               ▼
         ┌──────────────────────────────────────┐
         │         omega.db (SQLite)             │
         │  memories | edges | embeddings        │
         └──────────────────────────────────────┘

Single database, modular handlers. Optional modules (coordination, router, entity, knowledge, profile) are available with OMEGA Pro and register into the same server process. No separate daemons, no microservices.

MCP Tools Reference

OMEGA runs as an MCP server inside Claude Code. By default it shows the client five tools (omega_store, omega_welcome, omega_protocol, omega_tools, omega_call) to save context: omega_tools lists everything available and omega_call runs any of it. Set OMEGA_CONDENSED=0 in the server's environment to expose every tool directly.

Core tools

ToolWhat it does
omega_storeStore a memory (decision, lesson, error, preference, ...)
omega_querySearch memories: semantic, exact phrase, timeline, or browse
omega_welcomeSession briefing: recent context, reminders, profile
omega_protocolOperating rules for the session
omega_checkpointSave task state for cross-session continuity
omega_resume_taskResume a checkpointed task
omega_memoryEdit, delete, supersede, rate, or link one memory; find similar ones
omega_profileRead or update the user profile and preferences
omega_remindSet, list, or dismiss time-based reminders
omega_maintainHealth, consolidation, compaction, backup and restore
omega_statsType breakdown, session stats, weekly digest
omega_reflectFind contradictions; trace how a topic's decisions evolved
omega_reviewReview a diff with memory of your codebase's conventions
context_packetCompact, task-aware memory packet for the current work
omega_consult_gpt, omega_consult_claudeAsk another model for a second opinion (needs your own API key for that provider)

OMEGA Pro adds coordination, routing, entity, knowledge base, and profile tools.

CLI

CommandDescription
omega setupCreate dirs, download model, register MCP, install hooks (--dry-run to preview)
omega doctorVerify installation health
omega hooks setup / omega hooks doctorInstall or check the Claude Code hooks only
omega statusMemory count, store size, model status
omega query <text>Search memories by semantic similarity
omega store <text>Store a memory with a specified type
omega remember <text>Store a permanent preference
omega timelineShow memory timeline grouped by day
omega activityShow recent session activity overview
omega statsMemory type distribution and health summary
omega consolidateDeduplicate, prune, and optimize memory
omega compactCluster and summarize related memories
omega backupBack up omega.db (keeps last 5)
omega validateValidate database integrity
omega logsShow recent hook errors
omega migrate-dbMigrate legacy JSON to SQLite
omega serveRun the MCP server (omega serve --help for the HTTP daemon)

Free and Pro

@omega-memory
Ships withomega-memory
2261 skill1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
226
Star history of omega-memory/omega-memory on GitHub, a chart by star-history.com

More MCP servers from other plugins.

mem0
Auto-invoked

mem0

MCP

Stores and retrieves long term memories for AI agents to personalize their responses.

mem08d69k
@mem0ai@mem0aiInstall MCP
phrocs

phrocs

MCP

Ships with posthog: :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI…

posthog4d41k
@posthog@posthogInstall MCP
agentmemory
Auto-invoked

agentmemory

MCP

Ships with agentmemory: #1 Persistent memory for AI coding agents based on real-world benchmarks

@rohitg00@rohitg00Install MCP
skill-seekers

skill-seekers

MCP

Ships with skill-seekers: 🧠 The data layer for AI systems. Skill Seekers turns documentation sites, GitHub repos, PDFs, videos,…

Questions about omega-memory.

Which coding agents can use omega-memory?
omega-memory works in any agent that reads an MCP config file: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf. Each agent reads it from its own file; this page names the file for each one.