EverMemOS

Welcome to EverMemOS! Join our community to help improve the project and collaborate with talented developers worldwide.

Community	Purpose
	Join the EverMind Discord community to connect with other users
	Join the EverMind WeChat group for discussion and updates

OpenClaw Long-Term Memory Plugin(coming this week)

Claw is putting the pieces of his memory together. Imagine a 24/7 agent with continuous learning memory that you can carry with you wherever you go next.

Live2D Character with Memory

Add long-term memory to your anime character that can talk to you in real-time powered by TEN Framework. See the Live2D Character with Memory Example for more details.

Computer-Use with Memory

Use computer-use to launch screenshot to do analysis all in your memory. See the live demo for more details.

Game of Thrones Memories

A demonstration of AI memory infrastructure through an interactive Q&A experience with "A Game of Thrones" See the code for more details.

EverMemOS Claude Code Plugin

Persistent memory for Claude Code. Automatically saves and recalls context from past coding sessions. See the code for more details.

Visualize Memories with Graphs

Memory Graph view that visualizes your stored entities and how they relate, this is a pure frontend demo which hasn't been plugged with the backend yet, we are working on it. See the live demo.

• Python 3.10+ • Docker 20.10+ • uv package manager • 4GB RAM

Verify Prerequisites:

# Verify you have the required versions
python --version  # Should be 3.10+
docker --version  # Should be 20.10+

# 1. Clone and navigate
git clone https://github.com/EverMind-AI/EverMemOS.git
cd EverMemOS

# 2. Start Docker services
docker compose up -d

# 3. Install uv and dependencies
curl -LsSf https://astral.sh/uv/install.sh | sh
uv sync

# 4. Configure API keys
cp env.template .env
# Edit .env and set:
#   - LLM_API_KEY (for memory extraction)
#   - VECTORIZE_API_KEY (for embedding/rerank)

# 5. Start server
uv run python src/run.py

# 6. Verify installation
curl http://localhost:1995/health
# Expected response: {"status": "healthy", ...}

✅ Server running at http://localhost:1995 • Full Setup Guide

Store and retrieve memories with simple Python code:

import requests

API_BASE = "http://localhost:1995/api/v1"

# 1. Store a conversation memory
requests.post(f"{API_BASE}/memories", json={
    "message_id": "msg_001",
    "create_time": "2025-02-01T10:00:00+00:00",
    "sender": "user_001",
    "content": "I love playing soccer on weekends"
})

# 2. Search for relevant memories
response = requests.get(f"{API_BASE}/memories/search", json={
    "query": "What sports does the user like?",
    "user_id": "user_001",
    "memory_types": ["episodic_memory"],
    "retrieve_method": "hybrid"
})

result = response.json().get("result", {})
for memory_group in result.get("memories", []):
    print(f"Memory: {memory_group}")

📖 More Examples • 📚 API Reference • 🎯 Interactive Demos

# Terminal 1: Start the API server
uv run python src/run.py

# Terminal 2: Run the simple demo
uv run python src/bootstrap.py demo/simple_demo.py

Try it now: Follow the Demo Guide for step-by-step instructions.

# Extract memories from sample data
uv run python src/bootstrap.py demo/extract_memory.py

# Start interactive chat with memory
uv run python src/bootstrap.py demo/chat_with_memory.py

See the Demo Guide for details.

• Group Chat Conversations - Combine messages from multiple speakers
• Conversation Metadata Control - Fine-grained control over conversation context
• Memory Retrieval Strategies - Lightweight vs Agentic retrieval modes
• Batch Operations - Process multiple messages efficiently

EverMemOS achieves 93% overall accuracy on the LoCoMo benchmark, outperforming comparable memory systems.

• LoCoMo - Long-context memory benchmark with single/multi-hop reasoning
• LongMemEval - Multi-session conversation evaluation
• PersonaMem - Persona-based memory evaluation

# Install evaluation dependencies
uv sync --group evaluation

# Run smoke test (quick verification)
uv run python -m evaluation.cli --dataset locomo --system evermemos --smoke

# Run full evaluation
uv run python -m evaluation.cli --dataset locomo --system evermemos

# View results
cat evaluation/results/locomo-evermemos/report.txt

📊 Full Evaluation Guide • 📈 Complete Results

EverMemOS supports GitHub Codespaces for cloud-based development. This eliminates the need to set up Docker, manage local network configurations, or worry about environment compatibility issues.

Note: If your company provides GitHub Codespaces, hardware limitations typically won't be an issue since enterprise plans often include access to larger machine types.

1. Click the "Open in GitHub Codespaces" button above
2. Select a 4-core or larger machine when prompted
3. Wait for the container to build and services to start
4. Update API keys in .env (LLM_API_KEY, VECTORIZE_API_KEY, etc.)
5. Run make run to start the server

All infrastructure services (MongoDB, Elasticsearch, Milvus, Redis) start automatically and are pre-configured to work together.

EverMemOS is available on these AI-powered Q&A platforms. They can help you find answers quickly and accurately in multiple languages, covering everything from basic setup to advanced implementation details.

Service	Link
DeepWiki

We love open-source energy! Whether you’re squashing bugs, shipping features, sharpening docs, or just tossing in wild ideas, every PR moves EverMemOS forward. Browse Issues to find your perfect entry point—then show us what you’ve got. Let’s build the future of memory together.

Read our Contribution Guidelines for code standards and Git workflow.

Apache 2.0 • Citation • Acknowledgments