EverMemOS
The Memory OS for Agentic AI
Long-term memory infrastructure for AI that remembers, adapts, and evolves.
92.3%
82%
Why Memory Matters
“An entity without memory cannot exhibit consistency or evolve—because its foundation is missing beneath the surface.”
Four-Layer System Architecture
Agentic Layer
Task understanding, planning, execution (Prefrontal Cortex analogy)
Memory Layer
Long-term storage & retrieval(Cortical memory networks)
Index Layer
Embeddings, key-value pairs, KG indexing (Hippocampus analogy)
API / MCP Interface Layer
Integrates with external enterprise systems (Sensory interface)
Three Core Innovations of EverMemOS
EverMemOS Evaluation Framework
Quickly Build Long-Term Memory AI
# 1. Clone the repository git clone https://github.com/EverMind-AI/EverMemOS.git cd EverMemOS # 2. Start Docker services docker-compose up -d # 3. Verify service status docker-compose ps # 4. Install uv (if not already installed) curl -LsSf https://astral.sh/uv/install.sh | sh # 5. Install project dependencies uv sync # 6. Configure environment variables cp env.template .env # Edit the .env file and fill in the necessary configurations: # - LLM_API_KEY: Enter your LLM API Key (for memory extraction) # - DEEPINFRA_API_KEY: Enter your DeepInfra API Key (for Embedding and Rerank) # For detailed configuration instructions, please refer to: [Configuration Guide](docs/usage/CONFIGURATION_GUIDE.md)