Skip to main content
Glama
arunkumars-mf

mem0-agent-memory

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AWS_REGIONNoAWS region for Bedrock
FAISS_PATHNoOptional path for FAISS index (default: .mem0/memory)
MEM0_RUN_IDNoOptional run ID for session partitioning
OLLAMA_HOSTNoOllama server URL (required for Ollama)
QDRANT_HOSTNoQdrant server host (for server mode)
QDRANT_PATHNoOptional path for embedded Qdrant
QDRANT_PORTNoOptional Qdrant server port (default: 6333)
MEM0_API_KEYNoAPI key for Mem0 Platform
MEM0_USER_IDNoOptional user ID (default: system username)
MEM0_VERBOSENoSet to 'true' for verbose response mode
LMSTUDIO_HOSTNoLM Studio server URL (required for LM Studio)
MEM0_AGENT_IDNoOptional agent ID (default: workspace name)
OPENSEARCH_HOSTNoOpenSearch endpoint URL
OLLAMA_LLM_MODELNoOptional Ollama LLM model (default: llama3.2)
AWS_ACCESS_KEY_IDNoAWS access key for Bedrock
BEDROCK_LLM_MODELNoOptional Bedrock LLM model (default: us.anthropic.claude-3-5-haiku-20241022-v1:0)
BEDROCK_MAX_TOKENSNoOptional max tokens for Bedrock (default: 1500)
LMSTUDIO_LLM_MODELNoOptional LM Studio LLM model (default: llama-3.2-3b-instruct)
MEM0_INFER_DEFAULTNoSet to 'true' (default) for LLM inference on storage
MEM0_MAX_RELATIONSNoMax graph relations in compact mode (default: 20)
NOMIC_USE_PREFIXESNoSet to 'true' for better search accuracy with Nomic embeddings
OLLAMA_EMBED_MODELNoOptional Ollama embedding model (default: nomic-embed-text)
BEDROCK_EMBED_MODELNoOptional Bedrock embedding model (default: amazon.titan-embed-text-v2:0)
LMSTUDIO_EMBED_MODELNoOptional LM Studio embedding model (default: text-embedding-nomic-embed-text-v1.5)
AWS_SECRET_ACCESS_KEYNoAWS secret key for Bedrock
MEM0_MIN_RELEVANCE_SCORENoMinimum relevance score for search (0.0-1.0, default: 0.7)

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/arunkumars-mf/mem0-agent-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server