mem0-agent-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region for Bedrock | |
| FAISS_PATH | No | Optional path for FAISS index (default: .mem0/memory) | |
| MEM0_RUN_ID | No | Optional run ID for session partitioning | |
| OLLAMA_HOST | No | Ollama server URL (required for Ollama) | |
| QDRANT_HOST | No | Qdrant server host (for server mode) | |
| QDRANT_PATH | No | Optional path for embedded Qdrant | |
| QDRANT_PORT | No | Optional Qdrant server port (default: 6333) | |
| MEM0_API_KEY | No | API key for Mem0 Platform | |
| MEM0_USER_ID | No | Optional user ID (default: system username) | |
| MEM0_VERBOSE | No | Set to 'true' for verbose response mode | |
| LMSTUDIO_HOST | No | LM Studio server URL (required for LM Studio) | |
| MEM0_AGENT_ID | No | Optional agent ID (default: workspace name) | |
| OPENSEARCH_HOST | No | OpenSearch endpoint URL | |
| OLLAMA_LLM_MODEL | No | Optional Ollama LLM model (default: llama3.2) | |
| AWS_ACCESS_KEY_ID | No | AWS access key for Bedrock | |
| BEDROCK_LLM_MODEL | No | Optional Bedrock LLM model (default: us.anthropic.claude-3-5-haiku-20241022-v1:0) | |
| BEDROCK_MAX_TOKENS | No | Optional max tokens for Bedrock (default: 1500) | |
| LMSTUDIO_LLM_MODEL | No | Optional LM Studio LLM model (default: llama-3.2-3b-instruct) | |
| MEM0_INFER_DEFAULT | No | Set to 'true' (default) for LLM inference on storage | |
| MEM0_MAX_RELATIONS | No | Max graph relations in compact mode (default: 20) | |
| NOMIC_USE_PREFIXES | No | Set to 'true' for better search accuracy with Nomic embeddings | |
| OLLAMA_EMBED_MODEL | No | Optional Ollama embedding model (default: nomic-embed-text) | |
| BEDROCK_EMBED_MODEL | No | Optional Bedrock embedding model (default: amazon.titan-embed-text-v2:0) | |
| LMSTUDIO_EMBED_MODEL | No | Optional LM Studio embedding model (default: text-embedding-nomic-embed-text-v1.5) | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret key for Bedrock | |
| MEM0_MIN_RELEVANCE_SCORE | No | Minimum relevance score for search (0.0-1.0, default: 0.7) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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