Self-evolving memory system for AI agents
Connect Runs on your machine
claude mcp add a-mem-mcp -e LLM_BACKEND=<LLM_BACKEND> -e LLM_MODEL=<LLM_MODEL> -e OPENAI_API_KEY=<OPENAI_API_KEY> -e EMBEDDING_MODEL=<EMBEDDING_MODEL> -e CHROMA_DB_PATH=<CHROMA_DB_PATH> -- uvx a-mem==0.2.1
{
"mcpServers": {
"a-mem-mcp": {
"command": "uvx",
"args": [
"a-mem==0.2.1"
],
"env": {
"LLM_BACKEND": "<LLM_BACKEND>",
"LLM_MODEL": "<LLM_MODEL>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"EMBEDDING_MODEL": "<EMBEDDING_MODEL>",
"CHROMA_DB_PATH": "<CHROMA_DB_PATH>"
}
}
}
}
{
"mcpServers": {
"a-mem-mcp": {
"command": "uvx",
"args": [
"a-mem==0.2.1"
],
"env": {
"LLM_BACKEND": "<LLM_BACKEND>",
"LLM_MODEL": "<LLM_MODEL>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"EMBEDDING_MODEL": "<EMBEDDING_MODEL>",
"CHROMA_DB_PATH": "<CHROMA_DB_PATH>"
}
}
}
}
{
"servers": {
"a-mem-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"a-mem==0.2.1"
],
"env": {
"LLM_BACKEND": "<LLM_BACKEND>",
"LLM_MODEL": "<LLM_MODEL>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"EMBEDDING_MODEL": "<EMBEDDING_MODEL>",
"CHROMA_DB_PATH": "<CHROMA_DB_PATH>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
LLM_BACKENDOptional | LLM backend to use (openai, ollama, sglang, or openrouter) |
LLM_MODELOptional | LLM model name (e.g., gpt-4o-mini, llama2, etc.) |
OPENAI_API_KEYRequired, secret | OpenAI API key (required if LLM_BACKEND=openai) |
EMBEDDING_MODELOptional | Sentence transformer model for embeddings |
CHROMA_DB_PATHOptional | ChromaDB storage directory path |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 9 Jan 2026 |
| Last updated | 9 Jan 2026 |
| Registry name | io.github.DiaaAj/a-mem-mcp |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
