io.github.xultrax-web/agent-memory-mcp
Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"agent-memory-mcp": {
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
],
"env": {
"AGENT_MEMORY_DIR": "<agent_memory_dir>",
"AGENT_MEMORY_SCOPE": "<agent_memory_scope>",
"AGENT_MEMORY_LOG": "<agent_memory_log>"
}
}
}
}{
"mcpServers": {
"agent-memory-mcp": {
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
],
"env": {
"AGENT_MEMORY_DIR": "<agent_memory_dir>",
"AGENT_MEMORY_SCOPE": "<agent_memory_scope>",
"AGENT_MEMORY_LOG": "<agent_memory_log>"
}
}
}
}npx -y @xultrax-web/agent-memory-mcpAGENT_MEMORY_DIRAbsolute path to a custom memory storage directory. Overrides the default per-project location.
AGENT_MEMORY_SCOPESet to 'global' to store memories in ~/.agent-memory/ instead of the per-project default ./.agent-memory/.
AGENT_MEMORY_LOGLog level: debug | info | warn | error. Defaults to info. Logs go to stderr (won't pollute MCP stdio).
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Expert-curated knowledge graphs for AI agents — PSFK Retail, Beauty, Sports and more.