Cognitive memory system for AI agents with 129 MCP tools. Persistent hierarchical memory, emotional recall, knowledge graphs, spreading activation, hybrid retrieval (BM25+RRF), metacognition, goal tracking, spaced repetition, dream consolidation, and more.
Overview
EMMS - Enhanced Memory Management System
Cognitive memory for AI agents. 129 MCP tools. MIT License.
Install
pip install emms-mcp
# or
npx -y emms-mcp
# or
uvx emms-mcp
Configuration
{
"mcpServers": {
"emms": {
"command": "uvx",
"args": ["emms-mcp"]
}
}
}
Tool Categories (129 tools)
- Storage: store, store_batch, load, save
- Retrieval: retrieve, hybrid_retrieve, adaptive_retrieve, plan_retrieve, affective_retrieve, spotlight_retrieve, associative_retrieve
- Knowledge Graph: build_association_graph, graph_communities, spreading_activation, export_graph_dot, export_graph_d3
- Reflection: reflect, dream, synthesize_wisdom, abstract_principles
- Emotions: current_emotion, regulate_emotions, mood_trend, emotional_landscape
- Goals: push_goal, complete_goal, active_goals, exploration_goals
- Metacognition: metacognition_report, consciousness_metrics, presence_metrics, detect_biases
- Memory Management: apply_decay, deduplicate, reconsolidate, batch_reconsolidate, llm_consolidate
- Identity: update_self_model, agent_model, map_values
- Prediction: predict, pending_predictions, plausible_futures, project_future
- Multi-Agent: merge_from, list_namespaces, migrate_namespace
- And more: SRS, norms, schemas, causal maps, timelines, narratives...
Links
Server Config
{
"mcpServers": {
"emms": {
"command": "uvx",
"args": [
"emms-mcp"
]
}
}
}