Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-agent-hierarchical-episodic-memory-skill what do you remember about our last meeting?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
genpark-agent-hierarchical-episodic-memory-skill delivers zero-dependency, low-latency, deterministic agentic memory and retrieval primitives engineered strictly using Python 3.9+ standard library.
Zero External Dependencies: Operates exclusively via pure Python (math, re, collections, heapq, hashlib, json). Zero pip install overhead, zero C-extension compile errors.
Enterprise RAG & Memory Invariants: Implements formal algorithms for cognitive decay, BM25 Okapi lexical scoring, Reciprocal Rank Fusion, knowledge graph traversal, semantic query caching, and lost-in-the-middle context reordering.
Native Anthropic MCP Protocol: Compliant with standard JSON-RPC 2.0 stdio MCP specifications for Claude Desktop, Cursor, and Windsurf.
Related MCP server: llm-memory-tool
flowchart TD
UserQuery["User Prompt / Agent Goal"] --> SemCache["Semantic Cache Check"]
SemCache -->|Cache Hit| FastReturn["Cached Response (0ms)"]
SemCache -->|Cache Miss| DualRetrieval["Dual Retrieval Pipeline"]
subgraph DualRetrieval ["Hybrid Search Engine"]
BM25Lex["BM25 Okapi Lexical Ranker"]
DenseVec["Dense Cosine Vector Similarity"]
end
DualRetrieval --> RRF["Reciprocal Rank Fusion (RRF)"]
RRF --> GraphExp["Knowledge Graph Triplet Expansion"]
GraphExp --> LostMiddle["Lost-In-The-Middle Context Reorderer"]
LostMiddle --> LLM["LLM Synthesis with Optimal Context"]
LLM --> EpisodicMem["Episodic Consolidation & Recency Decay"]from client import AgentHierarchicalEpisodicMemory
# Initialize engine
engine = AgentHierarchicalEpisodicMemory()
# Execute self-testing benchmark suite
result = engine.run_benchmark_hierarchical_memory()
print("Execution Result:", result)Add to your claude_desktop_config.json or cursor.json:
{
"mcpServers": {
"genpark-agent-hierarchical-episodic-memory-skill": {
"command": "python",
"args": ["-u", "/path/to/genpark-agent-hierarchical-episodic-memory-skill/mcp_server.py"]
}
}
}This skill contains pre-configured smithery.yaml and pyproject.toml manifests. Install directly via pip:
pip install git+https://github.com/alphaparkinc/genpark-agent-hierarchical-episodic-memory-skill.gitThis server cannot be deployed
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
