MCP App StoreMCP App Store
from graphmemory149
Embedded GraphRAG: DuckDB-backed hybrid graph + vector store for extracting, storing, deduping, and querying entity/relationship graphs with BM25, HNSW vectors,
GraphMemory provides an embedded GraphRAG engine built on DuckDB that combines vector search (HNSW), full-text (BM25), and hybrid retrieval with a fluent query builder and multi-hop traversal. It adds extraction tools (DSPy) to convert text into nodes and edges, fuzzy deduplication and merge strategies, NetworkX-based graph algorithms (PageRank, centrality), and a lightweight D3.js visualizer. The library is single-package and file-backed, intended for local or prototype deployments where a serverless, single-writer graph is desirable.
Use GraphMemory when your retrieval needs go beyond pure vectors or pure graph databases — e.g., RAG workflows that require traversals across entities, or when you want to extract structured knowledge (entities & relations) from documents and keep it deduplicated and queryable. It is suited for prototyping, small-to-medium datasets, and applications where embedding model vector lengths are fixed. Avoid when you need distributed multi-writer graph databases at massive scale (hundreds of millions of nodes).
examples/ covering extraction and ingest patterns.ask() patterns, DSPy extraction usage, two-pass dedup best practices, and gotchas for production use.Likely compatible with agents that can run Python tooling and call LLMs for extraction (Copilot/Codex/Gemini CLI style workflows).
GraphMemory is a DuckDB-backed embedded GraphRAG library offering hybrid vector+BM25 search, entity/relationship extraction via DSPy, and fuzzy deduplication. The SKILL.md is comprehensive with clear decision tables, canonical code snippets, and well-documented gotchas. No scripts were bundled to execute. No security concerns found — no remote code execution patterns, no hardcoded credentials, no exfiltration risks. The skill is well-structured and would be useful for developers building knowledge graph applications without wanting to manage external databases.
Clean, well-documented skill with excellent structure. No bundled scripts to audit. The SKILL.md itself is exemplary — clear triggers, decision table, gotchas section, data models table. Minor deduction for code quality due to no runnable scripts to verify, but the documentation quality is high. Usefulness is good but niche — GraphRAG is a specific use case, not universally applicable.
DSPy — Declarative LM Programming
Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti
Microsoft Foundry Classic — Expert Guidance
Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.
OpenViking Memory Plugin
Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver
Synalinks Framework
Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.
DNA Memory
Three-layer agent memory system (working / short-term / long-term) with active forgetting, automatic pattern induction and a reflect loop to let agents learn an
libagent
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a
py_mnn_kb — Local GraphRAG Knowledge Base
Local GraphRAG knowledge base backed by SQLite + MNN embeddings; provides CLI tools to build, note, query, and check status for an on-device RAG KB.
Supabase Expert
Comprehensive Supabase expert with access to 2,616 official documentation files covering PostgreSQL database, authentication, real-time subscriptions, storag...