Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.
Alpha-Park/genpark-hierarchical-navigable-small-world-hnsw-graph-skillGenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
Alpha-Park/genpark-maximal-marginal-relevance-mmr-reranker-skillGenPark AI Agent Skill - Maximal Marginal Relevance (MMR) diversity-aware vector reranker balancing query relevance vs intra-result redundancy.
alphaparkinc/genpark-hierarchical-navigable-small-world-hnsw-graph-skillGenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
alphaparkinc/genpark-maximal-marginal-relevance-mmr-reranker-skillGenPark AI Agent Skill - Maximal Marginal Relevance (MMR) diversity-aware vector reranker balancing query relevance vs intra-result redundancy.
Alpha-Park/genpark-knowledge-graph-entity-relation-triplet-extractor-skillEntity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.
Alpha-Park/genpark-cosine-bm25-reciprocal-rank-fusion-skillZero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.
Alpha-Park/genpark-context-window-lost-in-middle-reorderer-skillContext window attention optimizer reordering retrieved documents to place critical evidence at prompt boundaries, mitigating lost-in-the-middle degradation.
alphaparkinc/genpark-agent-semantic-cache-similarity-deduplicator-skillHigh-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
Alpha-Park/genpark-agent-hierarchical-episodic-memory-skillCognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.
Alpha-Park/genpark-agent-semantic-cache-similarity-deduplicator-skillHigh-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
alphaparkinc/genpark-agent-hierarchical-episodic-memory-skillCognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.
alphaparkinc/genpark-context-window-lost-in-middle-reorderer-skillContext window attention optimizer reordering retrieved documents to place critical evidence at prompt boundaries, mitigating lost-in-the-middle degradation.
alphaparkinc/genpark-cosine-bm25-reciprocal-rank-fusion-skillZero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.
alphaparkinc/genpark-knowledge-graph-entity-relation-triplet-extractor-skillEntity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.
nisargpatel1906/Aethos_MemoryUniversal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.
impossibleG/impossible-embeddingsA self-hosted embedding server with HTTP, gRPC and MCP APIs, verified model installation, batching, health checks, metrics and Windows and Linux releases.
AdamRussak/self-docSelf-hosted documentation RAG pipeline that serves semantic search to LLM agents over the Model Context Protocol.
tinhien11/remem-mcpLong-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.
17861102832/wanyimem为了服务于大众