React Refs made easy.
演示地址：[el-rrf-vue-element-base-components]
OpenCodeHub — BM25 + RRF hybrid search
Cognitive core algorithms (RRF fusion, SMG gating, surprisal detection) for Memo
Postgres and pgvector adapter for @jeffs-brain/memory: tsvector BM25, halfvec cosine, and RRF hybrid retrieval.
MemberJunction: Reusable server-side search engine - vector + full-text + entity search with RRF fusion
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
Hybrid keyword + embedding semantic matcher with RRF fusion
AI Memory & Knowledge Management MCP Server — 32 tools, BM25 R@5=95%, hybrid search (RRF), knowledge graph, analytics, cloud sync, Obsidian compatible. Works with Claude Code, Cursor, Gemini CLI, Windsurf, hermes-agent.
SearXNG MCP server with password protection, language-adaptive expansion, RRF fusion, entity-aware ranking, and diagnostics
OpenCode plugin: semantic search with query decomposition, RRF merge, and context-efficient workspace (v4.5.0)
seekx engine: SQLite store, hybrid search (BM25 + vector + RRF), indexing, and file watching. TypeScript sources for Bun.
PG-native long-term memory for AI agents. Turn-level embedding, hybrid RRF ranking, optional knowledge graph. MCP server, CLI, and library API.
Token-budget aware memory engine + MCP server for AI agents — GBrain alternative with RRF hybrid search
Standalone semantic memory storage with hybrid search (BM25 + vector + RRF fusion)
Lotl — Living-off-the-Land memory for AI agents. BM25 + vector RRF fusion + LLM rerank + temporal knowledge graph, on top of SQLite-vec and local ONNX. No infra, no LLM required.
Hybrid RAG search pipeline (vector + trigram + FTS) with Postgres-native stemming and RRF fusion
Persistent memory for AI agents. Multi-strategy retrieval (semantic + BM25 + RRF), 3-zone cosine triage, type-aware lifecycle, entity canonicalization. Postgres + pgvector.
Docusaurus search theme with BM25, Vecto.ai vector search, and hybrid (RRF) modes
Rank fusion algorithms for hybrid search — RRF, ISR, CombMNZ, Borda, DBSF. Zero dependencies.
Long-term memory MCP server for Claude Code with hybrid search (FTS5 + semantic), RRF ranking, and auto context injection
超长会话记忆系统 — RRF多路融合+本地Cross-Encoder精排+Weibull衰减+三层记忆分级，支持所有LLM平台
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
Remote MCP server for searching U.S. FOIA statutes via Supabase. Provides hybrid search (BM25 + vector + RRF) with VoyageAI embeddings and reranking.
Reciprocal Rank Fusion (RRF) algorithm implementation in Rust
Rank fusion algorithms for hybrid search — RRF, ISR, CombMNZ, Borda, DBSF. Zero dependencies.
Interactive CLI and REPL for VelesDB with VelesQL support
Fast rank fusion algorithms for hybrid search (RRF, CombMNZ, Borda)
Operations on ranked lists: fusion (RRF, Copeland, CombMNZ, DBSF, 14 methods), reranking (MaxSim/ColBERT, MMR, DPP), evaluation (NDCG, MAP, MRR), diagnostics, pipeline builder.
Rank fusion and reranking: RRF, ISR, CombMNZ, Borda, DBSF, MaxSim (ColBERT), MMR, DPP, Matryoshka.
High-performance local RAG library - SIMD-accelerated vector search, HNSW indexing
Database layer for foxstash — collections, filtering, hybrid search, WAL persistence, and concurrent access
Sift — a DSL for agents to search codebases in faster, deeper, and more sophisticated ways
Tauri plugin for VelesDB - Vector search in desktop apps
High-performance vector database engine written in Rust
A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology
No description provided.
No description provided.
No description provided.
No description provided.