hybrid-retrieval

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

A Python Search Engine for Humans 🥸

个人用的 agent memory OS——记忆系统 + self-drive 自主情感，内置对抗式自审 harness。内在过程需要外在标准。

Semantic storage for AI agents. Active pre-release.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

🎵 专属你的私人数字调音师|AI 音乐搜索推荐 Agent | 基于大模型 + 知识图谱 + 双模型声学向量的本地智能音乐推荐系统 | LLM-powered Music Recommendation Agent with Hybrid RAG, Neo4j, and Long-term Memory

Production-grade Node.js RAG system with hybrid retrieval, pluggable adapters, and OpenTelemetry tracing

One memory, every terminal — a shared memory layer for any MCP client.

Movie and Series Streaming Android Application

[ANON for Submission]

Persistent memory for AI coding agents with outcome-based learning

Production-ready RAG system for technical documentation with hybrid retrieval, cross-encoder reranking, and RAGAS evaluation metrics.

Evidence-synthesis RAG assistant for TCM practitioners — hybrid vector + knowledge graph retrieval over 17 classical texts, with query classification, self-critique verification, and blind A/B arena evaluation.

GraphRAG over aviation safety incident reports for causal reasoning and safety pattern extraction

Open-source framework for cold-start recommendations and lazy knowledge graph construction from product catalogs

Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.

Unified memory for all your A.I. agents. Knowledge graph hybrid retrieval of important context.

个人知识库引擎：PDF/Word/EPUB → LLM 实体关系图谱 + 混合检索（向量+BM25+RRF 融合）+ 0.92 语义缓存 + Obsidian 实体隔离导出 + MCP（Claude/Cursor 直连）。智能 PDF 分类器（公式密度≥2% 自动 MinerU），懒初始化 + 生产级异步鲁棒性。欢迎贡献示例与 benchmark。

Agentic RAG system with LangGraph, hybrid BM25+FAISS retrieval, cross-encoder reranking, Corrective RAG, FastAPI, RAGAs evaluation, and Docker deployment

Fully offline iPhone meeting memory. Zero network calls, no Wi Fi required. Records, transcribes, summarises, and answers questions entirely on device. Audio, transcripts, summaries, embeddings, and chat never leave the phone.