Havuz

XERJ, kod ve dokümanları yerel olarak indeksleyip agent ve uygulamalar için arama, RAG ve bellek işlevleri sunan Rust tabanlı bir arama motorudur.

Neden yükseliyor · 90 günlük yaşına karşılık 2.496 yıldız ve son 28 günde 307 commit dikkat çekiyor. README, belirli bir coding-agent çalışmasında aynı çözüm oranıyla 2,7 kat daha az output token ölçüldüğünü bildiriyor; bu sonuç proje tarafından yayımlanan bir çalışmaya dayanıyor ve bağımsız doğrulama bilgisi verilen içerikte net değil. Yüksek commit sayısına rağmen dönemde yalnızca 2 farklı yazar bulunması aktivitenin dar bir ekibe bağlı olabileceğini gösteriyor.

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

Local document Q&A in your terminal — powered by on-device LLMs.

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown

Chinese AI learning notes and a minimal RAG demo with Sentence-Transformers, BM25, OpenAI-compatible APIs, and retrieval evaluation.

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offli

Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and r

Open-source vector database and sub-microsecond key-value store in one Go engine — embed it as a library, run it standalone, or replicate it

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary,

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

Local-first semantic search engine for your files — hybrid BM25 + vector + HyDE search over docs, PDFs, images, audio and video. 100% offlin

Agentic memory built on Postgres

Hybrid vector + knowledge graph RAG system for enterprise documents. Fuses Pinecone dense vectors, BM25 sparse reranking, and Neo4j multi-ho

Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

Zero-token long-term memory for Claude Code. Indexes your own session transcripts and retrieves evidence deterministically — entity-context

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search,

Canonical memory infrastructure: BM25 recall over trusted files for AI agents.

a rag-based wiki skill with obsidian just like karpathy-llm-wiki

Low-power, offline retrieval (RAG) for disaster and infrastructure-failure guidance.