Havuz

MemPalace, AI konuşma geçmişini yerel olarak özgün metin halinde saklayıp semantic search ile gerektiğinde geri çağıran bir memory sistemi sunuyor.

Neden yükseliyor · AI agent’larda kalıcı memory ihtiyacına doğrudan odaklanması ve local-first yaklaşımı ilgi çekiyor; 176 günde 59 binden fazla yıldız dikkat çekici bir görünürlük gösteriyor. Son 28 gündeki 132 commit ve 22 farklı yazar da kayda değer geliştirme hareketliliğine işaret ediyor; ancak yıldızlar benimseme veya kaliteyi tek başına kanıtlamaz.

Local AI search for podcast and video archives on Apple Silicon: Whisper speech, Apple Vision OCR and SigLIP-2 visual search fused into one

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual i

職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-mo

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

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

根据 Crash/ANR/OOM 等日志构建证据链，实现自动修复代码的Agent框架，并支持衔接自动测试验证、Bug管理平台 Agent framework that builds evidence chains from Crash/ANR/OOM logs, auto-fix

Bilingual AI study coach that answers only from your own course material, with citations

A local-first Python personal AI assistant for reasoning, memory, voice, vision, automation, and device control.

.NET client for Chroma and Chroma Cloud, tested with Chroma 0.4.10 to 1.5.9.

A standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP server

A lightweight CLI tool for RAG over local documents

Mako — AI Career Intelligence System

A local-first CLI that makes your Obsidian vault (or Markdown Notes) searchable and AI-Agents queryable with semantic search and hidden conn

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

Persistent RAG memory layer for AI agents - store observations, retrieve context by semantic similarity, self-prune on TTL

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

Claude Code workspace toolkit: persistent memory, multi-account inbox MCPs, rule discipline, auto-capture knowledge base. MIT.

Apricity — a fast, local-first web UI for MemPalace: browse, search, edit & curate your AI agent's memory, knowledge graph & vector store. Z

Fully local AI companion with Long-Term Memory RAG, branch-isolated worldlines, Live2D/VRM 3D avatars, and real-time TTS for consumer GPUs (

Measure whether an embedding upgrade is worth it, bridge it without reindexing when it is, and migrate safely when you are ready.

Domain-specializált, RAG-alapú multi-ágens pre-audit rendszer transzferár-dokumentációk (TP) elemzésére. 🏆 7. helyezés a PwC Hungary AI Hack

AI-powered English learning assistant for Chinese elderly users, with RAG, ReAct Agent, two-stage retrieval, and 5-dim evaluation framew