Havuz

Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite

Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines

A reproducible catalog for choosing embedding layouts under quality, memory, and latency constraints

Persistent memory for Claude Code. Your AI never starts from scratch again.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Curso

Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP too

Agent-native screenshot gallery CLI: index, caption, search & safely rename local photos.

Local semantic search, symbol graphs, secrets scanning, output filters, and CLI hooks that save 60-90% LLM tokens.

Self-hosted intent radar — Reverse RAG for any input stream.

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

A local-first, LLM-agnostic memory layer for AI assistants

书内 BOOKNOTE · 多账户教材 RAG 学习助手 —— 回答必引原文:C/W 双引用校验、批注阅读器、长对话自动压缩、可选联网补充(MCP)

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown

A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like

Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MC

MemXT is a Local long-term memory for Claude Code & coding agents. 100% local

Code intelligence engine for AI coding agents. Structural graph queries plus semantic search, exposed via CLI and MCP.

Lightweight text and scans processing: embedding, document processing, OCR, OMR, etc, with inference via ggml in pure C++

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

A hex-native embedded database for Go. Morton keys, native ring scans, seams (contradictions), MVCC, provenance, and optional HNSW embedding

Personal knowledge graph MCP server on Cloudflare D1 + Vectorize. Deploy your own sovereign second brain in one click — Claude captures atom

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hoste

Copper does not rust and is essential for modern infrastructure, written in rust

Semble, coding agent’ların bir codebase içindeki ilgili kod parçalarını doğal dil sorgularıyla bulması için yerel çalışan bir code-search kütüphanesi ve aracı sunuyor.

Neden yükseliyor · 174 günde 6.145 yıldıza ulaşması dikkat çekiyor. Coding agent’ların codebase bağlamına erişimi güncel ve yaygınlaşan bir ihtiyaç; yerel çalışma ve MCP entegrasyonu kurulumu kolaylaştırabilir. Son 28 günde 14 commit ve 3 farklı yazar aktivitenin sürdüğünü gösteriyor, ancak README’deki performans ve token tasarrufu ölçümleri proje tarafından sunulan benchmark iddiaları; bağımsız doğrulama bilgisi verilmemiş.

SQL-like query language and CLI for Qdrant vector search engine

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supe

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Ap

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically que

Find, connect, rediscover your notes — a local-first second brain for Obsidian. Semantic search with strong Chinese/CJK, relation graphs and

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

Hivemind turns your traces into reusable skills across agents

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matry

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

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

Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

turbovec, TurboQuant ile vektörleri sıkıştırıp Rust ve Python üzerinden arama yapmayı sağlayan yerel bir vector index kütüphanesidir.

Neden yükseliyor · 185 günde 17.245 yıldız almış olması ve bellek tasarrufu ile hızlı yerel arama vaadi dikkat çekiyor. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; bu veriler yükselişin güncel olarak sürdüğünü göstermiyor. README'deki performans karşılaştırmaları proje tarafından bildiriliyor, bağımsız doğrulama bilgisi verilen ölçümlerde yok.

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

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

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

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown

Unified multi-layer caching library for AI/agent pipelines — LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A

Context retrieval engine for AI agents — semantic + lexical search over codebases

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

Universal memory runtime for AI agents

A Redis-compatable key-value store. Up to 10x faster. Native vector support.

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

Client-side vector search powered by HNSW. 54KB gzipped WASM. Sub-millisecond latency.