Havuz

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

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

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

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

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Curso

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

Terminal UI and local CLI for crawling GitHub issues and pull requests, generating embeddings, and clustering related work.

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

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

A modular local AI agent built with Python and Ollama, featuring tool calling, memory, web search, document processing, embeddings, and RAG.

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

A 100% local, privacy-first alternative to Windows Recall — captures your screen, OCRs it, and lets you semantically search and chat with yo

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

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

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

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

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

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa

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

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

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

One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server

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

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)

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama

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

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

Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.

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

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

An open-source, local-first CV & resume management platform featuring privacy-focused semantic search to instantly match your skills, projec

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Mar

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers

Türkçe SQL Server 2025 başucu kitabı: kod örnekleri, errata, topluluk soru-cevap · CC BY-NC-SA 4.0 + MIT

The in-browser vector store that remembers — a Rust→WASM HNSW engine that persists to OPFS and stays consistent across tabs. Private, offlin

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

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

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

Semantic product search for commerce: find products by meaning, not keywords. A Medusa v2 module backed by pgvector + Gemini embeddings, wit

🧠 Hybrid long-term memory plugin for OpenClaw agents — SQLite+FTS5 for structured facts, LanceDB for semantic recall