Havuz

Makra is a memory layer between the web and your AI agents. It serves real-time structured data from the open web at the cost of a vector se

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

The fastest pure Go in-memory Redis alternative. 6.87M+ ops/s peak throughput, 119µs latency, Multi-Reactor engine, embedded Cyberpunk Web S

Python + Terraform. Cloud-ready GraphRAG solution that uncovers distant connections across data and grows incrementally as new documents arr

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embedding

Official benchmark reproduction code for the SAG paper

The open-source talent graph for humans and AI agents.

TurboQuant-compatible vector search plus graph memory for constrained RAG.

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-

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

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own mach

The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-rankin

PostgreSQL-compatible SQL, graph, and vector database built from scratch in Rust.

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

A blank-slate, memory-safe, ultra-high-performance property-graph database in Rust — unified MVCC/time-travel/branches/replication over a fo

Private, fully offline photo search for Android. Find photos with words in English, Arabic, French, Russian or Spanish, or with another phot

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page cit

A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector

AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible fi

RAMen is a fast in-memory data store like Redis, but built for AI: drop-in Redis protocol, native vector search, semantic caching, and a bui

A custom, high-performance, disk-backed Approximate Nearest Neighbor (ANN) vector database built entirely from scratch in C. Feel free to co

Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip inst

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

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native

HR policy RAG assistant with LangChain LCEL, RunnableBranch, FAISS, FastAPI, and an OpenAI-compatible model API.

HR policy RAG workflow with LangGraph StateGraph, conditional routing, FAISS, FastAPI, and an OpenAI-compatible model API.

Vector search library built from scratch with exact and approximate nearest-neighbor indexes. Includes Flat, IVF, HNSW, Product Quantization

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

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,

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

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

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

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

Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent.

Amazon DynamoDB storage backend for the Strands Agents SDK (TypeScript and Python): sessions, agent memory, semantic search over DynamoDB ve

The official Drizzle integration for ParadeDB

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

The open-source, self-hosted alternative to NotebookLM.

Intro to Hyperdimensional Computing (HDC) using a tea dataset

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

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

The most capable Calibre MCP server — full read/write tools plus multilingual semantic search over your whole ebook library or a single book

Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git com

本地嵌入式多模态混合检索：COS + 豆包 Embedding + BM25 + zvec/SQLite，无需单独部署数据库。