Temporal Knowledge Graph System for Architectural Memory - Track decisions, patterns, and failures with MCP integration for Claude Code/Desktop
Give AI agents cited, versioned context from your docs and spreadsheets. Build, diff and roll back what Claude Code, Codex and any MCP client read. Local-first, no API keys.
A tool for retrieving Discord messages and storing them in a vector database for semantic search and analysis.
Universal Local RAG Server for Model Context Protocol (MCP)
Keeps your agent true to your rules. Keeps them true to the code. Keeps learning as you build.
Personal claude.ai conversation archive: schema, ingest, embeddings, hybrid retrieval, MCP server
LLM-free memory distillation engine + MCP server for companion AIs. Compiles conversations into cognitive facts, keeps persona consistent across sessions. No API key, no LLM guessing.
Rust foundation library for AI-native apps — 16-provider catalog, async LLM client, MCP server, knowledge graph, local ONNX embedding (44 models), and safety utilities
零依赖确定性 Agent 长期记忆系统 — Markdown 权威源 + 薄索引,拒答/澄清替代向量硬猜,玻璃盒可审计。 | Zero-dependency deterministic agent memory system — Markdown authoritative store + thin index, refuse/clarify instead of vector guessing.
A Go read-only file-to-Markdown database with SQLite FTS5 keyword search and MCP retrieval tools for AI agents
Unified MCP server for scraping Salesforce developer documentation and searching a local SQLite vector-like database.
Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.
Docker container for centralized Ruflo MCP server with PostgreSQL (RuVector). Architecture: Ruflo (stdio) → Express proxy (Streamable HTTP /mcp).
A Python-based server implementation of the Model Context Protocol (MCP) designed for Retrieval-Augmented Generation (RAG) workflows. It manages the flow of context, tool invocation and model output i
Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems
Rootz Archive: a Claude Code plugin that keeps an exact copy of every conversation and every file Claude edits, on your own computer, searchable by your AI. Free for individual users. No account, work
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client). Autoskill proposes new skills from your sessions, so each project impr
Local-first memory shared by Codex, Claude Code, Cursor, Gemini CLI and other MCP agents. One local file, no account. By Sergey Moloman.
Distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs, incident reviews and a knowledge graph — local-first, evidence-linked.
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
winnow — 把群聊噪声压缩为结构化知识:LangGraph 降噪管道 + L3 知识层 + MCP 接口 + 长期群记忆
Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
Vek-Sync - Built by Vektor Memory - (Model Context Protocol) MCP-sync server configurations in sync across all your AI editors - Open Source
A high-precision local knowledge base server (RAG) that implements the Model Context Protocol (MCP).
ACTA · API MCP com ferramentas de integração entre IA, PostgreSQL, MongoDB e Qdrant · Inteligência Artificial
LLM local persistent storage for security nerds
SolidWorks 2022 MCP server: run, test and auto-fix VBA macros via COM. Self-improving knowledge base, JS-rendered API-docs pipeline, 23 feature generators (parts, assemblies, surfaces, sheet metal).
Persistent memory MCP server for Codex with local SQLite storage and progressive retrieval tools.
Persistent memory for AI coding agents. Single binary, instant full-text search, workspaces, MCP server.
The Karpathy LLM Wiki, production-ready. Zero-RAG personal knowledge base with MCP server, multi-agent support, knowledge graph visualization, and hallucination enforcement. No embeddings, no vector D
Signed, append-only decision records for AI coding agents: an MCP server and CLI that open Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, VS Code and Cursor sessions with your team's decisions
Model Context Protocol server that brings Moorcheh search and RAG tools to MCP clients.
Engram is a self-hostable AI memory layer. It sits between an application and an LLM provider, retrieves relevant user memories from pgvector, injects them into chat prompts, forwards the request, and
Autonomous AI assistant plugin for Claude Code — 5 MCP servers, 21 skills, 3-tier persistent memory, knowledge graph, multi-agent orchestration with Discord/Telegram integration for 24/7 Everyday work
Memory engine for self-evolving AI agent ecosystems. Multi-tenant, multi-space isolation with Bayesian truth maintenance, emotional valence, automatic consolidation, and configurable per-agent persona
Wake Intelligence: 5-Layer Temporal Intelligence for AI Agents A production-ready Model Context Protocol (MCP) server implementing a temporal intelligence "brain" with five layers: Past (causality tr
Весь каталог
RAG, графы и долговременная память агентов. Серверов: 2,636, сначала самые используемые. Каждый ведёт на страницу издателя.