基于ollama推理框架本地部署的Agent应用,实现MCP工具调用,短长期记忆等功能。|| A locally deployed agent application built on the Ollama, featuring MCP tool integration along with both short-term and long-term memory support.
Open-source Glean for SaaS and the physical world. 87 connectors, hybrid search, autonomous agents, MCP server. Self-hosted, AGPL.
Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.
Self-hosted agent memory in your Obsidian vault: an MCP server with hybrid search, link graph, change feed, tasks and guarded writes, for claude.ai, ChatGPT and Claude Code.
Give Claude Code a permanent memory — 100% local, zero config, graph-powered
MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ONNX embeddings, SQLite-backed semantic search.
开源、用户自有、运行在个人 Cloudflare 账号中的 AI 记忆层。
MCP server for the EVEE (Evo Variant Effect Explorer) API — variant effect prediction from genomic foundation model embeddings
A standalone Rust memory engine for AI coding assistants. Single binary, zero runtime deps. Graph-vector hybrid with MCP tools.
DevMind MCP provides **persistent memory capabilities** for AI assistants through the Model Context Protocol (MCP). It enables AI to remember context across conversations, automatically track developm
The most advanced MCP memory server. Hybrid search (BM25 + jina v5 embeddings + cross-encoder rerank), 100+ languages, temporal knowledge graph, finds any past Cursor or Claude conversation from a vag
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.
Vectorless code retrieval for AI coding agents — search code by business intent (@intent, @domainRule) over a Tree-sitter graph. Built for MSA via MCP.
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, n
A persistent memory MCP server for Claude Code - Recursive Language Model integration for Claude Code inspired by MIT CSAIL paper
Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no cloud.
MCP Server for indexing your local directories into a knowledgebase for your AI Assistants.
Persistent knowledge-graph memory for AI agents: MCP server on SurrealDB with spreading activation and decay
Self-hosted AI roleplay client with memory that survives long campaigns — tiered canon/heuristic/reflex writes, retrieval-time privacy ACL for group chats, native MCP tool support.
This repository contains the packages that make up Pipeshub’s local MCP server
Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, an MCP server and a local browser viewer. No AI/LLM inside; b
An OpenClaw (2026.4/2026.6+) and Hermes Agent plugin that turns AI conversations into a permanent Zettelkasten knowledge base — atomic notes, bi-directional links, knowledge distillation, and MCP tool
Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, n
Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, smart context assembly - in single tool calls. 54 languages + PLC exports. 69.8% R@5 / 43.6% R@1 on dual-judge c
Bridge Stack-chan (xiaozhi-esp32) to Claude Code via MCP — voice-control your personal knowledge base, skills, and 30+ MCP servers through Stack-chan.
Ask questions about the books you own: an AI reader that turns e-books into a knowledge graph and answers with every sentence cited, without spoilers past your chapter. GraphRAG + MCP.
Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.
Deterministic AST Context Compressor & MCP Server for Cursor, Claude & Local LLMs. Cuts prompt tokens by 85–95% with 100% Zero-Leak security.
Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Open-source client SDKs (Python/TypeScript/Go), CLI, API docs,
A Model Context Protocol (MCP) server that builds rich code graphs to provide deep contextual understanding of TypeScript codebases to Large Language Models.
Simple RAG implementation from scratch using MCP, focusing on Perception, Memory, Decision and Action
Memory database for LLM agents — persistent keyword + optional semantic memory, project namespacing, served over HTTP REST and MCP from a single ASGI process. SQLite-backed, packaged as a Docker conta
Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
Interactive visualizer for Anthropic's Memory MCP knowledge graphs. Instantly explore, debug, and analyze entities, relations, and observations from memory.json files in the Model Context Protocol.
Local vector store for Obsidian notes with semantic search via MCP server
Annuaire complet
RAG, graphes et mémoire d'agent à long terme. 2,618 serveurs, les plus utilisés en premier. Chacun ouvre la page de l'éditeur.