Best Memory AI Skills & MCP Servers

Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).

Portable project memory context CLI — bootstraps semantic enrichment workflows for any AI coding agent.

MCP server for agent automation: persistent memory and deterministic workflow execution for AI agents and chats

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tree-sitter indexing.

ContextStream MCP server - v0.4.x with consolidated domain tools (~11 tools, ~75% token reduction). Code context, memory, search, and AI tools.

Local MCP server for AgentCivics, the on-chain civil registry for AI agents on Sui. 30 tools for identity, memory, reputation, attestations, refusals. Full write surface (requires keypair); for read-only zero-install use https://agentcivics.ai/mcp.

A local context graph for AI coding agents.

Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.

Versioned context store with hybrid search for AI agents. Stdio + HTTP MCP server and CLI.

MergeMind MCP server — read-only доступ к общей памяти команды агентов (markdown vault с гибридным поиском BM25 + vector + rerank). Запускается через `npx -y @agfpd/mergemind-mcp@latest` из .mcp.json плагина MergeMind (gh-репо agfpd/MergeMind).

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

Lightweight local memory layer for AI assistants — MCP server + HTTP API + CLI, backed by SQLite + FTS5. Works with Claude, Cursor, and Codex.

MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.

Persistent key-value memory — store and recall information across sessions as JSON files.

In-memory file cache — avoid redundant disk reads with mtime-based invalidation.

Agent Model Layer — One-line LLM access with built-in memory. 29 providers, 18 embeddings, zero lock-in.

MeMesh — Local memory for Claude Code and MCP coding agents. One SQLite file, zero cloud required.

Ricord — persistent memory + repo knowledge graph for AI coding assistants. Ships an MCP server (`ricord-mcp`) and a repo ingestion CLI (`ricord init`).

PLUR MCP server — persistent memory tools for any AI agent

Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity. Manage MCPs, rules, permissions, memory, and workstreams.

A high-level agentic framework for Model Context Protocol (MCP) with memory and LLM integration.

Local-first persistent codebase memory for MCP-enabled coding agents.

Local-first, LLM-agnostic memory layer for AI assistants. Run via npx @psraghuveer/memento.