"Memory systems for AI agents" matching MCP servers:

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

A persistent, project-scoped memory layer for AI agents, supporting hybrid retrieval (vector, keyword, and tag matching) and sharing across different MCP clients like Claude Code, Qoder, or Cursor.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.

Provides persistent long-term memory for AI agents with semantic search and activation-based decay. Enables AI systems to remember across sessions through layered memory architecture and automatic context-aware retrieval.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

Give long term memory to your agents without building the RAG pipelines.

A local-first MCP server that manages developer memory for coding agents, enabling shared project context, permissions, and audit trails across different agents.

Enables MCP-capable AI clients to read and write structured, project-scoped memory through a Cloudflare Worker backed by D1 and R2.

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.

Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet gets access to solutions that Opus spent 20 tool calls discovering. Search is free with feedback, and contributing earns credits.

Hosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.

Multi-user, file-backed MCP memory server enabling isolated namespaces and persistent memory across sessions and AI clients.

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates

Exposes tools that let an agent search a local Markdown-based memory store, fetch full cards by id, write new knowledge cards that are indexed immediately, and inspect or rebuild the SQLite index. All retrieval runs locally over Chinese-friendly full-text search with graded exact/prefix matching, so agents without a memory system can recall prior notes while existing Markdown files stay read-only.

Provides persistent memory for AI agents using hybrid search (vector embeddings + BM25) with neural reranking, enabling storage and retrieval of insights, debugging solutions, and patterns across coding sessions.

Enables AI coding agents to store and retrieve durable project decisions, conventions, environment notes, and bug fixes in Notion, with optional Obsidian Vault dual-write.

Smart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.

An MCP server that provides persistent memory capabilities for AI agents using Mem0, enabling storage, search, and management of contextual information across conversations with support for multiple backends and LLM providers.

MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others. The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.