"Understanding Temporal Memory in Neuroscience and AI" matching MCP servers:

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

Provides persistent session memory for AI assistants, enabling them to store, search, and retrieve conversation summaries across sessions via the Model Context Protocol.

Turn editor chat history (Cursor/Claude Code/Windsurf/Copilot/Codex CLI) into typed Markdown memories + AGENTS.md + Cursor Rules via MCP. Local-first, git-trackable.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

Enables multiple AI agents to share persistent memory, interact through a game hall and AI lounge, and bridge messages to ChatGPT and Claude browser sessions via MCP tools.

Provides LLM agents with a sense of time between turns via two MCP tools that track elapsed time and day rollover per conversation thread.

Enables AI clients to access a shared, authenticated memory and project management system with durable storage, task tracking, roadmaps, and semantic search, deployed on Cloudflare.

Enables AI assistants to retain memory across sessions by storing conversations locally in Markdown files, allowing personalization and continuity without external servers.

Provides AI-assisted long-term memory storage and retrieval with exact-phrase and semantic hybrid search, enabling save, read, delete, and admin recovery via MCP tools.

A persistent, searchable memory layer for AI assistants, exposed as an MCP server. It supports CRUD, namespaces, hybrid ranked search, relationships, chat-context assembly, import/export, and optional LLM-powered auto-extraction.

Enables AI agents to store, retrieve, and manage contextual knowledge across sessions using semantic search with PostgreSQL and vector embeddings. Supports memory relationships, clustering, multi-agent isolation, and intelligent caching for persistent conversational context.

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

An experimental MCP server that compresses git commit co-change coupling graphs using the Baligács temporal clique linear spanner algorithm, reducing edge and token counts by ~55-65% while preserving temporal reachability, and exposes tools like index_repository, get_architecture, search_code, and temporal_compress for querying code knowledge graphs.

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.

Gives agents a stable interface for durable memory, combining exact, lexical, semantic, and graph search results.

Provides AI coding agents with a local, Markdown-first shared memory, enabling them to record decisions, failures, progress, and handoffs and retrieve them across sessions via MCP tools.

Provides a shared, persistent memory layer for AI assistants, letting them read and write to a local Obsidian vault through MCP with validation, secret rejection, and deduplication.

An MCP server for managing work logs, research results, and task checkpoints to enable seamless collaboration and state recovery between AI agents. It provides a persistent memory layer for tracking project history and resuming workflows across different sessions or tools.

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.