Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
Memoket — access your recording transcripts, summaries, and key takeaways over MCP.
Search, read, create and edit your Memol notes from Claude.
Personal memory layer for AI assistants.
- Memory Store: Stores a piece of text as a durable memory in the user's MemoraEU account, with an optional category and tags. Applicable to preferences, decisions, biographical facts and long-lived con
- Memory Recall: Searches the user's stored memories by meaning rather than exact wording, using a natural-language query. Returns the closest matches with a relevance score, their category and their ID
- Memory Delete: Deletes one of the user's memories, identified by its full or partial ID. The memory stops appearing in searches and listings and its search vector is removed. Returns whether a matchin
Create and look after online memorials for people and pets who have died.
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Long-term memory for AI assistants.
Count keys in a JSON object.
MemBridge Memory MCP Server allows you to share your memory across multiple AI tools like Claude, ChatGPT, Cursor, and more.
- MemBridge List Records: Retrieve a comprehensive list of all MemBridge Memory Records stored for the authenticated user. MemBridge Memory Records contain information that users have explicitly saved f
- MemBridge Create Record: Create and save a new MemBridge Memory Record when the user explicitly requests to save information for future reference. Records persist across chat sessions and AI tools. Ty
- MemBridge Update Record: Update an existing MemBridge Memory Record's content and title while preserving the original creation timestamp. The updated timestamp will be refreshed. Useful for consolidat
Portable AI memory shared across models and harnesses - plain markdown you own.
Updated 9-16-25 Fixed EV issues Connections should be solid!
- Get Context: Get or create context for a topic or project
- Update Context: Update or add context for a topic or project
- List Topics: List all available topics/projects
The SQLite of AI Memory — persistent, zero-dependency memory for any LLM application.
- Remember: Store a new memory in MemoryMesh. Use this to save facts, preferences, decisions, or any information that should persist across conversations.
- Recall: Recall relevant memories from MemoryMesh using semantic similarity and keyword matching.
- Forget: Permanently delete a specific memory by its ID. Searches both project and global stores.
Persistent long-term memory for AI agents.
- Memoryoss Recall: Search your long-term memory. Call this FIRST at the start of every conversation turn to retrieve relevant context from previous sessions. Pass the user's question or topic as the qu
- Memoryoss Store: Save important information to long-term memory so you can recall it in future sessions. Store facts, decisions, user preferences, project context, and key findings. Call this whenever
- Memoryoss Update: Update an existing memory by ID. Use this when information has changed - e.g. a user preference was corrected or a fact is outdated. Pass the memory ID from a previous recall result.
Give every AI you use one shared, permanent memory.
MemoryRouter is a persistent AI memory layer delivered as an MCP memory server.
- Search Memories: Use this when the user asks about a prior decision, preference, person, project, or other fact that may be in their connected MemoryRouter vault. Semantically searches only the OAuth-
- Store Memory: Use this only when the user explicitly asks to remember something or confirms a proposed durable fact. Saves concise user-approved content to the OAuth-selected vault; do not use it for
- Memory Status: Use this when the user asks whether MemoryRouter is connected, which opaque vault binding is active, or how many memories/tokens the connected vault contains. Does not reveal the memory
Durable, inspectable memory for AI agents and coding assistants.
- Search Memory: Search the user's stored memory for context relevant to a question and return the best matches. Use this before answering anything that depends on what the user told you previously.
- Add Memory: Store a durable fact or preference about the user. Text is run through extraction, so conversational filler is discarded and near-duplicates are merged; a skipped result is normal and not
- List Memories: List the user's most recent memories without searching.
Search and read MemorySync's API, SDK, and integration documentation from an MCP-compatible coding assistant.
- Search Docs: Search the MemorySync documentation and return matching pages with their headings and a link to the full Markdown text.
- Read Doc: Read the full Markdown text of one documentation page. Prefer this over a search snippet when you need exact method names, parameters, fields or limits.
- List Doc Sections: List the top-level documentation sections and how many pages each contains, to orient before searching.
Find useful knowledge as conversations unfold and draft it privately after confirmation.
https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk...).
- Mempalace Status: Summarize the current user's memory palace: total drawers, counts per wing, counts per room. Use when you need grounding before writes or searches, or when the user asks what is stor
- Mempalace Add Drawer: Persist a new memory drawer: writes to the user's D1 row, then embeds and upserts to Vectorize for later semantic search. Use when the user wants to remember something long-term
- Mempalace Search: Search the current user's memories by meaning (Vectorize embeddings), optionally scoped to wing and/or room. Use when answering questions that depend on prior stored context, or befo
Personal MCP memory server that runs on your Android phone via Termux.
- Memplato Status: Palace overview — total drawers, wings, rooms
- Memplato Search: Semantic search in memplato drawers
- Memplato Add Drawer: Save memory/content into memplato
mempool.space MCP — Bitcoin block explorer + mempool/fee stats
Shared project memory that keeps teammates and AI agents aligned across sessions.
Persistent memory for AI agents.
AI continuity and Library Templates: memories, profiles, rules, tasks, and checkpoints.
memsprout is a shared AI-context layer for teams — persistent memory your agents search and update over MCP.
- Store Memory: Save a memory — the single capture tool for everything you want to persist. Give it a concise, descriptive title whenever it holds durable knowledge — a decision, a procedure, a fact, a
- Search Memories: Semantic search across all memories you can read — your personal vault and every space you belong to. Each result is labeled personal or space-scoped. Pass space_id to narrow to a sin
- List Memories: List recent memories in reverse-chronological order (most recently updated first) across everything you can read — personal and all your spaces. Pass space_id to narrow to one space. Fi
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
Memxus is multi-platform persistent memory for AI assistants.
- Remember: Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend
- Recall: Search long-term memory. Pass collection (and/or tags, type) to search only that scope — e.g. collection=project:henry-memory for project questions, collection=personal:preferences for tastes.
- Get Context: Build a formatted context block for the current topic. Use collection to limit results to one domain (project, preferences, etc.).
Track how your brand appears in AI answers: rank, mentions, sentiment, share of voice.
Missing a connector?
Tell us which service you need, or add your own MCP server: we will check it and publish it in the catalog.
Suggest a connector