GroundMemory

Your agent now has structured, searchable memory that persists across every session - long-term facts, a user profile, agent instructions, an entity graph, and daily logs - all managed automatically. No changes to your agent's code required.

This config works with any MCP-compatible client, including AI coding assistants (Cursor, Cline, Windsurf, Claude Code, Codex CLI), AI desktop clients (Claude Desktop, Open WebUI), and agent frameworks and platforms (LangChain, CrewAI, AutoGen, Google ADK, LiteLLM, n8n).

Without memory, every session in every AI tool starts from zero. With GroundMemory, agents can maintain continuity across time, accumulate knowledge, and behave like they actually know the person they're working with. It makes conversations stateful, fluid, and natural.

The exchange below is an example of what this looks like. The first session happens inOpen WebUI. The second session happens inCline (VS Code)- a completely different tool, with no shared history other than the GroundMemory workspace both are connected to.

Session 1 - Open WebUI (first ever session)

Hey! Welcome - this is the start of something good. I have persistent memory, so anything we talk about I'll carry with me into every future session. No need to repeat yourself down the line.

A couple of quick things to get us started:

- What should I call you?
- Anything you always want me to keep in mind - how you like to work, things to avoid, preferences?

I'm Alice, a backend engineer working on a SaaS product. We're building a task management API - Node.js, PostgreSQL, Redis for caching, and we're planning to use BullMQ for job queues.

Got it, Alice. Backend engineer, task management API - Node.js, PostgreSQL, Redis, BullMQ for queues. I'll keep that as the baseline for everything we work on together.

Anything else before we dive in? Or are you ready to get into it?

The agent writes what it learned to memory.

Session 2 - Cline in VS Code (different tool, same GroundMemory workspace)

Hey. What tech stack did we agree to use for the task management API?

You're building a task management API with Node.js, PostgreSQL, Redis for caching, and BullMQ for job queues. That's what we landed on.

No introduction. No setup. The agent already knows.

A single identity across every AI tool you use.Your memory workspace is not bound to one assistant. Connect Claude Desktop, Cursor, Cline, and any other MCP-compatible tool to the same GroundMemory server and they all share the same memory - your preferences, your stack, your ongoing work. You stop being a stranger every time you open a different tool. There is something genuinely different about beingknownrather than just answered - it shifts the relationship from transactional to collaborative, and removes the quiet tax of re-establishing context that most people don't notice until it's gone.

A coding/personal assistant that builds a profile over time.After a few conversations, it knows your schedule, your priorities, how you like to communicate, your tech stack, your preferred patterns, the architectural decisions you've already made. It doesn't need to ask.

A research agent that constructs a knowledge graph.As it reads papers and sources across many sessions, it records entities, relationships, and findings.

A customer-facing agent with per-user memory.In multi-user setups, each user gets their own workspace - preferences, history, ongoing context - giving every interaction a personalised, stateful feel without any custom infrastructure.

A long-running autonomous agent that survives context limits.Each new session callsmemory_bootstrapto reload persisted facts, so the agent picks up exactly where the last one left off.

Automatic backup and restore when memory grows large.When the memory context exceeds a configurable token threshold, GroundMemory automatically backs up the workspace to a timestamped zip archive before asking the agent to compact it. You can also trigger a backup manually at any time withgroundmemory --backup. If something goes wrong, a single command restores the previous state:groundmemory --restore -1.

Most agents are stateless. They ask the same questions again, repeat the same mistakes, and lose track of the user's preferences and ongoing work. This is not a model limitation - it is missing infrastructure.

GroundMemory provides that infrastructure. It gives your agent a structured, searchable memory that persists across sessions, organised into distinct tiers with clear ownership:

At session start, all of these files are assembled into a compact system prompt block your agent receives as context - calledbootstrap injection. At search time, all tiers are queried together or individually.

- Hybrid search- BM25 keyword scoring and vector cosine similarity are combined and re-ranked in a single query, so recall is accurate even when the wording differs from what was stored.
- Zero-setup mode- withprovider: none, GroundMemory runs entirely on SQLite with FTS5. No API key, no GPU, no extra dependencies.
- Pluggable embedding providers- swap between a local sentence-transformers model, any OpenAI-compatible endpoint (OpenAI, Ollama, LM Studio, LiteLLM), or BM25-only without touching your agent code.
- Workspace isolation- each project, user, or agent gets its own directory-backed workspace with independent memory, relations, and daily logs.
- Relation graph with semantic deduplication- the graph automatically suppresses near-duplicate triples using configurable cosine similarity thresholding.

Comparison reflects publicly documented features as of MAR-2026. Submit a PR if anything is inaccurate.

¹ memsearch supports local ONNX embeddings + Milvus Lite, but requires initial model download
² Mem0 organizes memory into Conversation, Session, User, and Organizational layers
³ Letta uses Core Memory blocks (in-context) + Archival Memory (vector DB) + Conversation Search
⁴ Mem0 offers an MCP integration but the primary interface is the Python/Node SDK
⁵ Letta agents can consume external MCP servers as tools; Letta itself is not an MCP server
⁶ GroundMemory timestamps all relations but does not support date-range queries.

In normal mode, GroundMemory exposes four tools:memory_bootstrap,memory_read,memory_write, andmemory_relate. An optionalmemory_listtool can be enabled via config. In dispatcher mode, all actions are routed through a singlememory_toolcall - useful for clients that perform better with fewer tools in scope.

When using the MCP server, instruct your agent to callmemory_bootstrapat the start of every session before doing anything else, if you find out that it doesn't do that by default. This loads the full memory context (MEMORY.md, USER.md, AGENTS.md, RELATIONS.md, daily logs) into the conversation. Clients that support the MCP Prompts primitive (Cline, Claude Desktop) can instead use thememory_bootstrap_promptprompt from their Prompts panel.

When using the Python API, callsession.bootstrap()and pass the result as your system prompt - no tool call is needed.

┌─────────────────────────────────────────────────────┐ │ AI Agent / LLM │ │ (OpenAI, Anthropic, or any framework) │ └────────────────────┬────────────────────────────────┘ │ tool calls + bootstrap prompt ▼ ┌─────────────────────────────────────────────────────┐ │ MemorySession │ │ workspace · index · provider · config │ └───────┬──────────────┬──────────────────────────────┘ │ │ ▼ ▼ ┌───────────┐ ┌───────────────────────────────────┐ │ Workspace │ │ MemoryIndex │ │ │ │ SQLite + FTS5 (BM25 keyword) │ │ MEMORY.md │ │ + optional vector store │ │ USER.md │ │ hybrid re-ranking + MMR │ │ AGENTS.md │ └──────────────┬────────────────────┘ │ RELATIONS │ │ │ daily/ │ ▼ └───────────┘ ┌───────────────────────────────────┐ │ EmbeddingProvider │ │ NullProvider (BM25-only) │ │ SentenceTransformer (local) │ │ OpenAICompatible (HTTP API) │ └───────────────────────────────────┘

GroundMemory is designed around three values:
- Simplicity over features.Every addition must justify its complexity. A zero-dependency BM25-only mode must always work.
- Offline-first.The default configuration must not require an API key, a network connection, or a GPU.
- Test-driven.New behaviour ships with tests. The full suite must pass before any PR is merged.

The 1Password MCP server creates a bridge that allows MCP clients such as Codex and Kiro to manage your 1Password Environments with secure authorization prompts.

This is the 1st, easiest, and cheapest PPT, slides, presentation AI generation MCP Server in the world.

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.

A MCP server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.

Enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

An MCP server for WordPress plugin audits

Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.

Connect AI clients to Cal.com scheduling through the Model Context Protocol using the hosted server at mcp.cal.com or a local instance.