"memory" matching MCP servers:

Enables AI assistants to read training, sleep, recovery, nutrition, body composition, race and goal data, and with permission write workouts, daily targets, meal plans, logged meals and notes. Also supports checking for updates since the last look.

Lets Claude read and manage Speediance Gym Monster training data — session history, per-set logs, exercise progress, rowing and heart-rate stats, custom workouts and schedule — plus a coaching memory of goals, injuries and preferences. It runs self-hosted on the user's own machine, talking directly to the user's account and keeping stored data local.

Enables Claude to act as the memory and reasoning layer for nutrition tracking, letting users log meals from label photos or descriptions, save foods, recipes, meal-prep containers, and restaurant orders, record weigh-ins, and query targets, progress, and projections as tool calls. All writes are previewed with dry runs, checked for plausibility, and reversible.

Enables auditing speech intelligibility and acoustical distraction risk, modeling working-memory throughput penalties, and synthesizing pink or brown noise masking profiles for focused work.

Enables voice assistants to keep a persistent health memory across conversations, so allergies and temporary notes like a sore knee are remembered, expire on their own, and are checked against meals and daily calorie/macro goals as they are logged. Provides meal logging with allergy and diet warnings, memory recall and two-step forgetting, and daily weigh-ins that are never spoken aloud.

Enables users to organise messy symptom notes into a clearer, portable appointment-preparation record through privacy-conscious tools for ChatGPT and Codex. It processes submitted text in memory without intentionally persisting it, supporting symptom diary capture and appointment-prep workflows.

Enables Alexa+ and other MCP clients to maintain long-term elder-care memory, deliver proactive medication reminders, run daily check-ins, generate doctor-visit briefs and dashboards, and autonomously alert family members based on risk signals.

An AI training coach MCP server that integrates with Garmin Connect to provide science-based load management, code-enforced injury gates, and persistent coaching memory, keeping data local.

Your AI running coach that actually remembers. An MCP server with persistent memory that connects your Strava data to Claude — tracking your zones, pace trends, injuries, and goals across sessions so coaching advice stays current.

Enables consented, daily Alexa check-ins that score speech and memory answers against a personal baseline, flag sustained drift to family, produce clinician summaries, and export de-identified data for research. It also provides MCP tools, resources, prompts, and MCP Apps views for compatible agent hosts.

Enables elders facing memory loss, disability, or language gaps to converse with Alexa in their own language, receiving gentle memory support, medication reminders, two-way family translation, translated narration of their stories, and Ring doorbell monitoring—with check-ins screened for sentiment and safety so that loneliness nudges family members and true emergencies trigger a Step Functions escalation to the care circle. It provides 12 tools, 3 resources, and 2 prompts over Streamable HTTP with OAuth 2.1, and also deploys as a stateless AWS Lambda.

Enables an agent to run multi-turn, multi-rung senior wellness escalations over Streamable HTTP — opening or resuming an incident, issuing fail-closed check-in prompts, advancing or standing down rungs, notifying caretakers, and requesting a simulated call. Session state is keyed by household and incident, so each tool call returns a snapshot that carries one memory across turns rather than isolated requests.

An Alexa+ add-on backed by a self-hosted MCP server that gives Alexa a memory for your training: log sets by voice, ask for personal records, get today's plan and protein targets.

A remote MCP server that lets AI assistants such as Claude, ChatGPT, and any MCP client ask about a user's Apple Health data, with answers produced live by the user's iPhone via HealthKit. Health data is forwarded through process memory only — never written to disk — and covers sleep, workouts, metric series, health overviews, and user-defined custom metrics.

Exposes five tools that let Claude query training data from the intervals.icu API directly, covering weekly volume, fitness/fatigue/form, recent activities with per-rep detail, wellness metrics, and pace-at-heart-rate trends, with in-memory caching of upstream responses.

Theta Health MCP is a HIPAA-complaint intelligent memory layer for your health data — ready to plug into Cursor, Claude, and any AI agent. Query health data and ask health questions directly in your dev workflow.

An MCP server that turns an LLM into a nutrition assistant with persistent, database-backed memory, enabling conversational food logging with structured confirmation, accurate macro tracking, and multi-user support.