scanned May 12, 2026
Memory.store helps teams and individuals recall and share context from meetings, conversations, and decisions across various tools and platforms.
Tier 2 · Basic Presence
Scored by asking 15 questions a buyer of a ai-ml product asks, then grading this site’s own pages: answered, hedged (partial or vague), or silent (no page answers it). How scoring works
15 buyer questions · graded against the site’s own pages
Goes silent · getting-started · high importance
I want to test Memory.store before committing. How many memories or integrations can I create on the free tier before hitting a hard limit?
Goes silent · integration · high importance
We use Fathom for sales calls and need to keep recordings for 7 years for compliance. Does Memory.store sync and retain Fathom transcripts indefinitely, or do they expire?
This report is public. Own memory.store? Claiming is free: crawl every page, re-audit as you fix, and track your score over time.
Sign in to claim78 points sit between memory.store and 100: 15 open questions and 9 missing protocol checks, ordered by estimated payoff.
Point estimates are per fix under scoring v2. They are not additive to a promised total.
I want to test Memory.store before committing. How many memories or integrations can I create on the free tier before hitting a hard limit?
No page on the site addresses this.
Add a dedicated pricing/plans page or FAQ section that specifies free tier limits on memories and integrations, with clear upgrade thresholds.
confidence high · grounding synthesized · weight 0.00 · Absent
We use Fathom for sales calls and need to keep recordings for 7 years for compliance. Does Memory.store sync and retain Fathom transcripts indefinitely, or do they expire?
No page on the site addresses this.
Add a data retention/FAQ section to the Fathom integration page specifying retention periods, whether storage is indefinite, and compliance archiving capabilities for regulated industries.
confidence high · grounding world-knowledge · weight 0.00 · Absent
My security team requires SOC 2 Type II for any tool handling meeting data. Is Memory.store SOC 2 certified, and if so, can I request the report?
No page on the site addresses this.
Create a dedicated security/compliance page that explicitly states SOC 2 Type II certification status, audit scope, and how prospects can request the report under NDA.
confidence high · grounding synthesized · weight 0.00 · Absent
I'm evaluating Memory.store for my 3-person startup team. What's the minimum number of seats I have to buy on the team plan, or can I pay per user?
No page on the site addresses this.
The pricing page at /pricing exists (linked in navigation) but was not retrieved. Ensure the pricing page is crawled and indexed, including details on team plan minimum seats, per-user vs. flat pricing, and startup/small team options.
confidence high · grounding world-knowledge · weight 0.00 · Page missing
We're building an internal tool that would write to Memory.store via API. What's the daily rate limit for API calls, and is there a burst allowance?
No page on the site addresses this.
Create a dedicated API documentation page or section covering rate limits, authentication, and usage quotas. Consider adding this to a /docs or /api-reference section.
confidence high · grounding world-knowledge · weight 0.00 · Absent
I have a 3-hour workshop transcript that's about 50,000 words. Is there a maximum memory size or character limit that would truncate this?
No page on the site addresses this.
Add documentation on memory limits, maximum transcript size, or character limits to the pricing page, FAQ, or integration documentation—especially for the Fathom meeting transcript use case where users would reasonably want to know if long workshops or multi-hour recordings are fully supported.
confidence high · grounding synthesized · weight 0.00 · Absent
If we decide to leave Memory.store, can we export all our memories in a structured format like JSON or Markdown, or are they locked in?
No page on the site addresses this.
Add a dedicated data portability/export page or FAQ section explaining how users can export their memories in structured formats (JSON, Markdown, etc.) before account deletion.
confidence medium · grounding synthesized · weight 0.00 · Absent
We have EU employees and need to ensure their meeting data stays in EU data centers. Does Memory.store offer data residency controls or EU-only hosting?
No page on the site addresses this.
Add a dedicated data residency or regional hosting page that explicitly states whether EU data centers are available, whether customers can restrict data to specific regions, and which compliance frameworks (GDPR, DPA, etc.) are supported. The current privacy policy only mentions that data may be processed in the United States and other countries without any customer controls.
confidence high · grounding stated · weight 0.00 · Absent
Your 2026 sync article mentions automatic context sharing between AI tools. What happens if I edit the same memory in Cursor and ChatGPT simultaneously—how are conflicts resolved?
No page on the site addresses this.
Add a technical FAQ or documentation section explaining conflict resolution behavior for simultaneous edits, including whether last-write-wins, merge strategies, or locking mechanisms are used.
confidence high · grounding world-knowledge · weight 0.00 · Absent
I travel frequently with spotty wifi. Does the Raycast integration cache memories locally, or do I need internet to access everything?
No page on the site addresses this.
Add a section to the Raycast setup guide or FAQ addressing offline behavior: whether memories are cached locally, what functionality works without internet, and any sync-on-reconnect behavior.
confidence medium · grounding world-knowledge · weight 0.00 · Absent
Your prompt templates guide mentions variables. Do you use Handlebars, Jinja2, or a custom syntax—and can I set default values if a memory field is empty?
No page on the site addresses this.
Add documentation explaining the template variable syntax used in Memory Store prompts and whether default values can be set for empty memory fields.
confidence high · grounding world-knowledge · weight 0.00 · Absent
We're considering Memory.store for 200+ employees. Is there a guaranteed response time SLA for enterprise support, and does it include weekend coverage?
No page on the site addresses this.
Create a dedicated /enterprise or /support page with SLA details, response time commitments, and coverage hours for enterprise customers.
confidence high · grounding world-knowledge · weight 0.00 · Absent
A buyer gets something, then has to guess the rest. Expand any row for the evidence and the fix.
When I pull a memory into Claude via your integration, does it count against my Claude context window, or does Memory.store use some kind of retrieval mechanism?
Memory Store uses a retrieval mechanism rather than counting memories against your Claude context window. The system provides MCP tools including 'Checkin' which 'Loads your active context at the start of each conversation' and 'Recall' which 'Search past conversations by topic, time, or entities.' This suggests memories are retrieved on-demand rather than being pre-loaded into context. However, the chunks do not explicitly state whether retrieved memories consume context window tokens once pulled in, or whether there's any special handling to minimize context usage.
Add explicit documentation explaining whether retrieved memories consume Claude context window tokens, and if so, how Memory Store optimizes for context efficiency (e.g., summarization, relevance ranking, or compression).
Where we looked: /guides/memory-store-user-guide
confidence medium · grounding synthesized · weight 0.65 · Vague
Our team threads important decisions in Slack. Does the Slack integration capture full thread context or just the parent message when I save to Memory.store?
The chunks indicate that Memory Store for Slack extracts "decisions, projects, and blockers from messy threads" and enables retrieving "decisions and threads instantly," suggesting thread context is captured beyond just parent messages. However, there is no explicit confirmation of whether full thread context (all replies) or just extracted entities are saved.
Add explicit documentation on the Slack integration page clarifying whether full thread content is indexed or only AI-extracted entities/summaries, with technical details on thread depth handling.
Where we looked: /integrations/slack, /integrations/slack, /blog/sync-context-between-ai-tools-automatically-2026
confidence medium · grounding synthesized · weight 0.65 · Vague
For the Cursor integration, does Memory.store inject memories as system prompts, user messages, or via Cursor's rules file? I need to know for prompt engineering consistency.
Memory Store for Cursor uses system prompts, not Cursor's rules file or user messages. The integration provides ready-to-use system prompt templates that you paste into Cursor's AI settings. Specifically, the Developer Template is 'Optimized for coding workflows in Cursor, Claude Code, Windsurf, and similar tools' and instructs the AI 'You have access to Memory Store – persistent memory across all coding sessions.' However, the chunks do not explicitly confirm whether this is entered as a system prompt in Cursor's settings or if there's any alternative injection method via Cursor's rules file (.cursorrules).
The Cursor guide at https://memory.store/guides/memory-store-for-cursor likely contains the specific implementation detail about whether memories inject via system prompts, user messages, or Cursor's rules file, but the retrieved chunks only show heading anchors ('Configure Cursor Rules') without the body content. Expand the full page content or the 'Configure Cursor Rules' section specifically.
Where we looked: /guides/memory-store-prompt-templates, /guides/memory-store-prompt-templates, /guides/memory-store-for-cursor
confidence medium · grounding synthesized · weight 0.65 · Collapsed
The other half of the score: 16 checks for the files and headers agents look for. The 9 below are installs, not judgment calls, and most are an afternoon. Expand any for the snippet and the standard it follows. They sit after the queue because none of them changes what your pages say.
Sitedex generates this file from your crawl. Grab it in Files from this audit below.
Standardllmstxt.orgCommunity spec
User-agent: * Content-Signal: search=yes, ai-input=yes, ai-train=no Allow: /
StandardCloudflare proposalVendor proposal
StandardSitedex metricSitedex metric
StandardRFC 9110 + 7763IETF RFC
Sitedex generates this file from your crawl. Grab it in Files from this audit below.
StandardModel Context ProtocolCommunity spec
StandardOpenAPI SpecIndustry standard
Sitedex generates this file from your crawl. Grab it in Files from this audit below.
StandardW3C WebMCP draftW3C / WHATWG
<link rel="canonical" href="https://memory.store/" />
StandardRFC 6596IETF RFC
Sitedex generates this file from your crawl. Grab it in Files from this audit below.
StandardSchema.org + JSON-LDIndustry standard
Already passing 7 of 16: robots.txt, sitemap.xml, AI crawler access, Server-rendered content, Meta descriptions, HTML lang attribute, Sitemap lastmod.
Sitedex already serves memory.store as an MCP endpoint. Ask memory.store anything an AI agent might ask, and see what its index returns. (To score your own site, use the form below.)
For developers and the engineer-on-call: copy these into your tools or your site.
Files from this audit
Built from this crawl. Download or copy each, then install it at the path noted.
Built from this crawl. Install at /llms.txt so agents start here.
Organization JSON-LD, pre-filled from this crawl. Wrap in a ld+json script.
MCP server card built from this crawl. Host at /.well-known/mcp/server-card.json.
WebMCP discovery manifest built from this crawl. Host at /.well-known/webmcp.json.
MCP endpoint
https://mcp.sitedex.dev/s/memory-store/mcp
The URL anyone's agent points at. Read-only; safe to share.
Claude Code
claude mcp add memory --transport http https://mcp.sitedex.dev/s/memory-store/mcp
One command, then the agent has it.
Cursor / Continue
{
"mcpServers": {
"memory": {
"url": "https://mcp.sitedex.dev/s/memory-store/mcp"
}
}
}Drop into mcp.json.
WebMCP: two parts
WebMCP-capable browsers run the widget at runtime. Crawlers without JS rendering need the discovery manifest to find your tool surface. Install both.
1 · Widget script
<script async src="https://sitedex.dev/widget.js"></script>
Drop in <head>. WebMCP-capable browsers (Chrome 146+ Origin Trial) call navigator.modelContext.provideContext() via this script.
2 · Discovery manifest
{
"$schema": "https://wellknownmcp.org/schemas/webmcp.json",
"name": "memory.store",
"tools": [
{ "name": "search", "description": "Search memory.store's indexed content." },
{ "name": "get_page", "description": "Fetch a page from memory.store as markdown." }
]
}Host alongside the script at /.well-known/webmcp.json. Crawlers that don't render JS rely on this.
Your turn
See which of these questions your site goes silent on.
Free, about 5 minutes. We crawl your site, test it against the buyer questions your category asks, and name what’s vague, contradictory, or missing, plus the files AI agents look for.