AgentSidekick

User Preference Memory

Remembering a user's preferences and personal context. As of 2026-11-21, 13 indexed products offer it (10 with full profiles), in 3 forms: 11 MCP servers, 1 Agent skill, 1 Plugin. 3 were published in the last 90 days, against 3 in the 90 days before. alive has the most GitHub stars, 100% of the total across 4 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 11 indexed · 8 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

User Preference Memory: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1sensefoldPersonal context for every AI: search, read, and write back to your private Markdown library.sensefold.app02mo ago
2contextLocal-first personal context over MCP: mail/calendar metadata, briefings, person lookups. No cloud.honeycrisp-suite02mo ago
3UseMyContext.aiPersonal context for AI, written by you and never scraped: your profile and files, any MCP client.usemycontext01mo ago
4DREAMHALLHuman-authored personal context before AI guidance, built through private structured reflection.dreamhall.app——
5AllClear Connect (OAuth, OIDC, and MCP)Verified identity plus consented personal context, starting with medical records, images & insuranceallclearid.com——
6Project FingerprintPersonal context and preferences for AI via OAuth-approved profile sections and taste data.projectfingerprint.com——
7cachetank-mcpCacheTank MCP server gives every AI tool your personal context so you never start from zero.jacobsilver7-art——
8mcp-gera-mindGeraMind MCP (placeholder) — personal context vault for AI agents. Launching 2026.geraservicesuk——

Agent skills 1 indexed · 1 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

User Preference Memory: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1ego-browserWhen you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is a Chromium browser designed for both human users and AI Agents. Agents can use the user's logged-in websites and personal context to complete tasks and collaborate smoothly with the user through the browser interface. Therefore, prefer ego-browser over built-in browsers or other web tools.citrolabs—today

Plugins 1 indexed · 1 profiled

1 of these are Claude plugins, which Claude Code documents (protocol-level). DER

User Preference Memory: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1alivePersonal Context Manager for Claude Code. Your life in walnuts.alivecontext1323d ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

No integrations named

None of the products matched here names a tracked third-party service.

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
user preferences0
personalization memory0
user profile memory0
remember preferences0
personal context13

Segment statistics

Whole catalogue (13 indexed products). Calculated 2026-11-21.

13DERIndexed products10 with full profiles
3DERLaunched, last 90 days3 in the 90 days before
9DERMomentum vs catalogue50 = same pace as the catalogue
100%DERLargest project's share of starsAcross 4 products with their own repository
1.000DERConcentration (HHI)About 1 equal-sized projects’ worth; highly concentrated
0SRCMedian starsPer product with its own repository
31%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 1.000 means stars are spread as if across about 1 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: User Preference Memory: score 61.0 HEU, competition Medium, confidence Low. Only 13 indexed products match "User Preference Memory", against 850 in Memory & State overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .