Personal Agents

Build assistants that truly know their users

Personal agents need to remember preferences, track evolving interests, and connect the dots between different aspects of a user’s life. With Headkey, your assistant builds a persistent model of who they’re helping.

See Demo Below

Three Primitives, One Cognitive Architecture

Each primitive serves a different purpose. Here's how they work for this use case.

Memories

Remember everything the user shares

Preferences, past conversations, important dates, project notes — all searchable by natural language across every session.

rememberrecallforget
{
  "content": "User prefers dark mode in all IDEs and uses Vim keybindings.",
  "tags": [
    "preferences",
    "development"
  ],
  "importance": "normal"
}

Beliefs

Build an evolving user model

"User prefers morning meetings" starts as a weak belief and strengthens over time. When preferences change, the old belief is superseded — not just overwritten.

believebeliefs
{
  "statement": "User prefers morning meetings before 10am",
  "confidence": 0.75,
  "subject": "User",
  "object": "meeting schedule"
}

Relationships

Connect people, projects, and interests

The agent maps how contacts relate to projects, how interests connect, and which topics come up together. Context is linked, not flat.

relateentities
{
  "subject": "Sarah Chen",
  "object": "Q4 Product Launch",
  "predicate": "leads"
}

Flat Memory vs. Structured Cognition

What changes when your agent has a mind, not just a vector store.

DimensionFlat Memory (RAG)Headkey
Personalization depthKeyword matching on stored notesEvolving belief model with confidence scores
Preference changesOld and new preferences conflict silentlyBelief supersession tracks how preferences evolve
Connected contextFlat list of disconnected factsGraph of people, projects, and interests
Privacy controlAll-or-nothing sharingVisibility scopes: private, scoped, or org-wide

See It in Action

A personal assistant that remembers preferences, builds an evolving user model, and connects people to projects.

Step 1 of 5
> The assistant stores user preferences during a conversation.
Tool Call: remember
|

Start building your personal agent

Free to start. Add persistent cognition to any MCP-compatible agent in 60 seconds.

Explore Use Cases