HebbrixBack to Home
Voice Agents

"Hi, I'm calling about my appointment." Your agent already knows which one.

Voice has no room for hesitation. When a caller speaks, your agent has roughly 300 milliseconds before the silence feels awkward. Hebbrix fetches everything it knows about a caller on call-connect — in parallel with your greeting — so the context is already in place for a natural, informed response.

Start BuildingHow Memory Works

Memory off the critical path

The trick to voice isn't a magically instant database — it's fetching memory off the critical path. Hebbrix fires a search the moment a call connects, in parallel with your greeting, so a caller's history is in hand before they finish their first sentence.

Call connects (caller ID)
start
Memory search (in parallel)
sub-second
Caller's opening sentence
~2 to 3s of speech
Agent responds, fully briefed
context already loaded

Because retrieval runs on connect — overlapping your greeting and the caller's opening — it never competes with the per-turn response budget.

Anatomy of a voice call with memory

Three phases. Two API calls. Your agent goes from stranger to informed assistant before the caller finishes their first sentence.

Before

Call connects

  • •Caller ID triggers a memory search
  • •Hebbrix returns name, preferences, history
  • •Context injected into the agent's system prompt
  • •All of this happens on call-connect, before the first request
During

Conversation flows

  • •Agent speaks with full context from the start
  • •No "can you repeat your account number?"
  • •New facts extracted in real time with infer:true
  • •Knowledge graph connects related entities
After

Memory updates

  • •Call summary stored as a new memory
  • •Preferences and decisions saved to long-term
  • •Next call starts with even more context
  • •Old memories decay naturally over time

What your agent sees when a call connects

Caller context loaded automatically from previous interactions.

Incoming: +1 (503) 555-0147
4 MEMORIES
Caller
David Chen
Last Call
3 days ago
Open Items
Dental cleaning scheduled Thu 2pm. Wants to switch to Dr. Park.
Preferences
Prefers morning appointments. Has dental anxiety, responds well to calm tone.
Graph Connections
David → patient_of → Dr. Martinez. David → prefers → Dr. Park. David → insurance → Delta Dental PPO.

Works with any voice platform

Hebbrix is a REST API. It works with whatever voice stack you use.

VapiBland.aiRetell AIElevenLabsPlay.aiCustom SIP/WebRTC

One search call when the call connects. One store call when it ends. That's the entire integration.

The difference memory makes

Same caller, same question. Two very different experiences.

Without Memory

"Can I have your account number?"

"What was this regarding?"

"Would you prefer morning or afternoon?"

"Let me transfer you to the right department."

Generic. Repetitive. Caller frustrated.

With Hebbrix

"Hi David, I see your account right here."

Caller identified

"Are you calling about your Thursday appointment?"

Open items recalled

"I know you prefer mornings. How about 9am?"

Preferences remembered

"I see you wanted to switch to Dr. Park. I can handle that now."

History applied

Personal. Efficient. Caller delighted.

How Hebbrix features map to voice

Each capability solves a specific voice problem.

FeatureHow it helps
Sub-second searchFast enough for real-time turn-taking. No awkward pauses while the agent thinks.
3-tier memoryRecent call context in short-term. Ongoing relationships in medium. Permanent preferences in long-term.
Knowledge graphConnects callers to their doctors, appointments, insurance plans, and related entities automatically.
Smart ingestionFeed in call transcripts with infer:true. Hebbrix extracts the facts without any parsing code.
Multi-tenant collectionsOne deployment serves all callers. Each person gets isolated memory with no cross-contamination.
Natural decayOutdated scheduling info fades. Core preferences persist. Memory stays relevant without cleanup.

Give your voice agents a memory

Start with the free tier. 1,000 credits/month (≈ 1,000 API operations), full hybrid search, sub-second retrieval. No credit card needed.

Start Building FreeIntegration Guide