Memory API

Hubify uses a four-layer memory model to give agents persistent context across sessions:

Layer	Store	Contents
`messages`	`userMemory`	Captain—agent conversation history
`preferences`	`userMemory`	Captain’s persistent preferences and working style
`learnings`	`agentLearnings`	Facts and patterns agents have extracted from experiments
`decisions`	`labDecisions`	Lab-level policy decisions logged by the Captain

Get Memory

string

required

Convex ID of the lab.

string

default:"all"

Which layer to return: messages, preferences, learnings, decisions, or all.

# All layers
curl "https://www.hubify.com/api/v1/memory?labId=$LAB_ID" \
  -H "Authorization: Bearer $HUBIFY_TOKEN"

# Just learnings
curl "https://www.hubify.com/api/v1/memory?labId=$LAB_ID&layer=learnings" \
  -H "Authorization: Bearer $HUBIFY_TOKEN"

object[]

Recent user—agent messages (up to 50, newest first). Only present when layer=messages or layer=all.

Show Message

string

One of user, assistant.

string

Message text.

string

Chat session ID.

number

Unix ms.

object[]

Captain preferences. Only present when layer=preferences or layer=all.

Show Preference

string

Preference key (e.g., default_model).

string

Preference value.

object[]

Agent-extracted facts and patterns. Only present when layer=learnings or layer=all.

Show Learning

string

Extracted fact or pattern.

string

Agent that extracted the learning.

string

Source experiment, if any.

number

0-1 confidence score.

number

Unix ms.

object[]

Lab policy decisions logged by the Captain. Only present when layer=decisions or layer=all.

Show Decision

string

Short decision title.

string

Why this decision was made.

number

Unix ms.

Append Memory

string

required

Convex lab ID.

string

required

Target layer: messages, preferences, learnings, or decisions.

string

Message or learning content (for messages, learnings).

string

Message role (user or assistant) — required for messages layer.

string

Preference key — required for preferences layer.

string

Preference value — required for preferences layer.

string

Decision title — required for decisions layer.

string

Decision rationale — required for decisions layer.

# Log a decision
curl -X POST https://www.hubify.com/api/v1/memory \
  -H "Authorization: Bearer $HUBIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "labId": "$LAB_ID",
    "layer": "decisions",
    "title": "Use H200 SXM for MCMC runs only",
    "rationale": "CPU is sufficient for Fisher matrix forecasts; reserve GPU for MCMC."
  }'

Overview

Labs

Data

Compute

Lab Ops

Memory

Memory API

Get Memory

Append Memory

​Memory API

​Get Memory

​Append Memory

Memory API

Get Memory

Append Memory