---
title: "Record a conversation into an agent's memory of a contact"
method: POST
path: "/voice/agents/{agent_id}/memory"
tags: ["Voice"]
---

# Record a conversation into an agent's memory of a contact

`POST /voice/agents/{agent_id}/memory`

## Request

- Base URL: `https://be.graph8.com/api/v1`
- URL: `https://be.graph8.com/api/v1/voice/agents/{agent_id}/memory`
- Auth: HTTP bearer

Teach an agent what was said, so the next call is not the first one.

This is how a conversation that happened somewhere ELSE - your own product,
a human rep, another channel - becomes context the agent has. Calls the
agent places itself are recorded already; this route exists for everything
it did not witness.

Written to two places by voice: a durable interaction row and the vector
memory retrieval reads. There is no delete for a memory on this surface.

The agent is named in the PATH for a readable URL. Voice's own handler
scopes the write by `(org_id, contact_id)`, so the memory attaches to the
contact within the caller's org either way.

## Path parameters

- `agent_id` string, required: The agent doing the remembering.

## Headers

- `Authorization` string, nullable
- `X-Target-Org-Id` string, nullable

## Request body

- BodyUpdateAgentMemoryVoiceAgentsAgentIdMemoryPost
  - `contact_id` string, required: Who the conversation was with.
  - `interactions` unknown[], required: Ordered messages, each `{"role": "user"|"assistant", "content": "..."}`. Oldest first.
    - unknown
  - `session_id` string, nullable: Groups messages into one conversation. Generated when omitted.
  - `actor` string, nullable: Who the human side was.
  - `interaction_type` string: Channel: "chat", "email", "phone_call", ...

## Response `200`

Successful Response

- ApiResponseVoicePayload
  - `data` VoicePayload, required: One voice object - a collection, an agent, a route, a chat. Open-shaped: voice adds fields to these bodies on its own release cadence and a dropped-or-added key must not be a 500 in this service.
  - `pagination` PaginationMeta
    - `page` integer, required: Current page number (1-indexed)
    - `limit` integer, required: Items per page
    - `total` integer, required: Total number of items
    - `has_next` boolean, required: Whether there are more pages
    - `next_cursor` string, nullable: Opaque cursor for the next page; null when there are no more items. Pass it back as the `cursor` query param to fetch the following page without computing page numbers.
    - `total_available` integer, nullable: Search endpoints only: how many records really match, when known. Can be larger than `total`, which is capped at the 10,000 results that can be paged. For company search this is a distinct-company estimate. Null when unknown; absent outside search.
    - `total_is_lower_bound` boolean, nullable: Search endpoints only: true when more records match than `total` shows (the result set is larger than the 10,000 results that can be paged). Absent outside search.
    - `notes` string[], nullable: Search endpoints only: plain-language notes about the result, e.g. that more records match than can be paged, or that a reversed `between` range was put in order.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/graph8/apis/graph8-developer-api.md) · [All operations](https://skmtc.dev/graph8/apis/graph8-developer-api/llms.txt) · [OpenAPI document](https://skmtc.dev/graph8/apis/graph8-developer-api/revisions/89fc11143b70?raw)