> This page is for version v4 (default).
> For other versions, use one of these documentation indexes:
> - v4 (default): https://help.getzep.com/v4/llms.txt
> - v3: https://help.getzep.com/v3/llms.txt
> - v2: https://help.getzep.com/v2/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://help.getzep.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://help.getzep.com/_mcp/server.

# Add thread messages

POST https://api.getzep.com/api/v4/threads/{thread_uuid}/messages
Content-Type: application/json

Reference: https://help.getzep.com/sdk-reference/thread/add-messages

## Authentication

- `Authorization` header (required) (prefixed with ` Api-Key  `) — Type "Api-Key" followed by a space and the project API key.

## Request

### Path parameters

- `thread_uuid` (string, required) — Thread UUID

### Body (application/json)

This endpoint expects a v4.AddMessagesRequest.

- `messages` (list of v4.AddMessage, required) — The messages to add to the thread.
- `ignore_roles` (list of string, optional) — Message roles to skip during graph extraction; the messages are still stored.
- `return_context` (boolean, optional) — When true, returns the context block for the thread's most recent messages.
- `strict_ontology` (boolean, optional) — When true, prevents extraction of generic entity nodes that do not match the configured ontology.

## Response

### 202

Accepted

- `context` (string, optional) — The context block assembled from the graph after adding the messages, present only when return_context is true in the request.
- `messages` (list of v4.Message, optional) — The messages that were added, each including its assigned identifier.
- `task` (v4.Task, optional) — The asynchronous task that tracks the messages' graph extraction and indexing.

## Errors

### 400 Bad Request Error

Bad Request

- `error` (v4.ErrorBody, optional)

### 401 Unauthorized Error

Unauthorized

- `error` (v4.ErrorBody, optional)

### 404 Not Found Error

Not Found

- `error` (v4.ErrorBody, optional)

### 409 Conflict Error

Conflict

- `error` (v4.ErrorBody, optional)

## Types

### v4.AddMessage

- `content` (string, optional) — The content of the message.
- `metadata` (map from string to any, optional) — Custom metadata to store with the message. Max 10 keys. Values must be strings, numbers, booleans, or arrays of scalars.
- `name` (string, optional) — A customizable name for the sender of the message, for example "john" or "sales_agent".
- `reference_time` (string, optional) — The message's reference time, used for temporal reasoning rather than ingestion time. Defaults to the ingestion time.
- `role` (enum, optional) — The role of the message's sender.
  - Allowed values: `system`, `assistant`, `user`, `function`, `tool`
- `uuid` (string, optional) — Reserved for future use. Message identifiers are always server-assigned, so this field must be left unset.

### v4.Message

- `content` (string, optional) — The content of the message.
- `created_at` (string, optional) — The time Zep received the message.
- `metadata` (map from string to any, optional) — Arbitrary key-value metadata attached to the message.
- `name` (string, optional) — A custom name for the message's sender, for example a specific user or agent name.
- `processed` (boolean, optional) — Whether the message has finished being ingested into the user's graph.
- `reference_time` (string, optional) — The message's reference time: the time that the developer supplied on add, or the ingestion time when the developer supplied no time.
- `role` (enum, optional) — The role of the message's sender: system, assistant, user, function, or tool.
  - Allowed values: `system`, `assistant`, `user`, `function`, `tool`
- `thread_uuid` (string, optional) — The unique identifier of the thread this message belongs to.
- `uuid` (string, optional) — The unique identifier of the message.

### v4.Task

- `completed_at` (string, optional) — The time the task reached a terminal status; absent while it is still in progress.
- `created_at` (string, optional) — The time the task was created.
- `error` (v4.ErrorBody, optional) — The error that caused the task to fail; also present on a partial task when the worker can name a single cause.
- `progress` (v4.TaskProgress, optional) — The last processing stage a worker reported for this task. It is not cleared when the task finishes, so a completed task may still show its final stage.
- `result` (v4.TaskResult, optional) — Operation-specific output populated once the task reaches succeeded or partial, such as identifiers the operation could not return synchronously.
- `started_at` (string, optional) — The time a worker began processing the task; absent until then.
- `status` (enum, optional) — The task's current state: pending, processing, succeeded, partial, or failed.
  - Allowed values: `pending`, `processing`, `succeeded`, `partial`, `failed`
- `type` (string, optional) — The kind of asynchronous operation the task represents.
- `updated_at` (string, optional) — The time the task was last updated.
- `uuid` (string, optional) — The unique identifier of the task, used to poll its status.

### v4.ErrorBody

- `code` (string, optional)
- `details` (map from string to any, optional)
- `message` (string, optional)
- `param` (string, optional)
- `request_id` (string, optional)

### v4.TaskProgress

- `stage` (string, optional) — The most recent processing stage reported by the worker handling the task.

### v4.TaskResult

- `content_policy` (v4.TaskResultContentPolicy, optional) — The content policy outcome of the task.
- `edge_uuid` (string, optional) — The UUID of the edge that the task wrote.
- `edges` (list of v4.TaskResultEdge, optional) — The edges that the task wrote.
- `episode_uuid` (string, optional) — The UUID of the episode that the task added.
- `episodes` (list of v4.TaskResultEpisode, optional) — The content policy outcome of each message that the task added.
- `hyperedge_uuid` (string, optional) — The UUID of the hyperedge that the task created.
- `skill_uuid` (string, optional) — The UUID of the skill that the task imported.
- `source_node_uuid` (string, optional) — The UUID of the source node of the edge that the task wrote.
- `target_node_uuid` (string, optional) — The UUID of the target node of the edge that the task wrote.

### v4.TaskResultContentPolicy

- `category_keys` (list of string, optional) — The keys of the categories with a matched rule.
- `dropped_count` (integer, optional) — The number of derived candidates of the episode that were dropped.
- `failed_count` (integer, optional) — The number of episodes in the batch whose evaluation failed.
- `retained_count` (integer, optional) — The number of derived candidates of the episode that were published to the graph.
- `revision` (integer, optional) — The project revision number of the policy that the graph bound.
- `status` (enum, optional) — The evaluation status of the episode. pending means the evaluation has not finished, complete means every candidate was evaluated, and failed means ingestion retries were exhausted.
  - Allowed values: `pending`, `complete`, `failed`
- `violated` (boolean, optional) — Whether at least one derived candidate of the episode matched a rule.
- `violated_count` (integer, optional) — The number of episodes in the batch that a content policy flagged.

### v4.TaskResultEdge

- `edge_uuid` (string, optional) — The UUID of the edge.
- `source_node_uuid` (string, optional) — The UUID of the source node of the edge.
- `target_node_uuid` (string, optional) — The UUID of the target node of the edge.

### v4.TaskResultEpisode

- `content_policy` (v4.TaskResultContentPolicy, optional) — The content policy state of the episode.
- `episode_uuid` (string, optional) — The UUID of the episode of the message.

## Examples

**Request**

```json
{
  "messages": [
    {}
  ]
}
```

**Response**

```json
{
  "context": "string",
  "messages": [
    {
      "content": "string",
      "created_at": "string",
      "metadata": {},
      "name": "string",
      "processed": true,
      "reference_time": "string",
      "role": "system",
      "thread_uuid": "string",
      "uuid": "string"
    }
  ],
  "task": {
    "completed_at": "string",
    "created_at": "string",
    "error": {
      "code": "string",
      "details": {},
      "message": "string",
      "param": "string",
      "request_id": "string"
    },
    "progress": {
      "stage": "string"
    },
    "result": {
      "content_policy": {
        "category_keys": [
          "health"
        ],
        "dropped_count": 0,
        "failed_count": 1,
        "retained_count": 7,
        "revision": 3,
        "status": "complete",
        "violated": false,
        "violated_count": 2
      },
      "edge_uuid": "7a1f3c2e-4b5d-4e6f-8a9b-0c1d2e3f4a5b",
      "edges": [
        {
          "edge_uuid": "7a1f3c2e-4b5d-4e6f-8a9b-0c1d2e3f4a5b",
          "source_node_uuid": "b2c3d4e5-f6a7-4b8c-9d0e-1f2a3b4c5d6e",
          "target_node_uuid": "c3d4e5f6-a7b8-4c9d-8e1f-2a3b4c5d6e7f"
        }
      ],
      "episode_uuid": "f6a7b8c9-d0e1-4f2a-9b4c-5d6e7f8091a2",
      "episodes": [
        {
          "content_policy": {
            "category_keys": [
              "health"
            ],
            "dropped_count": 0,
            "failed_count": 1,
            "retained_count": 7,
            "revision": 3,
            "status": "complete",
            "violated": false,
            "violated_count": 2
          },
          "episode_uuid": "f6a7b8c9-d0e1-4f2a-9b4c-5d6e7f8091a2"
        }
      ],
      "hyperedge_uuid": "d4e5f6a7-b8c9-4d0e-9f2a-3b4c5d6e7f80",
      "skill_uuid": "e5f6a7b8-c9d0-4e1f-8a3b-4c5d6e7f8091",
      "source_node_uuid": "b2c3d4e5-f6a7-4b8c-9d0e-1f2a3b4c5d6e",
      "target_node_uuid": "c3d4e5f6-a7b8-4c9d-8e1f-2a3b4c5d6e7f"
    },
    "started_at": "string",
    "status": "pending",
    "type": "string",
    "updated_at": "string",
    "uuid": "string"
  }
}
```