POST /api/memory/settings Bearer

Update Memory Settings

Update PocketPaw's memory backend configuration: switch between file store and Mem0, configure LLM and embedder providers, set vector store options, and toggle auto-learning.

Overview

Updates the memory backend configuration. Changes take effect immediately — the memory manager is reloaded with the new settings.

Request Body

Body Parameters

memory_backend
string

Memory backend to use. file is the default file-based store, mem0 enables semantic memory with auto-learn.

Allowed values:
filemem0
mem0_llm_provider
string

LLM provider for mem0’s extraction and summarization.

Allowed values:
ollamaopenaianthropic
mem0_llm_model
string

LLM model name (e.g., llama3.2, gpt-4o-mini).

mem0_embedder_provider
string

Embedding provider for semantic search.

Allowed values:
ollamaopenai
mem0_embedder_model
string

Embedding model name (e.g., nomic-embed-text, text-embedding-3-small).

mem0_vector_store
string

Vector store backend.

Allowed values:
qdrant
mem0_ollama_base_url
string

Ollama server URL (default: http://localhost:11434).

mem0_auto_learn
boolean

Enable automatic memory extraction from conversations.

Response

status string
"ok" on success
Terminal window
curl -X POST "http://localhost:8000/api/memory/settings" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "memory_backend": "mem0",
    "mem0_llm_provider": "ollama",
    "mem0_llm_model": "llama3.2",
    "mem0_embedder_provider": "ollama",
    "mem0_embedder_model": "nomic-embed-text",
    "mem0_vector_store": "qdrant",
    "mem0_auto_learn": true
  }'
const response = await fetch("http://localhost:8000/api/memory/settings", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    memory_backend: "mem0",
    mem0_llm_provider: "ollama",
    mem0_llm_model: "llama3.2",
    mem0_embedder_provider: "ollama",
    mem0_embedder_model: "nomic-embed-text",
    mem0_vector_store: "qdrant",
    mem0_auto_learn: true
  })
});
const data = await response.json();
console.log(data);
import requests


response = requests.post(
    "http://localhost:8000/api/memory/settings",
    headers={"Authorization": "Bearer <token>"},
    json={
        "memory_backend": "mem0",
        "mem0_llm_provider": "ollama",
        "mem0_llm_model": "llama3.2",
        "mem0_embedder_provider": "ollama",
        "mem0_embedder_model": "nomic-embed-text",
        "mem0_vector_store": "qdrant",
        "mem0_auto_learn": True
    }
)
print(response.json())
{
  "status": "ok"
}
Request
curl -X POST "http://localhost:8000/api/memory/settings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <token>"
const response = await fetch("http://localhost:8000/api/memory/settings", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer <token>"
},
});

const data = await response.json();
console.log(data);
import requests

response = requests.post(
    "http://localhost:8000/api/memory/settings",
    headers={'Content-Type':'application/json','Authorization':'Bearer <token>'},
)

print(response.json())
package main

import (
    "fmt"
    "net/http"
    "io"
)

func main() {
    req, _ := http.NewRequest("POST", "http://localhost:8000/api/memory/settings", nil)
    req.Header.Set("Content-Type", "application/json")
    req.Header.Set("Authorization", "Bearer <token>")

    client := &http.Client{}
    resp, _ := client.Do(req)
    defer resp.Body.Close()

    body, _ := io.ReadAll(resp.Body)
    fmt.Println(string(body))
}
Response
Send a request to see the response