Simple API

The Simple API provides opinionated, batteries-included endpoints for quick integration. No need to manage embeddings, types, or tiers—just send text and get results.

Tip

Use the Simple API for prototyping or simple agents. Graduate to the full API when you need fine-grained control over memory management.

Remember

POST/v1/simple/remember

Store a memory with auto-classification, auto-embedding, and auto-consolidation. If a very similar memory exists (similarity > 0.90), it's merged automatically.

Request Body

Field	Type	Required	Description
`text`	string	Yes	Memory content

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/remember" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"text": "User prefers TypeScript over JavaScript"}'

Response (Created)

{
  "id": "mem_abc123",
  "stored": true
}

Response (Consolidated)

If merged with an existing similar memory:

{
  "id": "mem_existing456",
  "stored": true,
  "consolidated": true,
  "mergedWith": "mem_existing456"
}

Auto-Classification

The Simple API automatically detects memory type and importance based on content patterns:

Pattern	Type	Tier
`"my name is", "I am called"`	identity	critical
`"must always", "never ever", "fundamental"`	constraint	critical
`"always", "never", "prefer", "important"`	preference	high
`Default`	fact	normal

Recall

POST/v1/simple/recall

Search memories and get just the text content—perfect for injection into prompts. Automatically tracks access and updates memory strength.

Request Body

Field	Type	Required	Description
`query`	string	Yes	Natural language search query
`limit`	number	No	Max results (default: 5, max: 20)

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/recall" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "user language preferences", "limit": 3}'

Response

{
  "results": [
    "User prefers TypeScript over JavaScript",
    "User likes Python for data science tasks",
    "User wants concise code examples"
  ],
  "count": 3
}

Note

Results are plain strings, ready to inject into your AI's context. No need to parse complex objects.

Get Context

POST/v1/simple/context

Get a pre-formatted context string ready to inject into your AI's system prompt. Combines critical and relevant memories into markdown format.

Request Body

Field	Type	Required	Description
`message`	string	Yes	User message for relevance matching
`limit`	number	No	Max memories to include (default: 10)

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/context" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"message": "Help me write some code"}'

Response

{
  "context": "## User Context\n\n### Core Identity\n- User is John, a software engineer in Singapore\n- User prefers morning work hours (9am-12pm SGT)\n\n### Relevant Memories\n- User prefers TypeScript over JavaScript\n- User wants concise code examples\n- User likes functional programming patterns",
  "tokensUsed": 78,
  "memoriesUsed": 5
}

Usage Pattern

Here's a complete example using the Simple API with OpenAI:

import requests
from openai import OpenAI

API_KEY = "mem_your_api_key"
BASE_URL = "https://fathippo.ai/api/v1/simple"

client = OpenAI()

def chat_with_memory(user_message: str) -> str:
    # Get relevant context
    context_resp = requests.post(
        f"{BASE_URL}/context",
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={"message": user_message}
    ).json()
    
    # Build messages
    messages = [
        {
            "role": "system",
            "content": f"You are a helpful assistant.\n\n{context_resp['context']}"
        },
        {"role": "user", "content": user_message}
    ]
    
    # Get response
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=messages
    )
    
    assistant_message = response.choices[0].message.content
    
    # Store any learnings (could be extracted from conversation)
    if "remember" in user_message.lower():
        requests.post(
            f"{BASE_URL}/remember",
            headers={"Authorization": f"Bearer {API_KEY}"},
            json={"text": user_message}
        )
    
    return assistant_message

# Example
response = chat_with_memory("Remember that I prefer dark mode")
print(response)

Simple API

The Simple API provides opinionated, batteries-included endpoints for quick integration. No need to manage embeddings, types, or tiers—just send text and get results.

Tip

Use the Simple API for prototyping or simple agents. Graduate to the full API when you need fine-grained control over memory management.

Remember

POST/v1/simple/remember

Store a memory with auto-classification, auto-embedding, and auto-consolidation. If a very similar memory exists (similarity > 0.90), it's merged automatically.

Request Body

Field	Type	Required	Description
`text`	string	Yes	Memory content

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/remember" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"text": "User prefers TypeScript over JavaScript"}'

Response (Created)

{
  "id": "mem_abc123",
  "stored": true
}

Response (Consolidated)

If merged with an existing similar memory:

{
  "id": "mem_existing456",
  "stored": true,
  "consolidated": true,
  "mergedWith": "mem_existing456"
}

Auto-Classification

The Simple API automatically detects memory type and importance based on content patterns:

Pattern	Type	Tier
`"my name is", "I am called"`	identity	critical
`"must always", "never ever", "fundamental"`	constraint	critical
`"always", "never", "prefer", "important"`	preference	high
`Default`	fact	normal

Recall

POST/v1/simple/recall

Search memories and get just the text content—perfect for injection into prompts. Automatically tracks access and updates memory strength.

Request Body

Field	Type	Required	Description
`query`	string	Yes	Natural language search query
`limit`	number	No	Max results (default: 5, max: 20)

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/recall" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "user language preferences", "limit": 3}'

Response

{
  "results": [
    "User prefers TypeScript over JavaScript",
    "User likes Python for data science tasks",
    "User wants concise code examples"
  ],
  "count": 3
}

Note

Results are plain strings, ready to inject into your AI's context. No need to parse complex objects.

Get Context

POST/v1/simple/context

Get a pre-formatted context string ready to inject into your AI's system prompt. Combines critical and relevant memories into markdown format.

Request Body

Field	Type	Required	Description
`message`	string	Yes	User message for relevance matching
`limit`	number	No	Max memories to include (default: 10)

Example Request

curl -X POST "https://fathippo.ai/api/v1/simple/context" \
  -H "Authorization: Bearer mem_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"message": "Help me write some code"}'

Response

{
  "context": "## User Context\n\n### Core Identity\n- User is John, a software engineer in Singapore\n- User prefers morning work hours (9am-12pm SGT)\n\n### Relevant Memories\n- User prefers TypeScript over JavaScript\n- User wants concise code examples\n- User likes functional programming patterns",
  "tokensUsed": 78,
  "memoriesUsed": 5
}

Usage Pattern

Here's a complete example using the Simple API with OpenAI:

import requests
from openai import OpenAI

API_KEY = "mem_your_api_key"
BASE_URL = "https://fathippo.ai/api/v1/simple"

client = OpenAI()

def chat_with_memory(user_message: str) -> str:
    # Get relevant context
    context_resp = requests.post(
        f"{BASE_URL}/context",
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={"message": user_message}
    ).json()
    
    # Build messages
    messages = [
        {
            "role": "system",
            "content": f"You are a helpful assistant.\n\n{context_resp['context']}"
        },
        {"role": "user", "content": user_message}
    ]
    
    # Get response
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=messages
    )
    
    assistant_message = response.choices[0].message.content
    
    # Store any learnings (could be extracted from conversation)
    if "remember" in user_message.lower():
        requests.post(
            f"{BASE_URL}/remember",
            headers={"Authorization": f"Bearer {API_KEY}"},
            json={"text": user_message}
        )
    
    return assistant_message

# Example
response = chat_with_memory("Remember that I prefer dark mode")
print(response)