agentmemory <a href="https://discord.gg/qetWd7J9De"><img style="float: right" src="https://dcbadge.vercel.app/api/server/qetWd7J9De" alt=""></a> <a href="https://github.com/AutonomousResearchGroup/agentmemory/stargazers"><img style="float: right; padding: 5px;" src="https://img.shields.io/github/stars/AutonomousResearchGroup/agentmemory?style=social" alt=""></a>

Easy-to-use memory for agents, document search, knowledge graphing and more.

<img src="resources/image.jpg">

Installation

pip install agentmemory

Quickstart

from agentmemory import create_memory, search_memory

# create a memory
create_memory("conversation", "I can't do that, Dave.", metadata={"speaker": "HAL", "some_other_key": "some value, could be a number or string"})

# search for a memory
memories = search_memory("conversation", "Dave") # category, search term

print(str(memories))

# memories is a list of dictionaries
[
    {
        "id": int,
        "document": string,
        "metadata": dict{...values},
        "embeddings": (Optional) list[float] | None
    },
    {
        ...
    }
]

Debugging

You can enable debugging by passing debug=True to most functions, or by setting DEBUG=True in your environment to get global memory debugging.

create_memory("conversation", "I can't do that, Dave.", debug=True)

Deployment

CLIENT_TYPE='POSTGRES' | 'CHROMA' POSTGRES_CONNECTION_STRING=postgres://postgres:MagickDatabase123!@db.xnzvmluhwpbngdufsbrd.supabase.co:6543/postgres

By default, agentmemory will use a local ChromaDB instance. If you want to use a Postgres instance, you can set the environment variable CLIENT_TYPE to POSTGRES and set the POSTGRES_CONNECTION_STRING environment variable to your Postgres connection string.

You can deploy an agentmemory-based application to the cloud in minutes using Supabase. Here is a tutorial and an explanation of pgvector.

Basic Usage Guide

Importing into your project

from agentmemory import (
    create_memory,
    create_unique_memory,
    get_memories,
    search_memory,
    get_memory,
    update_memory,
    delete_memory,
    delete_similar_memories,
    count_memories,
    wipe_category,
    wipe_all_memories
)

Create a Memory

# category, document, metadata
create_memory("conversation", "I can't do that, Dave.", metadata={"speaker": "HAL", "some_other_key": "some value, could be a number or string"})

Search memories

memories = search_memory("conversation", "Dave") # category, search term
# memories is a list of dictionaries
[
    {
        "id": int,
        "document": string,
        "metadata": dict{...values},
        "embeddings": (Optional) list[float] | None
    },
    {
        ...
    }
]

Get all memories

memories = get_memories("conversation") # can be any category
# memories is a list of dictionaries
[
    {
        "id": int,
        "document": string,
        "metadata": dict{...values},
        "embeddings": (Optional) list[float] | None
    },
    {
        ...
    }
]

Get a memory

memory = get_memory("conversation", 1) # category, id

Update a memory

update_memory("conversation", 1, "Okay, I will open the podbay doors.")

Delete a Memory

delete_memory("conversation", 1)

Delete Similar Memories

delete_similar_memories(category, content, similarity_threshold=0.95)

Search for memories that are similar to the one that contains the given content and removes them.

Parameters

• category (str): The category of the collection.
• content (str): The content to search for.
• similarity_threshold (float, optional): The threshold for determining similarity. Defaults to 0.95.

Returns

• bool: True if the memory item is found and removed, False otherwise.

API Reference

Create a Memory

create_memory(category, text, id=None, embedding=None, metadata=None)

Create a new memory in a collection.

Arguments

# Required
category (str): Category of the collection.
text (str): Document text.

# Optional
id (str): Unique id. Generated incrementally unless set.
metadata (dict): Metadata.
embedding (array): Embedding of the document. Defaults to None. Use if you already have an embedding.

Example

>>> create_memory(category='sample_category', text='sample_text', id='sample_id', metadata={'sample_key': 'sample_value'})

Create Unique Memory

create_unique_memory(category, content, metadata={}, similarity=0.95)

Create a new memory only if there aren't any that are very similar to it. If a similar memory is found, the new memory's "novel" metadata field is set to "False" and it is linked to the existing memory.

Parameters

• category (str): The category of the collection.
• content (str): The text of the memory.
• metadata (dict, optional): Metadata for the memory.
• similarity (float, optional): The threshold for determining similarity.

Returns

None

Search Memory

search_memory(category, search_text, n_results=5, min_distance=None, max_distance=None, filter_metadata=None, contains_text=None, include_embeddings=True, novel=False)

Search a collection with given query texts.

A note about distances: the filters are applied after the query, so the n_results may be dramatically shortened. This is a current limitation of Chromadb.

Arguments

# Required
category (str): Category of the collection.
search_text (str): Text to be searched.

# Optional
n_results (int): Number of results to be returned.
filter_metadata (dict): Metadata for filtering the results.
contains_text (str): Text that must be contained in the documents.
include_embeddings (bool): Whether to include embeddings in the results.
include_distances (bool): Whether to include distances in the results.
max_distance (float): Only include memories with this distance threshold maximum.
    0.1 = most memories will be exluded, 1.0 = no memories will be excluded
min_distance (float): Only include memories that are at least this distance
    0.0 = No memories will be excluded, 0.9 = most memories will be excluded
novel (bool): Whether to return only novel memories.

Returns

list: List of search results.

Example

>>> search_memory('sample_category', 'search_text', min_distance=0.01, max_distance=0.7, n_results=2, filter_metadata={'sample_key': 'sample_value'}, contains_text='sample', include_embeddings=True, include_distances=True)
[{'metadata': '...', 'document': '...', 'id': '...'}, {'metadata': '...', 'document': '...', 'id': '...'}]

Get a Memory

get_memory(category, id, include_embeddings=True)

Retrieve a specific memory from a given category based on its ID.

Arguments

# Required
category (str): The category of the memory.
id (str/int): The ID of the memory.

#optional
include_embeddings (bool): Whether to include the embeddings. Defaults to True.

Returns

dict: The retrieved memory.

Example

>>> get_memory("books", "1")

Get Memories

get_memories(category, sort_order="desc", filter_metadata=None, n_results=20, include_embeddings=True, novel=False)

Retrieve a list of memories from a given category, sorted by ID, with optional filtering. sort_order controls whether you get from the beginning or end of the list.

Arguments

# Required
category (str): The category of the memories.

# Optional
sort_order (str): The sorting order of the memories. Can be 'asc' or 'desc'. Defaults to 'desc'.
filter_metadata (dict): Filter to apply on metadata. Defaults to None.
n_results (int): The number of results to return. Defaults to 20.
include_embeddings (bool): Whether to include the embeddings. Defaults to True.
novel (bool): Whether to return only novel memories. Defaults to False.

Returns

list: List of retrieved memories.

Example

>>> get_memories("books", sort_order="asc", n_results=10)

Update a Memory

update_memory(category, id, text=None, metadata=None)

Update a memory with new text and/or metadata.

Arguments

# Required
category (str): The category of the memory.
id (str/int): The ID of the memory.

# Optional
text (str): The new text of the memory. Defaults to None.
metadata (dict): The new metadata of the memory. Defaults to None.

Example

# with keyword arguments
update_memory(category="conversation", id=1, text="Okay, I will open the podbay doors.", metadata={ "speaker": "HAL", "sentiment": "positive" })

# with positional arguments
update_memory("conversation", 1, "Okay, I will open the podbay doors.")

Delete a Memory

delete_memory(category, id, contains_metadata=None, contains_text=None)

Delete a memory by ID.

Arguments

# Required
category (str): The category of the memory.
id (str/int): The ID of the memory.

# Optional

Example

>>> delete_memory("books", "1")

delete_memories(category, document=None, metadata=None)

Delete all memories in the category either by document, or by metadata, or by both.

Arguments

# Required
cat