Skip to main content

Symbol Machines Memory SDK — Long-term cognitive memory for any LLM.

Project description

Symbol Machines Memory SDK (Python)

A lightweight SDK that adds structured long-term memory to any LLM.

Learn more at https://symbolmachines.com


Installation

pip install symbolmachines

Usage

from symbolmachines import Symbol

symbol = Symbol(api_key="sk-...")

# Inject memory context before calling your LLM
context = symbol.memory.inject.create(input="What should i eat for lunch?")

# ... call your LLM with the contextual input ...

# Save memory after generation
symbol.memory.save.create(output="Eating sushi is a healthy meal.")

API

symbol.memory.inject.create(input=str) Injects memory context into user input.

symbol.memory.save.create(output=str) Writes an output into the Symbol's memory.


Configuration

symbol = Symbol(
    api_key="sk-...",
    base_url="https://api.symbol.ai/v1" # optional override
)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

symbolmachines-0.1.0.tar.gz (2.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

symbolmachines-0.1.0-py3-none-any.whl (2.7 kB view details)

Uploaded Python 3

File details

Details for the file symbolmachines-0.1.0.tar.gz.

File metadata

  • Download URL: symbolmachines-0.1.0.tar.gz
  • Upload date:
  • Size: 2.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for symbolmachines-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0deb6acb60dbae5d1173c61faafe1a59f01642f5c54c7d354b63b44cc683b735
MD5 29657308ba940f6d1c49eaca4d368729
BLAKE2b-256 b84016fe1bca16bd7c8c56a6a7336a4d992b732f943f2855eb084c2a2b5f4689

See more details on using hashes here.

File details

Details for the file symbolmachines-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: symbolmachines-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for symbolmachines-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c25602a2781896a0a8ab3927c1c2e88dee1ddd13a6544470ffc2a6781a89f98c
MD5 cab9cb6910c543476bb95377c48f530c
BLAKE2b-256 8a5c3ea3f0624ceeba5cb6a00a062d4cdb5228d98bb0c9706fcd2cfb81ae8923

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page