Skip to main content

NeuroMem - Brain-inspired memory system for AI agents with multi-modal storage

Project description

NeuroMem Logo

Love grows from the smallest of memories ~

| 中文文档 | Developer Slack |

🔥 Welcome! NeuroMem is a subproject of SAGE, dedicated to exploring memory systems for large language models.


Publication

This repository supports the NeuroMem memory runtime described in the following paper:

  • Ruicheng Zhang et al. "Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs." ICML 2026.

Getting Started

Install neuromem with pip :

pip install isage-neuromem

For development, clone the repo and use the provided quickstart script:

git clone https://github.com/intellistream/NeuroMem.git
cd neuromem
./quickstart.sh

This will set up a local development environment (virtualenv + dependencies) suitable for running tests and benchmarks. You can then:

  • Explore examples in examples/
  • Run the benchmark suite in benchmarks/
  • Dive into the core implementation under sage/neuromem/

License

Apache-2.0 License - see LICENSE file for details.

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

isage_neuromem-0.2.1.11.tar.gz (472.5 kB view details)

Uploaded Source

Built Distribution

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

isage_neuromem-0.2.1.11-py2.py3-none-any.whl (610.9 kB view details)

Uploaded Python 2Python 3

File details

Details for the file isage_neuromem-0.2.1.11.tar.gz.

File metadata

  • Download URL: isage_neuromem-0.2.1.11.tar.gz
  • Upload date:
  • Size: 472.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for isage_neuromem-0.2.1.11.tar.gz
Algorithm Hash digest
SHA256 7c64251ce7419aeece71f6e67308408e978d94d34554f0c414159bc6fc1162f9
MD5 1acc847254d40e3039471e641e1125ff
BLAKE2b-256 76d0a4d6e5a5e84bc7ea77cf1110e2a9fa15dda5ab93e5427b1e4a5951e4eafd

See more details on using hashes here.

File details

Details for the file isage_neuromem-0.2.1.11-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for isage_neuromem-0.2.1.11-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 aa536b69c3202e18bcc8f5fb8c336c1fcccd803c34661b6d11994aca107faa7a
MD5 7264ebc92511c66dac648dd1b529c15b
BLAKE2b-256 aee46504838d5c99b76c06396312d91b4c9cf430604be42971cc199bc93f9236

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