Skip to main content

Compressed memory chunks for AI chat history - 60-70% space savings

Project description

Adaptive Memory Chunk eXtended (amcx)

A Python library for efficient memory chunking with adaptive algorithms (zero dependencies).

read wiki or see changelog for more info

Installation

pip install amcx

to slow?

use add-ons (function under development of the amcx library)

Usage

from amcx import chunk_memory

# Your code here

License

This project is licensed under the GNU Lesser General Public License v3.0 or later (LGPL-3.0+). See the LICENSE file for details.

Author

  • hacko223

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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

amcx-0.3.3.2.tar.gz (23.5 kB view details)

Uploaded Source

Built Distribution

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

amcx-0.3.3.2-py3-none-any.whl (21.5 kB view details)

Uploaded Python 3

File details

Details for the file amcx-0.3.3.2.tar.gz.

File metadata

  • Download URL: amcx-0.3.3.2.tar.gz
  • Upload date:
  • Size: 23.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for amcx-0.3.3.2.tar.gz
Algorithm Hash digest
SHA256 44abf566211aa48a68a39725ab6756a93ca37601a27c74068669682d86664481
MD5 25c19902b023b7dd105aadcbddec5451
BLAKE2b-256 72dd977b322752749ee8a38399deb2b7a2bb1f478ca2272b79bddee02fe38a9a

See more details on using hashes here.

File details

Details for the file amcx-0.3.3.2-py3-none-any.whl.

File metadata

  • Download URL: amcx-0.3.3.2-py3-none-any.whl
  • Upload date:
  • Size: 21.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for amcx-0.3.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6bf01af647e86fbbe4ecbacce16b2b7056acaa1f092926d1809ae096fb4d7408
MD5 ae5122ddfc5bde4f2bd42637e47913e1
BLAKE2b-256 58e71115a6897ae3d9da6a5cfb7b20739e366076044e26315c4711a5215c24df

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