Skip to main content

unibaseio-membase-core

The engine of Membase, the memory layer for AI agents: conversations become dated episodes, documents a topic tree, and search is a multi-round retrieval. 93.1% on LoCoMo, 92.6% on LongMemEval_S and 92.2% on DMR (method and results).

Compiled wheels for CPython 3.12 and 3.13 on Linux, macOS and Windows. Applications use it through unibaseio-membase: pip install 'unibaseio-membase[local]'.

Proprietary (see LICENSE); the bundled membase_algo is Apache-2.0 (see NOTICE).

Metadata

Release files for unibaseio-membase-core 0.3.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for unibaseio-membase-core 0.3.2
File
unibaseio_membase_core-0.3.2-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details
unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.17+ x86-64 Details
unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl CPython 3.13 CPython 3.13 Linux glibc 2.17+ ARM64 Details
unibaseio_membase_core-0.3.2-cp313-cp313-macosx_11_0_arm64.whl CPython 3.13 CPython 3.13 macOS 11.0+ ARM64 Details
unibaseio_membase_core-0.3.2-cp313-cp313-macosx_10_13_x86_64.whl CPython 3.13 CPython 3.13 macOS 10.13+ x86-64 Details
unibaseio_membase_core-0.3.2-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details
unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.17+ x86-64 Details
unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl CPython 3.12 CPython 3.12 Linux glibc 2.17+ ARM64 Details
unibaseio_membase_core-0.3.2-cp312-cp312-macosx_11_0_arm64.whl CPython 3.12 CPython 3.12 macOS 11.0+ ARM64 Details
unibaseio_membase_core-0.3.2-cp312-cp312-macosx_10_13_x86_64.whl CPython 3.12 CPython 3.12 macOS 10.13+ x86-64 Details

Total release size: 20.8 MB

Release files / unibaseio_membase_core-0.3.2-cp313-cp313-win_amd64.whl

Download URL unibaseio_membase_core-0.3.2-cp313-cp313-win_amd64.whl
Size 1.8 MB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
91157f6ebbaa90235d276d991ec8186daafcca7918078f8dc000210840b2c039
BLAKE2b-256 checksum
How to use checksums
afa8bb76d4072740d579f3f615b46dddcb375dd88e20dbf33b1d120a52bf4771
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 2.3 MB
Tags CPython 3.13 Linux glibc 2.17+ x86-64
SHA-256 checksum
How to use checksums
e1071a0404cd5829114c0fb03ff518bee6a1e52fc600f99da08bc2050500d6aa
BLAKE2b-256 checksum
How to use checksums
2538a66a1c45d0ad160bd273947c9bd1eecf7ba232de2b9c59b4c79a3cfeeb5e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL unibaseio_membase_core-0.3.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 2.2 MB
Tags CPython 3.13 Linux glibc 2.17+ ARM64
SHA-256 checksum
How to use checksums
1522d5d15dd9b395c25d6d7da93704fdf210db0f9f903f043b19855498ad0e22
BLAKE2b-256 checksum
How to use checksums
f71486f8082847b7e691a6ed23750b3a4480cd1f7c247c07a6ab3406c231c87f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp313-cp313-macosx_11_0_arm64.whl

Download URL unibaseio_membase_core-0.3.2-cp313-cp313-macosx_11_0_arm64.whl
Size 2.0 MB
Tags CPython 3.13 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
447706bfe46ff5b153a95c8d6605fd03bc9a314b2e8a4d8e0b0822246bdf73ed
BLAKE2b-256 checksum
How to use checksums
a32903b4515195f2365265c70929d07a0cfcb86a529fb2e66c93dec203d6684e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp313-cp313-macosx_10_13_x86_64.whl

Download URL unibaseio_membase_core-0.3.2-cp313-cp313-macosx_10_13_x86_64.whl
Size 2.1 MB
Tags CPython 3.13 macOS 10.13+ x86-64
SHA-256 checksum
How to use checksums
13f5c80f351df85d5d60d698098d8808a6c7d055609fd41bff4fe9461e1a3660
BLAKE2b-256 checksum
How to use checksums
b1495f1bfd1a59921073a821df1c6df906f2d90db9c68927a124c04ea2cbe9c2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp312-cp312-win_amd64.whl

Download URL unibaseio_membase_core-0.3.2-cp312-cp312-win_amd64.whl
Size 1.9 MB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
ad1ab7976c494b2629536a2ab741e022fc038f536e6ab0b1c415461d286a8a52
BLAKE2b-256 checksum
How to use checksums
14b44ddcf214c808bb265745803bdd874c6af6092ffb04bf1257bf0d29efc21e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 2.3 MB
Tags CPython 3.12 Linux glibc 2.17+ x86-64
SHA-256 checksum
How to use checksums
aa85b32514491e325740fe48d164ebf6813d852e7dc6bd48f223bf8875a52e2e
BLAKE2b-256 checksum
How to use checksums
c2114cca15461904a73296375b8ca050943dd71fece64280748be13dbde9e1a3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL unibaseio_membase_core-0.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 2.2 MB
Tags CPython 3.12 Linux glibc 2.17+ ARM64
SHA-256 checksum
How to use checksums
f0fdd4b1216f497a47ee67738cffdd4cd606b02f3b58dc8bbc0a1dbf7cb37efe
BLAKE2b-256 checksum
How to use checksums
408697031cf317601ca72f1ba723ddfb6740bee432d3cd0277526d2cd5aa86fd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp312-cp312-macosx_11_0_arm64.whl

Download URL unibaseio_membase_core-0.3.2-cp312-cp312-macosx_11_0_arm64.whl
Size 2.0 MB
Tags CPython 3.12 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
422ba91daf87c9d29ea70873a8ad959422bf1efc8b08b5022ed54c99ac7a0e2f
BLAKE2b-256 checksum
How to use checksums
95947c1e187094f7bffebcadf70d43c76b06c1640cac71a725ec1b390bf294da
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / unibaseio_membase_core-0.3.2-cp312-cp312-macosx_10_13_x86_64.whl

Download URL unibaseio_membase_core-0.3.2-cp312-cp312-macosx_10_13_x86_64.whl
Size 2.1 MB
Tags CPython 3.12 macOS 10.13+ x86-64
SHA-256 checksum
How to use checksums
c83c40c102083eeaaac25c25799c37aa21c0cc46fb8de4d6158ad1665cd65b41
BLAKE2b-256 checksum
How to use checksums
ab0ee030e68c2e6d52d639694c432c54e99c7d4bf3f3e7c0933fb1452fb66b0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Security for unibaseio-membase-core 0.3.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page