Factual package intelligence from PyPI

mlx-memo 4.4.0 package intelligence

Local-first semantic memory for AI agents — MLX (Apple Silicon) or CPU sentence-transformers (Linux/Ubuntu) embeddings + sqlite-vec, MCP server. No cloud, no API keys.

pip install mlx-memo

Current version
4.4.0
Python requirement
>=3.13
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
2.7 MiB
Release history
38 releases with files
Median release cadence
0 days

mlx-memo dependencies

PyPI declares 38 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. click >=8.1.7
  2. cryptography >=42.0
  3. fastmcp <4,>=0.5
  4. mlx-lm >=0.18 when sys_platform == "darwin" and platform_machine == "arm64"
  5. mlx <1,>=0.18 when sys_platform == "darwin" and platform_machine == "arm64"
  6. pydantic >=2.6
  7. python-frontmatter >=1.1
  8. pyyaml >=6.0
  9. questionary >=2.0
  10. rich >=13.7
  11. sentence-transformers >=3.0 when sys_platform == "linux"
  12. sqlite-vec <0.2,>=0.1.9

The compact report shows 12 of 38 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

mlx-memo publishes 1 wheel and 1 source archive for version 4.4.0. Wheel platform tags: any.

Declared Python classifiers: 3.13, 3.14.

Security snapshot for mlx-memo 4.4.0

An OSV query completed on and found 0 known vulnerabilities affecting this version. 0 advisories are classified as critical. 0 advisories appear in the CISA Known Exploited Vulnerabilities catalog.

Release activity and sources

PyPI lists 38 releases with files. The first dated release is ; 38 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .