Skip to main content

alaya-memory

A persistent memory engine for conversational AI agents — Python bindings for Alaya.

Install

pip install alaya-memory

Quick start

from alaya import Alaya, NewEpisode, Query

# Open (or create) a memory store
mem = Alaya("agent.db")

# Store an episode
mem.store_episode(NewEpisode(
    content="User prefers concise answers",
    session_id="sess-001",
    role="user",
))

# Query
results = mem.query(Query(text="communication preferences", limit=5))
for r in results:
    print(r.score, r.content)

# Run the full dream cycle (consolidate → transform → forget)
mem.dream()

Features

  • Episodic memory — store and retrieve conversation turns
  • Semantic consolidation — episodes are distilled into durable knowledge nodes
  • Forgetting curves — weak or contradicted knowledge decays over time
  • Knowledge graph — typed links between episodes, nodes, preferences, and categories
  • Encrypted storage — optional SQLCipher encryption (open_encrypted)
  • MCP server — expose memory over the Model Context Protocol via alaya-mcp on npm

Documentation

See the Alaya repository for full API docs and the Rust crate.

License

MIT

Metadata

Release files for alaya-memory 0.4.8

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 alaya-memory 0.4.8
File
alaya_memory-0.4.8-cp39-abi3-win_amd64.whl CPython 3.9 abi3 Windows x86-64 Details
alaya_memory-0.4.8-cp39-abi3-manylinux_2_38_x86_64.whl CPython 3.9 abi3 Linux glibc 2.38+ x86-64 Details
alaya_memory-0.4.8-cp39-abi3-macosx_11_0_arm64.whl CPython 3.9 abi3 macOS 11.0+ ARM64 Details
alaya_memory-0.4.8-cp39-abi3-macosx_10_12_x86_64.whl CPython 3.9 abi3 macOS 10.12+ x86-64 Details

Total release size: 9.7 MB

Release files / alaya_memory-0.4.8-cp39-abi3-win_amd64.whl

Download URL alaya_memory-0.4.8-cp39-abi3-win_amd64.whl
Size 3.0 MB
Tags CPython 3.9 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
6a656e7fb3ae214d11344e489f4f5db0342d41d7f925ef9754f7e98503c982b7
BLAKE2b-256 checksum
How to use checksums
339543a50feda5155dd2e3036de5180c0194f0d8571569ab921fa0d1e3570cf1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 18, 2026.

Transparency log

Release files / alaya_memory-0.4.8-cp39-abi3-manylinux_2_38_x86_64.whl

Download URL alaya_memory-0.4.8-cp39-abi3-manylinux_2_38_x86_64.whl
Size 3.7 MB
Tags CPython 3.9 Linux glibc 2.38+ x86-64 abi3
SHA-256 checksum
How to use checksums
3dcb69c405cff4e3d3bf6ab451894e68a436ecb99c27f55aafcf5571bf5c7763
BLAKE2b-256 checksum
How to use checksums
5ddc80b13016b46f1586bbb08c18c1ebd965670c5baa2fc18ba0018f2ae3c83a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 18, 2026.

Transparency log

Release files / alaya_memory-0.4.8-cp39-abi3-macosx_11_0_arm64.whl

Download URL alaya_memory-0.4.8-cp39-abi3-macosx_11_0_arm64.whl
Size 1.5 MB
Tags CPython 3.9 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
cb596a3b25dd029c43e117c472d0888c258caeb683b29399db7e026b012d6f7b
BLAKE2b-256 checksum
How to use checksums
2433783aebaf14c5622ecd1a86d835f0fb4ae72ae2cc20a016e18dfda7ecdb9a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 18, 2026.

Transparency log

Release files / alaya_memory-0.4.8-cp39-abi3-macosx_10_12_x86_64.whl

Download URL alaya_memory-0.4.8-cp39-abi3-macosx_10_12_x86_64.whl
Size 1.6 MB
Tags CPython 3.9 abi3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
7891d2f2b62e1f0e4bff56e8c5883147d7e7d8c97f215d7d91729c07d665ac58
BLAKE2b-256 checksum
How to use checksums
4b1891bd8fcc0187422f0dc219528f5b25e20e50a90c5cbebbd44fe422459705
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 18, 2026.

Transparency log

Security for alaya-memory 0.4.8

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.

Full provenance

All 4 files in this release have been uploaded with provenance metadata.

Select from 4 files

Attestation for alaya_memory-0.4.8-cp39-abi3-win_amd64.whl

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 18, 2026.

Transparency log

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