Audrey Python SDK

Typed Python client for the Audrey REST API.

Install

pip install audrey-memory

For local development from this repository:

cd python
python -m pip install -e .

Quick Start

Start Audrey's REST API:

npm install -g audrey --allow-scripts=better-sqlite3,onnxruntime-node,sharp,protobufjs
audrey serve

Then use the client:

from audrey_memory import Audrey

brain = Audrey(
    base_url="http://127.0.0.1:7437",
    api_key="secret",
    agent="support-agent",
)

memory_id = brain.encode(
    "Stripe returns HTTP 429 above 100 req/s",
    source="direct-observation",
    tags=["stripe", "rate-limit"],
)

results = brain.recall("stripe rate limits", limit=5)
snapshot = brain.snapshot()
brain.close()

Restore snapshots only into an empty Audrey store, such as a sidecar started with a fresh AUDREY_DATA_DIR:

restore_target = Audrey(base_url="http://127.0.0.1:7437", api_key="secret")
restore_target.restore(snapshot)
restore_target.close()

Async usage:

import asyncio

from audrey_memory import AsyncAudrey


async def main() -> None:
    async with AsyncAudrey(base_url="http://127.0.0.1:7437") as brain:
        await brain.health()
        await brain.encode("Deploy failed due to OOM", source="direct-observation")
        await brain.recall("deploy failure", limit=3)


asyncio.run(main())

Features

Sync and async clients powered by httpx
Pydantic request and response models
Bearer auth via AUDREY_API_KEY
Optional X-Audrey-Agent header on client requests
Snapshot export and restore support

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

audrey_memory-1.3.0.tar.gz (10.4 kB view details)

Uploaded Sep 2, 2026 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

audrey_memory-1.3.0-py3-none-any.whl (7.3 kB view details)

Uploaded Sep 2, 2026 Python 3

File details

Details for the file audrey_memory-1.3.0.tar.gz.

File metadata

Download URL: audrey_memory-1.3.0.tar.gz
Upload date: Sep 2, 2026
Size: 10.4 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for audrey_memory-1.3.0.tar.gz
Algorithm	Hash digest
SHA256	`c84dfa0fd9f46b2e677337ec664ac4cc5d0431ddecfc050329a7d0779e67b0d8`
MD5	`6ae4b1454bf568b9b14a7078dd523a6c`
BLAKE2b-256	`c9c0865ecd7774f2fb0cd683ae3226a73811c3467a0a35c9dc88ce4b5d20d400`

See more details on using hashes here.

Provenance

The following attestation bundles were made for audrey_memory-1.3.0.tar.gz:

Publisher: publish.yml on Evilander/Audrey

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: audrey_memory-1.3.0.tar.gz
- Subject digest: c84dfa0fd9f46b2e677337ec664ac4cc5d0431ddecfc050329a7d0779e67b0d8
- Sigstore transparency entry: 2686953045
- Sigstore integration time: Sep 2, 2026
Source repository:
- Permalink: Evilander/Audrey@6d1746a6130969feda926efca9cfc409821ff0a0
- Branch / Tag: refs/tags/v1.3.0
- Owner: https://github.com/Evilander
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@6d1746a6130969feda926efca9cfc409821ff0a0
- Trigger Event: release