memoricai Python SDK
Stdlib-only client for the memoricai /v1 HTTP API (Python 3.9+).
from memoricai import Client
client = Client("http://localhost:7373", "mc_...")
doc = client.add_text("My name is Ada.", container_tag="mc_project_default")
client.wait_for_document(doc["id"])
res = client.search_memories("what is my name",
container_tag="mc_project_default", digest=True)
print(res["digest"]) # ready-to-inject, date-stamped context
print(client.profile("mc_project_default"))
Install from the repo: pip install ./sdks/python. Transient failures (429/5xx)
are retried with exponential backoff; API errors raise MemoricaiError(status, message).
The client covers the complete v0.3.2 engine surface: batch and multipart
ingestion, document lifecycle operations, search/context/profile, memory
management, projects and container tags, settings and scoped keys, buckets and
inferred-memory review, analytics, connectors, MCP helpers, provisioning, and
the memory router. request() is the forward-compatible low-level escape hatch.
Metadata
Release files for memoricai 0.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| memoricai-0.3.2.tar.gz | 9.6 kB | Without provenance | Details for memoricai-0.3.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| memoricai-0.3.2-py3-none-any.whl | Python 3 | none | any | Details for memoricai-0.3.2-py3-none-any.whl |
Total release size: 17.4 kB
Release files / memoricai-0.3.2.tar.gz
| Download URL | memoricai-0.3.2.tar.gz |
|---|---|
| Size | 9.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a25d8f74788304f39da30b5987f172a0249bda7e402981b05e942a4eb1b6e0e8
|
|
BLAKE2b-256 checksum How to use checksums |
bc49bad0bb9b047e6523fc88ad19b140757043539a1a982cb378a88821e0fa9c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Release files / memoricai-0.3.2-py3-none-any.whl
| Download URL | memoricai-0.3.2-py3-none-any.whl |
|---|---|
| Size | 7.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ca0eab691514a31aab0c3f5b73ea5a1b2ca00f13a5f73e19e36e878fda930e5b
|
|
BLAKE2b-256 checksum How to use checksums |
087d3545e8733e28317bea547478d0d7e25458ac5539bc119874c090edae760e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Security for memoricai 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.