crewai-memory-core
Shared core for building CrewAI unified-memory StorageBackend implementations. CrewAI 1.10+ has one Memory engine (LLM analysis, consolidation, scope inference, composite scoring) over a pluggable storage protocol; this core implements the whole protocol — save / search / delete / update / get_record / list_records / get_scope_info / list_scopes / list_categories / count / reset / touch_records and the async variants — so a backend only supplies five primitives:
from crewai_memory_core import MemoryBackend
class MyBackend(MemoryBackend):
def _put(self, rows): ... # upsert rows by id
def _get(self, record_id): ... # -> row | None
def _delete_ids(self, ids): ... # -> int deleted
def _scan(self, scope_prefix): ... # every row in the scope subtree
# optional — native ANN; default ranks _scan rows by cosine in Python
def _vector_search(self, vector, scope_prefix, limit): ... # -> [(row, score), ...]
A row is a dict of the MemoryRecord fields plus embedding. Scope paths are hierarchical (/company/team/user); a prefix matches the scope itself and everything under it, never a sibling that merely shares characters (/a does not match /ab).
Use a backend with CrewAI:
from crewai import Crew
from crewai.memory import Memory
memory = Memory(storage=MyBackend(...))
crew = Crew(agents=[...], tasks=[...], memory=memory) # or set_memory_storage_factory(...) once at startup
crewai_memory_core.testing ships FakeEmbedder (deterministic, no network — pass as Memory(embedder=...)) and InMemoryBackend; crewai_memory_core.contract is an importable test suite every provider runs, including an end-to-end pass through CrewAI's real Memory engine with zero LLM calls.
Concrete backends: crewai-memory-dynamodb, crewai-memory-postgres, crewai-memory-cosmosdb, crewai-memory-firestore.
Docs: https://skamalj.github.io/agentstate-reducer/
License
MIT
Metadata
Release files for crewai-memory-core 0.1.0
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 |
|---|---|---|---|---|
| crewai_memory_core-0.1.0.tar.gz | 8.6 kB | Without provenance | Details for crewai_memory_core-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| crewai_memory_core-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for crewai_memory_core-0.1.0-py3-none-any.whl |
Total release size: 18.5 kB
Release files / crewai_memory_core-0.1.0.tar.gz
| Download URL | crewai_memory_core-0.1.0.tar.gz |
|---|---|
| Size | 8.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0f8c23ce4653c8700984c7ee16e2a7f2a7a07adbc23eebe55497b8f91023402d
|
|
BLAKE2b-256 checksum How to use checksums |
a1c48ff24732625a02e352c1e25653755d059bc1478b1bad6e87b0f8e356bc0e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.23 {"installer":{"name":"uv","version":"0.11.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / crewai_memory_core-0.1.0-py3-none-any.whl
| Download URL | crewai_memory_core-0.1.0-py3-none-any.whl |
|---|---|
| Size | 10.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3481027f4e0ae778e8a1af2eb72882f364c605cf509f1e650ea6ecc4f2c6ebcc
|
|
BLAKE2b-256 checksum How to use checksums |
1be44f5ce7090b870b3e7a08d3a1d989ee05dea8c02643c11dec45fbbd97d119
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.23 {"installer":{"name":"uv","version":"0.11.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for crewai-memory-core 0.1.0
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.