m3-langchain
A recognizable, databricks-langchain-style alias for m3-memory's LangChain
/ LangGraph integration. It contains no code of its own — it re-exports
m3_memory.langchain
and depends on m3-memory[langchain], so pip install m3-langchain gives you the
full, local-first m3 memory layer under a discoverable name.
pip install m3-langchain
from m3_langchain import Memory, M3Store, M3Saver
# Memory → drop-in Mem0 replacement (one-line import swap)
# M3Store → LangGraph BaseStore / backs LangMem
# M3Saver → LangGraph checkpointer (pause / resume / time-travel)
These are the same objects as from m3_memory.langchain import .... New code can
import from either path; this package exists for name-discoverability.
Full integration guide, examples, and the complete surface list (retriever,
chat history, LCEL MemoryWrite/MemoryRetrieve, the m3-native extras
.supersede/as_of=/.forget/.related) live in the main repo:
skynetcmd/m3-memory.
Apache-2.0.
1 maintainer
Metadata
1 maintainer
Release files for m3-langchain 2026.7.15.1
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 |
|---|---|---|---|---|
| m3_langchain-2026.7.15.1.tar.gz | 3.0 kB | Without provenance | Details for m3_langchain-2026.7.15.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| m3_langchain-2026.7.15.1-py3-none-any.whl | Python 3 | none | any | Details for m3_langchain-2026.7.15.1-py3-none-any.whl |
Total release size: 6.0 kB
Release files / m3_langchain-2026.7.15.1.tar.gz
| Download URL | m3_langchain-2026.7.15.1.tar.gz |
|---|---|
| Size | 3.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
40b45c33531e98d9d7cc4b8ed74c8779dddf89812460af3860bb945c6490d440
|
|
BLAKE2b-256 checksum How to use checksums |
cfee1ed1ca1f4c7cd53288392134f1d6aa2dd318aadd4226dd649f390d729c7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.6
|
Release files / m3_langchain-2026.7.15.1-py3-none-any.whl
| Download URL | m3_langchain-2026.7.15.1-py3-none-any.whl |
|---|---|
| Size | 3.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
60f47982d420e1ce1cf9fa1ed0b3335c84bc42d26713dd4c9094cf4d80101487
|
|
BLAKE2b-256 checksum How to use checksums |
920721c6f56a318d0f556684dfe475f493292c50ef492e721304e8bcd366dcf1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.6
|
Security for m3-langchain 2026.7.15.1
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.
