Skip to main content

mnemo-db

PyPI distribution of Mnemo — an MCP-native memory database for AI agents.

pip install mnemo-db

The package directory and import path are still mnemo — only the PyPI distribution name has the -db suffix because the unqualified mnemo is held by an unrelated 2021 notebook project. Your code keeps saying:

from mnemo import MnemoClient

Quick start

from mnemo import MnemoClient

client = MnemoClient(db_path="agent.mnemo.db", agent_id="agent-1")

# Three primitives carry most workflows.
result = client.remember("The user prefers dark mode", tags=["preference"])
memories = client.recall("user preferences", limit=5)
client.forget([result["id"]])

# Mem0-compatible aliases also work:
# client.add(...), client.search(...), client.delete(...)

# Write provenance + FORGET BY PROVENANCE — audit who wrote what, then clean up.
prov = client.write_provenance(result["id"])        # who wrote it, under what authority
client.writes_by_principal("agent-1")                # everything a principal wrote
client.forget_by_principal("agent-1", "hard_delete") # revoke it all (audit trail survives)

# Each provenance record has a `flags` list. On remember(), content shaped like a
# provider opaque reasoning payload (arXiv:2608.09867 — these have leaked secrets
# in the wild) is flagged "opaque_reasoning_payload" and RECORDED, not rejected,
# so you can revoke it by principal/session later. It detects a SHAPE — not proof
# a secret is present — and never decodes the content.
if "opaque_reasoning_payload" in (prov or {}).get("flags", []):
    client.forget_by_session(prov["session_id"], "redact")

What's in the box

Surface What
MnemoClient Native PyO3 binding to the Rust engine — DuckDB storage, USearch HNSW vector index, Tantivy full-text index, hybrid retrieval, hash-chained audit log
MnemoMemoryToolServer Anthropic memory_20250818 6-op handler. pip install 'mnemo-db[anthropic-memory-tool]'
MnemoLettaShared Letta-style Conversations adapter for shared agent memory
S3Workspace / CloudflareR2Workspace OpenAI Agents SDK GA snapshot store backends. pip install 'mnemo-db[openai-sandbox-s3]' or [openai-sandbox-r2]
MnemoAgentMemory (OpenAI), Mem0Compat, MnemoCheckpointer (LangGraph 1.x — ASMDCheckpointer is the back-compat alias), 12 more Drop-in framework integrations. Install the matching extra.

Optional extras

pip install 'mnemo-db[langgraph]'              # LangGraph checkpoint
pip install 'mnemo-db[crewai]'                 # CrewAI memory
pip install 'mnemo-db[openai-agents]'          # OpenAI Agents SDK
pip install 'mnemo-db[claude]'                 # Claude Agent SDK
pip install 'mnemo-db[anthropic-memory-tool]'  # memory_20250818
pip install 'mnemo-db[openai-sandbox-s3]'      # S3 workspace backend
pip install 'mnemo-db[openai-sandbox-r2]'      # Cloudflare R2 workspace backend
pip install 'mnemo-db[benchmark]'              # LoCoMo / LongMemEval harness

Each extra fails closed if not installed — from mnemo import MnemoMemoryToolServer will raise ImportError cleanly when [anthropic-memory-tool] isn't on the path.

License + source

Source: https://github.com/sattyamjjain/mnemo. Apache-2.0.

Documentation: https://github.com/sattyamjjain/mnemo#readme. Issues: https://github.com/sattyamjjain/mnemo/issues.

Metadata

Release files for mnemo-db 0.5.30

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mnemo-db 0.5.30
File Size Uploaded
mnemo_db-0.5.30.tar.gz 401.5 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for mnemo-db 0.5.30
File
mnemo_db-0.5.30-cp313-cp313-manylinux_2_28_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64 Details
mnemo_db-0.5.30-cp313-cp313-macosx_11_0_arm64.whl CPython 3.13 CPython 3.13 macOS 11.0+ ARM64 Details
mnemo_db-0.5.30-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details
mnemo_db-0.5.30-cp312-cp312-macosx_11_0_arm64.whl CPython 3.12 CPython 3.12 macOS 11.0+ ARM64 Details
mnemo_db-0.5.30-cp311-cp311-manylinux_2_28_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.28+ x86-64 Details
mnemo_db-0.5.30-cp311-cp311-macosx_11_0_arm64.whl CPython 3.11 CPython 3.11 macOS 11.0+ ARM64 Details
mnemo_db-0.5.30-cp310-cp310-manylinux_2_28_x86_64.whl CPython 3.10 CPython 3.10 Linux glibc 2.28+ x86-64 Details
mnemo_db-0.5.30-cp310-cp310-macosx_11_0_arm64.whl CPython 3.10 CPython 3.10 macOS 11.0+ ARM64 Details

Total release size: 172.9 MB

Release files / mnemo_db-0.5.30.tar.gz

Download URL mnemo_db-0.5.30.tar.gz
Size 401.5 kB
Tags Source
SHA-256 checksum
How to use checksums
a7633a5352a76a75bf919ea4c6fdab8fe8b56decb09ce58e6bf70ed565fda926
BLAKE2b-256 checksum
How to use checksums
0b3b0f689ece9414c912cd27692104339f62dd159ea6b01f2c0ebc606f846a3e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp313-cp313-manylinux_2_28_x86_64.whl

Download URL mnemo_db-0.5.30-cp313-cp313-manylinux_2_28_x86_64.whl
Size 24.0 MB
Tags CPython 3.13 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
0eeef43bf2de840362bc6527b656a882bb6b45cb665f754f35048c63d77028c2
BLAKE2b-256 checksum
How to use checksums
268c79c30a012be65fbdb5632550971a8ad4acf98de57a039140009c696013ef
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp313-cp313-macosx_11_0_arm64.whl

Download URL mnemo_db-0.5.30-cp313-cp313-macosx_11_0_arm64.whl
Size 19.1 MB
Tags CPython 3.13 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
fb771ea5e186053eca3a2e8b607974699cb8b3aff3abcf718a47d9c032f007df
BLAKE2b-256 checksum
How to use checksums
46c2ec46bde05b37cdff59988ee030d0d5a8e8469f8c177af631e652a064a7cb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp312-cp312-manylinux_2_28_x86_64.whl

Download URL mnemo_db-0.5.30-cp312-cp312-manylinux_2_28_x86_64.whl
Size 24.0 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
4ba22ede5bd2ffcd8d9ffdd8faf51c99fa557442e093fa323ccef995d9c3c93a
BLAKE2b-256 checksum
How to use checksums
7b6e87b8d96b309c285c1caa4151fb89a178f0641af9bb5af6a4bde168118055
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp312-cp312-macosx_11_0_arm64.whl

Download URL mnemo_db-0.5.30-cp312-cp312-macosx_11_0_arm64.whl
Size 19.1 MB
Tags CPython 3.12 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
3f792ced5946a86448cf9a80a326540c2a70e290b0f18990545ca5663c6dc481
BLAKE2b-256 checksum
How to use checksums
aa4fa65b280499ecbbd32201e465bd1fa166f92e7ea704278ed6efc121e1a516
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp311-cp311-manylinux_2_28_x86_64.whl

Download URL mnemo_db-0.5.30-cp311-cp311-manylinux_2_28_x86_64.whl
Size 24.0 MB
Tags CPython 3.11 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
b533121dc4efb01fa49156884f573cd3ef88676a81a3b3db1abb824e8633da35
BLAKE2b-256 checksum
How to use checksums
fdfa1ef616a0270cd43de00e5faea578a6192c3387f4db38d7d99a57cab12ddf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp311-cp311-macosx_11_0_arm64.whl

Download URL mnemo_db-0.5.30-cp311-cp311-macosx_11_0_arm64.whl
Size 19.1 MB
Tags CPython 3.11 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
3d9c2be2a6fd950ffddc6f7cba1c8b97c316f08802bbefb77796f33a8a1a4521
BLAKE2b-256 checksum
How to use checksums
d48ad76273ac9d06afd8cd63724302e4ea4a13a7a8e7c2eec320d32219c03773
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp310-cp310-manylinux_2_28_x86_64.whl

Download URL mnemo_db-0.5.30-cp310-cp310-manylinux_2_28_x86_64.whl
Size 24.0 MB
Tags CPython 3.10 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
4f53f32c2bfe0bf1065112a053f0ccb6313373e42996e133c6ca980c30851dee
BLAKE2b-256 checksum
How to use checksums
0aa1d44cecc07677f3b73adf4a70305c15feb867ae63c6975836bca4fa6bae28
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log

Release files / mnemo_db-0.5.30-cp310-cp310-macosx_11_0_arm64.whl

Download URL mnemo_db-0.5.30-cp310-cp310-macosx_11_0_arm64.whl
Size 19.1 MB
Tags CPython 3.10 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
6f367194557c97722d8c352eabbc7b6b785894eccabe0eb14f054bb157e34a9a
BLAKE2b-256 checksum
How to use checksums
0a3c6be49245e0cc6aa5abc4e9f3a87e5d687f30c42f8bfcaaa053dd0344489b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 6, 2026.

Transparency log
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