Source-grounded memory for agents that learn over time.
Project description
Mnemoir Provenance
Source-grounded memory for agents that learn over time.
Mnemoir Provenance (pronounced “nem-wahr”) is a local-first, source-grounded memory core for agents, assistants, and multi-agent systems. It preserves citations, correction history, source coverage, and recoverable maintenance receipts so memory remains inspectable as it evolves.
Mnemoir Provenance is an independent open-source project and is not affiliated with other projects using similar names.
Why it is different
- Cited recall reports which sources were searched and which were missing or degraded.
- Evidence, proposals, review, and durable writes are separate operations.
- Revisions, supersession, tombstones, and rollback preserve history.
- Overflow maintenance is preconditioned, authorized, auditable, and recoverable.
- The core works through Python or a JSON CLI; Hermes is an optional reference adapter.
Quick start
python -m venv .venv
. .venv/bin/activate
python -m pip install .
export MNEMOIR_DB="$PWD/demo.sqlite"
mnemoir ingest --limit 5
mnemoir recall "source grounded memory" --limit 3
The response is JSON. A healthy result includes cited_results and source_coverage; insufficient evidence returns an explicit empty or degraded state instead of an uncited fallback.
Mental model
sources -> raw events -> evidence -> proposals -> versioned memories
| |
+------ cited recall + coverage + receipts -----+
Canonical state is SQLite. Markdown/wiki output is derived and never becomes canonical merely because it is readable.
Integration paths
Documentation
Start at docs/index.md. Security boundaries are in SECURITY.md and the threat model. Overflow and writeback are explained in the operations guide.
Boundaries
This project is local/self-hosted software, not a hosted service. Installation does not grant access to arbitrary files, enable live writeback, start a network service, configure a host, or promote memory automatically. Citations identify evidence; they do not guarantee truth. Ranking heat affects attention, not authority.
License
MIT. See LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mnemoir_provenance-0.2.0.tar.gz.
File metadata
- Download URL: mnemoir_provenance-0.2.0.tar.gz
- Upload date:
- Size: 740.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6f380812fe2cd1b6657b5665ae3c1d1f02f9d76d0ac610edc972c4a593acbe14
|
|
| MD5 |
6abdab2825a42baff302b2bbb1d64b47
|
|
| BLAKE2b-256 |
35fe6d112324be27e08d80c2b59d103c690f6ff30009a437573023cc3f1e3793
|
Provenance
The following attestation bundles were made for mnemoir_provenance-0.2.0.tar.gz:
Publisher:
publish.yml on sayyied/mnemoir-provenance
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mnemoir_provenance-0.2.0.tar.gz -
Subject digest:
6f380812fe2cd1b6657b5665ae3c1d1f02f9d76d0ac610edc972c4a593acbe14 - Sigstore transparency entry: 2187922702
- Sigstore integration time:
-
Permalink:
sayyied/mnemoir-provenance@d6e1523720a4bd9a5c79afb81a2ae1be8079c1d9 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/sayyied
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@d6e1523720a4bd9a5c79afb81a2ae1be8079c1d9 -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file mnemoir_provenance-0.2.0-py3-none-any.whl.
File metadata
- Download URL: mnemoir_provenance-0.2.0-py3-none-any.whl
- Upload date:
- Size: 258.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
81eedc504556437d4783263a223d89cd6890c9c25cb3c8231a07d97064fb73ae
|
|
| MD5 |
abefcca5f3d87bba04a57faad4f21d16
|
|
| BLAKE2b-256 |
7a2355d63de7ac84b762e1dddaefe628c295c349a4399cf22227563b3ce1d02b
|
Provenance
The following attestation bundles were made for mnemoir_provenance-0.2.0-py3-none-any.whl:
Publisher:
publish.yml on sayyied/mnemoir-provenance
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mnemoir_provenance-0.2.0-py3-none-any.whl -
Subject digest:
81eedc504556437d4783263a223d89cd6890c9c25cb3c8231a07d97064fb73ae - Sigstore transparency entry: 2187922721
- Sigstore integration time:
-
Permalink:
sayyied/mnemoir-provenance@d6e1523720a4bd9a5c79afb81a2ae1be8079c1d9 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/sayyied
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@d6e1523720a4bd9a5c79afb81a2ae1be8079c1d9 -
Trigger Event:
workflow_dispatch
-
Statement type: