memor

Memory frameworkOfficial OpenSciLab project

Created by OpenSciLab

Published in openscilab/memor. Publisher page

69 GitHub starsUpdated 2026-10-04

What it is

Reproducible Structured Memory for LLMs

— the description by OpenSciLab

Summary from the brain’s metadata

Reproducible Structured Memory for LLMs Memor: Reproducible Structured Memory for LLMs

How it works

Memory model: JSON files

AutoGineer overview, from the brain’s own files

Memory model: JSON files. Folders: .github (agent config, 9 files); examples (examples, 8 files); tests (tests, 5 files). The agent reads get_message. The agent writes add_response, update_template, update_message, update_message_from_xml, update_score.

Folders
Folder	Role	Files
.github	agent-config	9
examples	examples	8
tests	tests	5
memor	folder	12
otherfiles	folder	6

The agent reads

get_message evidence: README.md

The agent writes

add_response evidence: README.md
update_template evidence: README.md
update_message evidence: README.md
update_message_from_xml evidence: README.md
update_score evidence: README.md
update_role evidence: README.md
update_title evidence: README.md
update_content evidence: README.md
update_map evidence: README.md
update_engine evidence: README.md
add_message evidence: README.md
update_messages evidence: README.md
update_messages_status evidence: README.md

Requirements

Runtimes: Python

Set it up

This brain runs code automatically: 1 script. Review setup.py before opening the folder in Claude Code. No step below turns a hook on for you.
- setup.py: python setup.py
Not scanned by AutoGineerThe author’s README also describes installing it as the PyPI package memor. Read its install section: AutoGineer did not scan that path. https://github.com/openscilab/memor/blob/0f5b66f0806482ddb73b8a33a4d68f19f3280f04/README.md#installation
Created by OpenSciLab. Published in openscilab/memor. Licence: MIT License.

Usage

From the brain’s own files

INSTRUCTION1: "*I'm providing you with a history of a previous conversation. Please consider this context when responding to my new question.*"
INSTRUCTION2: "*Here is the context from a prior conversation. Please learn from this information and use it to provide a thoughtful and context-aware response to my next questions.*"
INSTRUCTION3: "*I am sharing a record of a previous discussion. Use this information to provide a consistent and relevant answer to my next query.*"

Documentation by OpenSciLab

Read the documentation at the source

SECURITY.md

Security policy

Supported versions

Version	Supported
1.4	:white_check_mark:
< 1.4	:x:

Reporting a vulnerability

Please report security vulnerabilities by email to [e-mail address on the upstream page](mailto:e-mail address on the upstream page "e-mail address on the upstream page").

If the security vulnerability is accepted, a dedicated bugfix release will be issued as soon as possible (depending on the complexity of the fix).

56 files · 50 not served here

.coveragerc (not served here)
.github/CODE_OF_CONDUCT.md (not served here)
.github/CONTRIBUTING.md (not served here)
.github/ISSUE_TEMPLATE/bug_report.yml (not served here)
.github/ISSUE_TEMPLATE/config.yml (not served here)
.github/ISSUE_TEMPLATE/feature_request.yml (not served here)
.github/PULL_REQUEST_TEMPLATE.md (not served here)
.github/dependabot.yml (not served here)
.github/workflows/publish_pypi.yml (not served here)
.github/workflows/test.yml (not served here)
.gitignore (not served here)
.pydocstyle (not served here)
ATTRIBUTION.md
AUTHORS.md
AUTOGINEER-RUNS.md
CHANGELOG.md
LICENSE
README.md (not served here)
SECURITY.md
autopep8.bat (not served here)
autopep8.sh (not served here)
codecov.yml (not served here)
examples/README.md (not served here)
examples/dataframe_usage/1_secure_chat.py (not served here)
examples/dataframe_usage/2_session_df.csv (not served here)
examples/dataframe_usage/3_trimmed_chat.py (not served here)
examples/dual_llm_chat_same_instruction.py (not served here)
examples/requirements.txt (not served here)
examples/simple_chat.py (not served here)
examples/xml_usage.py (not served here)
memor/__init__.py (not served here)
memor/errors.py (not served here)
memor/functions.py (not served here)
memor/keywords.py (not served here)
memor/llm_models.py (not served here)
memor/message.py (not served here)
memor/params.py (not served here)
memor/prompt.py (not served here)
memor/response.py (not served here)
memor/session.py (not served here)
memor/template.py (not served here)
memor/tokens_estimator.py (not served here)
otherfiles/RELEASE.md (not served here)
otherfiles/donation.png (not served here)
otherfiles/logo.png (not served here)
otherfiles/meta.yaml (not served here)
otherfiles/requirements-splitter.py (not served here)
otherfiles/version_check.py (not served here)
requirements-dev.txt (not served here)
requirements-latest.txt (not served here)
setup.py (not served here)
tests/test_prompt.py (not served here)
tests/test_prompt_template.py (not served here)
tests/test_response.py (not served here)
tests/test_session.py (not served here)
tests/test_token_estimators.py (not served here)

Advantages

Local-first: the memory stays in files or a database on your own machine (a rule-derived fact from the brain’s files, evidence: README.md)
No API key is named in its files (a rule-derived fact from the brain’s files, evidence: README.md)
Open licence (MIT) (a rule-derived fact from the brain’s files)

Limitations

No ZIP download: install it from its source (a rule-derived fact from the brain’s files)

Security

Risk level: Low risk

This brain runs

Install scripts (1)

setup.py: python setup.py

Low risk: scripts-present (setup.py)

Attribution and licence

Created by

OpenSciLab

Publisher

OpenSciLab (Official OpenSciLab project)

Source

openscilab/memor · commit 0f5b66f

Licence

MIT License (files served here)

ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-12

AutoGineer is not affiliated with or endorsed by OpenSciLab.

Install from source

50 of its files are not served here, so there is no ZIP. openscilab/memor at 0f5b66f