Memory Governor

v0.2.9

Memory governance kernel for AI agents that complements OpenClaw Dreaming with explicit correction staging, target-class routing, adapter boundaries, and saf...

1· 133·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (a memory-governor governance kernel) align with the shipped files: policy docs, adapter/manifest guidance, fallback templates, and helper scripts for host checking, frontmatter validation, candidate review, and a lightweight bootstrap. There are no unrelated environment variables, binaries, or credentials requested.
Instruction Scope
SKILL.md and the references concentrate on classification, routing, promotion and exclusion rules. The included scripts read host manifests and structured memory files and the bootstrap script creates example files. This is coherent with the stated purpose, but note that running the scripts will read and (in the case of bootstrap) write files in a host directory — exactly as documented.
Install Mechanism
No install spec; the skill is instruction-only and ships helper scripts. No downloads, package managers, or external installers are referenced in the metadata. Risk from installation is low since nothing will be pulled from arbitrary URLs.
Credentials
The skill requires no environment variables, credentials, or config paths. The job it performs (governing memory artifacts) legitimately needs access to host files and manifests, which is consistent with the provided scripts and guidance.
Persistence & Privilege
Flags are default (always: false). The package does include a bootstrap script that can create host files when run, but installation metadata does not request permanent platform privileges or automatic modification of unrelated skills; the docs explicitly state integration should be explicit and not silent.
Assessment
This skill is internally consistent with its documentation: it provides rules, templates, and small helper scripts to check and bootstrap host-level memory adapter files. Before running anything, review the included scripts (bootstrap-generic-host.sh, check-memory-host.py, validate-memory-frontmatter.py, review-learning-candidates.py) so you understand what files they will read or create. The bootstrap script will create example files in a target directory (it documents that it won't overwrite existing files). Avoid copying secrets into the memory files it manages (references/exclusions.md explicitly forbids storing tokens/passwords). If you do not want the agent or scripts to access certain workspace files, run them in a controlled directory or inspect/limit file permissions. If you need stricter runtime guarantees, run the scripts manually rather than allowing autonomous agent invocation. Overall, the package appears to do what it claims; proceed if that governance model fits your host and you are comfortable with the scripts' filesystem access.

Like a lobster shell, security has layers — review code before you run it.

agentvk977ycb9jqkjajawr7s9ctjxyd849qgebetavk977ycb9jqkjajawr7s9ctjxyd849qgegovernancevk977ycb9jqkjajawr7s9ctjxyd849qgelatestvk97efekt2dhehx5e7c3ss6btm184aa4cmemoryvk977ycb9jqkjajawr7s9ctjxyd849qgeopenclawvk977ycb9jqkjajawr7s9ctjxyd849qge

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments