Alice Continuity for OpenClaw

v0.2.0

Local-first memory and continuity for OpenClaw — better recall, resumption, correction-aware memory, open-loop tracking, and provenance-backed context.

0· 34·0 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
medium confidence
Purpose & Capability
The name/description (continuity, memory, resumption) match the SKILL.md, README, and USAGE content. Nothing in the package requests unrelated credentials, binaries, or system paths that would be inconsistent with a local memory/continuity integration.
Instruction Scope
The instructions are high-level: they tell the agent/user to identify an OpenClaw workspace, run an 'Alice OpenClaw import path', and connect Alice, but they do not provide concrete commands, code, or explicit permitted file paths. The SKILL implicitly expects access to local OpenClaw memory directories (which is coherent for an import tool) but is vague about exact file I/O and data handling.
Install Mechanism
There is no install spec and no code files to execute; this is instruction-only. That reduces the risk of arbitrary code being downloaded or installed.
Credentials
No environment variables, credentials, or config paths are requested. The described functionality (reading/importing local OpenClaw memory) does not require additional secrets as presented.
Persistence & Privilege
The skill is not marked always:true and does not declare any persistent or cross-skill configuration changes. Autonomous invocation is allowed (platform default) but is not combined with other concerning privileges here.
Assessment
This is an instruction-only skill describing a local-first continuity layer; it does not include code or request credentials, which reduces immediate risk. Before installing or enabling it: 1) Review the GitHub repository linked in the docs (https://github.com/samrusani/AliceBot) to verify implementation and confirm there are no hidden remote endpoints or installers. 2) Understand that the skill implies reading your OpenClaw workspace/memory directories — only allow it access to directories you trust and avoid exposing sensitive system areas. 3) Because the instructions are high-level, ask for or review concrete import commands or scripts you'll run; if a later version adds install scripts, downloads, or requires secrets, reassess immediately. Additional information that would change this assessment: a shipped installer or code files (especially downloads from untrusted URLs), required environment credentials, or explicit instructions to transmit local data to third-party endpoints.

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

latestvk974jfytsekbc0s8sap525ads984tb3g

License

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

Comments