optimal-engine

optimal-engine is a Memory stores & recall skill for AI agents, published by Miosa-osa in the BusinessOS repository on GitHub. Skillspace rates optimal-engine D (69/100) and the safety scan flagged it for review; the rating is based on static analysis only.

Optimal Engine is a self-hosted second brain and operating engine for human and AI workspaces. It preserves messy sources, organizes them into workspaces and Nodes, classifies Signals, turns extracted assertions into reviewable Claims, promotes accepted Claims into source-backed Facts and Memory Objects, assembles governed Context Packages, and projects the same state into markdown, wiki/API views, CLIs, MCP tools, and app surfaces. Use this skill when building or using persistent organizational memory, workspace topology, source-backed retrieval, agent work loops, multimodal intake, packages/exports, or governed tool/model execution. Architectural commitments: source-first evidence, workspace/Node scope, Signal = Mode + Genre + Type + Format + Structure, Claim -> Fact gate, Memory Core lineage, Context Packages, Active Memory Pools, Skill Packages, and projection surfaces over canonical runtime state. Self-hosted, MIT, runs locally first.

Grade
D
Quality
69 / 100
Safety
Needs review
GitHub stars
90

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubMiosa-osa/BusinessOS

Our review

Architecture
78 / 100
Maturity
Structured: ships references or scripts
Security scan
Medium-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 1 other repositories, in 0 collections

What the scanner flagged

  • reads environment variables

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Memory stores & recall

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.