Skill of Skills
📄 skillActivePromisinghigh

MemTensor/MemOS

by MemTensor

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

9.9k

Skill Type

📖 Library & API Reference

Quality Score

97/200

License

Apache-2.0

Forks

903

Last Updated

Jul 13, 2026

Discovered

Jun 12, 2026

Validation

Passed

github.com/MemTensor/MemOS

Quality Breakdown

97/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multi-agent orchestration system: Repository contains .claude/agents/ and .codex/agents/ directories with multiple agent configurations (backend-dev, code-reviewer, design-reviewer, explorer, integration-tester) indicating autonomous agent spawning capability
  • Persistent configuration modification: CLAUDE.md and AGENTS.md files suggest system-level agent configuration and memory persistence across sessions
  • Install scripts present: install.sh and install.ps1 files in apps/memos-local-openclaw enable bootstrap automation for system setup
  • Autonomous operation without approval gates: Agent configuration files (.md and .toml formats) indicate agents can operate independently without explicit human approval per task
  • External code execution: Multiple skill directories (browserwing-admin, browserwing-executor) and postinstall scripts suggest capability to execute external code and perform system-level operations
  • GitHub workflow automation: .github/workflows/ contains CI/CD pipeline definitions (python-release.yml, python-tests.yml) that automate code execution and deployment