🔌 pluginActivePromisingmedium

memsearch

A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.

Stars

2.0k

Skill Type

📖 Library & API Reference

Quality Score

117/200

License

MIT

Forks

179

Last Updated

Jun 11, 2026

Discovered

Mar 26, 2026

Validation

Passed

github.com/zilliztech/memsearch

Quality Breakdown

117/ 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.

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

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

Contains shell scripts in hooks directory (common.sh, session-start.sh, session-end.sh, user-prompt-submit.sh, stop.sh, parse-transcript.sh) that execute during Claude Code plugin lifecycle
Install script present (plugins/codex/scripts/install.sh) for automated setup
CLAUDE.md and MEMORY.md files indicate persistent configuration/state management for AI agents
AGENT.md file suggests agent-specific behavior configuration
Multiple platform plugins (Claude Code, Codex, OpenClaw, OpenCode) with hook-based execution model
Shell scripts execute during user-prompt submission and session lifecycle events, potentially without explicit user approval per command