loci — security grade CAUTION, quality 66/100

Security audit verdict: CAUTION · quality 66/100

Flagged: curl | sh installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by codesstar · Claude Skill · ★ 141

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is loci safe to install? View the security audit →

About loci

The first agent-native memory system. A full brain architecture for AI. English | 中文 The Problem Your AI doesn't remember you. Every conversation starts from zero. You re-introduce yourself. You re-explain your project. You re-describe your preferences. The thing you spent an hour figuring out yesterday? Gone. The decision you made last week? Never happened. And it's not just forgetting between sessions. Chat long enough and the context fills up — your AI starts repeating itself, getting confused, forgetting things you said 20 minutes ago. You restart. Everything you built up is gone. Worse: your memories are scattered. Claude Code's auto-memory is a flat file that gets messy over time. Cursor's memory lives in and breaks across projects. Every t

aiclaude-codememoryopen-sourcepersonal-ai

Quick Facts

Stars141
Forks12
LanguageHTML
CategoryClaude Skill
LicenseMIT
Quality Score65.7423666526691/100
Open Issues3
Last Updated2026-09-02
Created2026-03-07
Platformsclaude-code
Est. Tokens~19k

Compatible Skills

These tools work well together with loci for enhanced workflows:

  • openclaw-config — semantic(0.37)+complementary+rare_topics+similar_pop+shared_platform (52%)

loci alternative? Top 6 similar tools

Looking for a loci alternative? If you're comparing loci with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • daymon by daymonio · ⭐ 368

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • MoltBrain by nhevers · ⭐ 253

    Long-term memory layer for OpenClaw & MoltBook agents that learns and recalls your project context automatical

  • Grov by TonyStef · ⭐ 193

    Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • ciana-parrot by emanueleielo · ⭐ 76

    Self-hosted AI assistant with multi-channel support, scheduled tasks, and extensible skills

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular HTML Agent Tools

Frequently Asked Questions

What is loci?

loci is Memory Palace for AI — persistent memory, identity, and multi-project orchestration for Claude Code. It is categorized as a Claude Skill with 141 GitHub stars.

What programming language is loci written in?

loci is primarily written in HTML. It covers topics such as ai, claude-code, memory.

How do I install or use loci?

You can find installation instructions and usage details in the loci GitHub repository at github.com/codesstar/loci. The project has 141 stars and 12 forks, indicating an active community.

What license does loci use?

loci is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to loci?

The top alternatives to loci on Agent Skills Hub include daymon, MoltBrain, Grov. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools