egregore — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by egregore-labs · Claude Skill · ★ 280

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

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

About egregore

A shared intelligence layer for teams using Claude Code. Website · Community · MIT License Egregore is a shared cognition layer for AI-native collaboration. It turns Claude Code into an inhabitable production environment where every session, handoff, and decision accumulates into a living memory owned by your organization. With use, the deep context that accumulates enables seamless continuity across multi-agent workflows, visibility into organizational patterns and decision-making, and persistence of collective intelligence across people, sessions, and time. https://github.com/user-attachments/assets/71a690fb-8a4e-4d0b-9a61-e6cdc7595430 Install This walks you through GitHub auth, names your egregore, creates the repos (instance + shared memory), clones everything locally, and adds a shell command to your profile. To join an existing egregore: (You will need an invitation from the instance owner. See below.) If your org blocks third-party GitHub Apps, there's a gh-CLI install path: see INSTALL-GH.md or the docs. Start Open a new terminal:

aiclaudeclaude-codeclicollaborationdeveloper-toolsmemorymultiplayershared-memoryteam

Quick Facts

Stars280
Forks20
LanguageShell
CategoryClaude Skill
LicenseMIT
Quality Score68.0235055076551/100
Open Issues17
Last Updated2026-09-03
Created2026-03-24
Platformsclaude-code, cli
Est. Tokens~11k

egregore alternative? Top 6 similar tools

Looking for a egregore alternative? If you're comparing egregore 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.

  • Grov by TonyStef · ⭐ 193

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

  • claude-duet by EliranG · ⭐ 143

    Two devs, one Claude. Share a Claude Code session in real-time with E2E encryption.

  • codesyncer by bitjaru · ⭐ 69

    Claude forgets everything when the session ends. CodeSyncer makes it remember.

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 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.

  • clay by chadbyte · ⭐ 399

    A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is egregore?

egregore is Shared intelligence layer for organizations. It is categorized as a Claude Skill with 280 GitHub stars.

What programming language is egregore written in?

egregore is primarily written in Shell. It covers topics such as ai, claude, claude-code.

How do I install or use egregore?

You can find installation instructions and usage details in the egregore GitHub repository at github.com/egregore-labs/egregore. The project has 280 stars and 20 forks, indicating an active community.

What license does egregore use?

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

What are the best alternatives to egregore?

The top alternatives to egregore on Agent Skills Hub include Grov, claude-duet, codesyncer. 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