gryph — security grade SAFE, quality 75/100

Security audit verdict: SAFE · quality 75/100

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 safedep · Agent Tool · ★ 161

Last updated: 2026-08-30 · Indexed by AgentSkillsHub · Auto-synced every 8h

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

About gryph

AI coding agents have no security boundaries. Gryph is building one. Everyone runs YOLO mode. Nobody checks what happened. Gryph does. Quick Start · Demo · Supported Agents · Use Cases [![Website](https://img.shields.io/badg

ai-agents ai-developer-tools claude-code gemini-cli security

Quick Facts

Stars	161
Forks	19
Language	Go
Category	Agent Tool
License	Apache-2.0
Quality Score	75.2644604012915/100
Open Issues	7
Last Updated	2026-08-30
Created	2026-01-29
Platforms	claude-code, cli, gemini, go
Est. Tokens	~18k

Compatible Skills

These tools work well together with gryph for enhanced workflows:

rampart — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (55%)
claude-code-supervisor — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)

gryph alternative? Top 6 similar tools

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

GAAI-framework by Fr-e-d · ⭐ 158
Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discove
vestige by samvallad33 · ⭐ 628
Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac
genie by automagik-dev · ⭐ 338
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated work
orchestkit by yonatangross · ⭐ 278
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
agent-skills by jdrhyne · ⭐ 241
A collection of AI agent skills for Clawdbot, Claude Code, Codex
SecOpsAgentKit by AgentSecOps · ⭐ 184
Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan c

More Agent Tool Tools

Explore other popular agent tool tools:

awesome-claude-code ⭐ 54.3k
open-saas ⭐ 15.8k
notebooklm-skill ⭐ 7.8k
playwright-skill ⭐ 3.0k
skills ⭐ 2.0k
agent-skills ⭐ 6.4k
raptor ⭐ 3.8k
excalidraw-diagram-skill ⭐ 4.3k
chinese-novelist-skill ⭐ 2.8k
claude-code-skill-factory ⭐ 844

View all Agent Tool tools →

Popular Go Agent Tools

github-mcp-server ⭐ 33.0k · MCP Server
nginx-ui ⭐ 11.5k · MCP Server
xiaohongshu-mcp ⭐ 15.8k · MCP Server
httprunner ⭐ 4.3k · MCP Server
ENScan_GO ⭐ 4.6k · MCP Server

Frequently Asked Questions

What is gryph?

gryph is Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.. It is categorized as a Agent Tool with 161 GitHub stars.

What programming language is gryph written in?

gryph is primarily written in Go. It covers topics such as ai-agents, ai-developer-tools, claude-code.

How do I install or use gryph?

You can find installation instructions and usage details in the gryph GitHub repository at github.com/safedep/gryph. The project has 161 stars and 19 forks, indicating an active community.

What license does gryph use?

gryph is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to gryph?

The top alternatives to gryph on Agent Skills Hub include GAAI-framework, vestige, genie. 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 Agent Tool tools