Skip to content
KitploitKITPLOIT
OutilsExploitsBlog
Log in
Soumettre
OutilsExploitsBlog
Soumettre

Outils de Hacking, PenTest et Cybersécurité pour votre Arsenal de Sécurité !

Kitploit est un répertoire d'outils de hacking, de cybersécurité et de pentesting. Découvrez les dernières mises à jour des projets pour trouver des vulnérabilités, analyser des systèmes, automatiser les tests et renforcer votre sécurité.

FluxContactConfidentialité© 2026 Kitploit

Répertoire d'outils

Catégories

Voir toutes les catégories
Loading categories
gryph — Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more. | Kitploit
Outils/GitHubGitHub/safedep/gryph
Defensive ToolsScripting & AutomationConfiguration AuditingDevSecOpsPrivacySecret DetectionIncident ResponseAI SecurityLog Analysis
GitHubsafedep/gryph

gryph

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

Voir le dépôtSite web
18323141il y a 7 joursVérifié par Kitploit
Partager
Contenu non disponible dans la langue demandée. Affichage de la version anglaise.

Gryph - Security Layer for AI Coding Agents

AI coding agents have no security boundaries. Gryph is building one.

Everyone runs YOLO mode. Gryph enforces guardrails and keeps the audit trail.

Quick Start · Demo · Supported Agents · Use Cases · Security Policy

GitHub stars Downloads Go Report Card License Release CodeQL Website Discord


AI coding agents (Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode) can read any file, write anywhere, and execute arbitrary commands on a developer's machine. They run dozens of tool calls per session. There are no boundaries on what they can do and no audit trail when something goes wrong.

Gryph fixes that. It hooks into agents, enforces YAML policy rules that block, warn, or guide actions in real time, and logs every event to a local SQLite database for review and audit. All data stays local. No cloud, no telemetry.

Gryph Interactive Query Demo

The Problem

A developer asks Claude Code to refactor a module. It runs 47 tool calls in 90 seconds. Then the tests fail.

  • Which files did the agent read before making changes?
  • Did it run shell commands that were not expected?
  • Did it touch config files, secrets, or CI pipelines?
  • What did the file look like before and after?

Without Gryph, developers are left guessing. With Gryph, gryph logs shows everything.

Quick Start

# Install Gryph with one command
curl -fsSL https://raw.githubusercontent.com/safedep/gryph/main/install.sh | sh

# Setup gryph for available agents
gryph install                    # hooks into all detected agents
gryph status                     # verify setup

# ... use your AI agent normally ...
gryph logs                       # see what happened
Other install methods
# Homebrew (macOS/Linux)
brew install safedep/tap/gryph

# npm
npm install -g @safedep/gryph

# Go
go install github.com/safedep/gryph/cmd/gryph@latest

Pre-built binaries for macOS, Linux, and Windows are available on the GitHub Releases page.

Tip: Set logging.level to full to see file diffs and raw events: gryph config set logging.level full. See Configuration for details.

Supported Agents

AgentHook Support
Claude CodeFull (PreToolUse, PostToolUse, Notification)
CodexFull (PreToolUse, PostToolUse, SessionStart, UserPromptSubmit, Stop)
Command CodeFull (PreToolUse, PostToolUse, Stop, SessionStart)
CursorFull (file read/write, shell execution, MCP tools)
Devin CLIFull (PreToolUse, PostToolUse, SessionStart, UserPromptSubmit, Stop, SessionEnd)
Gemini CLIFull (BeforeTool, AfterTool, Notification)
OpenCodeFull (tool.execute, session events)
Pi AgentFull (tool_call, tool_result, session events)
WindsurfFull (file read/write, commands, MCP tools)

Note: Codex hooks require enabling the codex_hooks feature flag in your Codex configuration (~/.codex/config.toml):

[features]
codex_hooks = true

Note: Devin CLI also loads Claude Code hooks from ~/.claude/settings.json by default (read_config_from.claude). When gryph hooks are installed for both agents, one Devin session emits devin events and claude-code events. Disable read_config_from.claude in the Devin user config to keep one stream.

One command installs hooks for all detected agents. No per-agent setup required.

See It in Action

Live streaming of agent actions as they happen with gryph logs --live:

Gryph Live Logs Demo

Use Cases

ScenarioHow Gryph Helps
Replay the full sessiongit diff shows final changes. Gryph shows the full sequence: what the agent read, what it ran, what it wrote and reverted, and in what order.
Catch invisible side effectsAgents run shell commands that leave no trace in git (npm install, curl, rm). gryph query --action exec surfaces them all.
Sensitive file accessGryph flags access to .env, *.pem, *.key, and similar files automatically. Actions are logged but content is never stored.
Block risky agent actionsAuthor YAML rules to block destructive commands, refuse writes that leak credentials, or scope behavior per agent or project. See Security Policy.
Security reviewExport events to your SIEM, or use the OpenSearch observability example for centralized dashboards and threat detection alerts.
Cost and token trackingTrack per-session token usage and estimated costs across models and agents. See docs
Compare agentsFilter by --agent to see how different agents approach the same task: which reads more, which runs more commands, which costs more.

How It Works

Gryph Architecture

Gryph installs lightweight hooks into AI coding agents. When an agent reads a file, writes a file, or executes a command, the hook sends a JSON event to Gryph. Events are stored in a local SQLite database and can be queried anytime. Because Gryph hooks into both pre-tool and post-tool events, it captures the full lifecycle of every agent action.

Security Policy

Télécharger l’outil

Populaires

Voir tout →

Découvrez les outils les plus utilisés par notre communauté.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 La boîte à outils OSINT ultime : graphe d'enquête, notation de confiance, familles d'alias, carte, chronologie et rapports. 49 modules, plus de 400 sites, aucune clé API requise.

    732
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # Application d'exécution en un clic GhostLock (CVE-2026-43499)

    506
  • 3

    ARTEX

    baarai/artex

    Plateforme autonome de tests d'intrusion multi-agents basée sur des LLM, avec agents planificateur/ouvrier, graphes d'actifs et d'exploration, enregistrement du trafic MITM et retest des vulnérabilités.

    405
  • 4

    redforge

    cybersecurity91/redforge

    Boîte à outils red team côté navigateur avec 102 outils hors ligne pour la reconnaissance, la génération de payloads, les attaques par identifiants, la cryptographie, l'encodage et le reporting d'engagement.

    342
  • 5

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    Le système d'action pour la cybersécurité native IA—où l'intention devient une exécution gouvernée, les preuves deviennent une mémoire opérationnelle, et chaque opération améliore la suivante.

    261
  • 6

    antifox

    antifox-ai/antifox

    Plateforme de test d'intrusion autonome multi-agents par IA qui exécute la reconnaissance, la découverte de la surface d'attaque, la validation de l'exploitation et la livraison de rapports étayés par des preuves.

    259

Explorer tous les outils

Parcourez notre collection d'outils

Voir tous les outils →