Cluster 462134

grith-ai/grith

OS-level security supervisor for AI coding agents. Gates security-relevant syscalls on Linux and…

digital-foundry/actualis

What actually ran. Reads existing coding-agent logs and turns them into clear answers about…

AGGIB/Stroq

Local action firewall for AI coding agents: scans what the agent reads, taints the session, blocks…

LuD1161/agentjail

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked…

lennney/stop-that-shit

Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。…

radiusmethod/gitlab-kiosk

a read-only GitLab CLI for coding agents

agent-contracts/skill-preflight

One-command pre-install scorecard for AI agent skills: security, permissions, token cost,…

OactoDev/claude-code-field-kit

Battle-tested drop-in kit for Claude Code: a safety hook (tested), lean CLAUDE.md templates, and a…

amalucelli/steer

Rule engine for agent tool calls: deny, rewrite, or attach context to a call before it runs. One…

vandith1/agent-guard

A pre-execution guard that stops your coding agent running destructive commands. One shell file, no…

termaxa/termaxa

A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude…

rashedInt32/claude-hl

Syntax colours for shell commands in Claude Code's output, Codex-style. A PTY wrapper; Claude Code…

klars-ai/agentobs

Stop your AI coding agent before it overspends. Budget limits, guardrails and cost tracking for…

kontext-security/sandy

Secure agents in seconds by running them in a sandbox.

h5i-dev/h5i

Fast, security-first headless browser for AI agents. Pure Rust, no Chromium or V8. Built for…

talos-kernel/talos

Self-hosted AI agent for terminal and Telegram, with Claude/Codex workers, live activity and a…

aminueza/Keyfence

Local proxy that keeps your API keys and secrets out of LLM requests. Works with Claude Code,…

Isa1asN/beckon

Distinct sounds for your AI coding agent: know whether it finished, needs a decision, or failed,…

aiconnai/agentshield

🛡️ The security firewall for AI agent tools & MCP servers (Claude 5, GPT-5.6, Gemini 3.8,…

kstenerud/yoloai

Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.