Search
Maggy Contributors
Maggy — a local AI engineering command center: multi-model routing, intent graph, memory, and a web dashboard for Claude Code.
...moreAkaash
Mask PII in LLM tool-call outputs before they reach the model, with role-based access control. Zero dependencies.
aiquilibria
A governed coding agent CLI built on Claude Code. Runs inside an isolated Docker container with operator-controlled policy baked into the image, per-tool-call audit logging, and QA gates enforced before every session is accepted.
...moreAkash Kumar Dey
Antarraksha AI Agent Enforcement SDK for LangChain
D4rk-3ch0
AI 自主渗透测试系统，基于 ARTEX v0.3.15 二次开发。保留原有主体框架，增强蜜罐识别、出口审查、范围强制（RoE）与反测绘门控，引入思维链提示词框架。AGPL-3.0 · 仅限授权环境使用
Ashutosh Rana
Reference patterns for compliance-aware retrieval-augmented workflows, context continuity, and governed AI integration in enterprise environments.
...moreGitHub Actions
Token usage and cost tracking for AI providers (OpenAI, Anthropic) with per-model pricing, usage reports, and budget alerts
...moretonioloewald
Type-safe JavaScript dialect with runtime validation, sandboxed VM execution, and AI agent orchestration. Transpiles TypeScript to validated JS with fuel-metered execution for untrusted code.
...morefncreator22
A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.
wdfdsyhb
11 种漏洞类型的完整挖法：方法论、payload 方向、真实案例、40 工具 | Full methodology for 11 vuln classes: steps, payloads, cases, 40 tools
overthetop
The world's first autonomous AI agent with built-in cybersecurity
mradermacher
AI model: mradermacher/AgentDoG-FG-Qwen2.5-7B-i1-GGUF
mradermacher
AI model: mradermacher/AgentDoG-FG-Qwen3-4B-i1-GGUF
keygent
Client SDK for Agentic JWT — Zero-Trust Identity, Intent & Delegation for AI Agents
A police department for your Claude Code agents — a logging hook + CLI that audits what the main agent and its subagents actually did.
...morenatifridman
Linter, scorer, and evaluator for AI agent skill files (Agent Skills spec)
Production-hardened Python redaction for structured logs, LLM agent payloads, and AWS-signed URLs.
airano
CLI tool for managing AI Agent skills - search, install, and update skills for Claude, Codex, Copilot, and more
fboiero
TypeScript SDK client for the Argentor AI agent framework REST API
Local secret vault for LLM-safe environments — encrypted secrets that agents can't bulk-discover