HisnLabs/Makhalib
Natural-language-driven LLM red-teaming framework in Rust — describe the attack, don't code it. Augustus-style scanner engine + PyRIT-style adaptive multi-turn, LLM brain, semantic memory. Authorized security testing only.
GitHub Topics
使用言語(バイト数比)
AI関連と判定した根拠
AI関連スコアは4つの箇所それぞれにAI関連キーワードが現れるかを判定し、該当した配点を合計したものです。 算出方法の詳細
合計 AI関連スコア: 70 / 100
同じ言語のAI関連Repoの中での位置
当サイトが追跡している Rust 製Repoは 905件 (うちAI関連スコア40以上は 746件)。 このRepoより スター数が多いのは 205件 (上位 22.8%)、 AI関連スコアが高いのは 133件 (上位 14.8%) です。
オーナー情報
HisnLabs, makers of Guardrino: the AI guardrail for Arabic, its dialects, Arabizi and English. Built in Dubai.
日付
| GitHub作成日 | 2026-10-24 |
| 最終Push | 2026-10-24 |
| 当サイト初検出 | 2026-10-24 |
| 最終取得 | 2026-10-24 16:11 |
類似Repo (同じ言語のAI関連Repo)
Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust
LiteLLM-Labs/litellm-agent-control-plane1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
akitaonrails/ai-usagebarRust-based waybar widget to monitor status of Claude, GPT, GLM, OpenRouter plans/credits - inspired by claudebar/codexbar
modiqo/waggleAttributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.
IvanWng97/pixtuoidTerminal pixel-art office for AI coding agents
Cmochance/codex-app-transferLocal desktop gateway that translates OpenAI Codex CLI's Responses API into Chat Completions for Kimi / DeepSeek / Zhipu GLM / Bailian and other OpenAI-compatible providers.
ghuntley/underclassunderclass: an OpenAI-compatible pooling proxy that pins sessions to one account (prompt cache stays warm), cools quota-exhausted subscriptions until their window resets, and fails fast with the earliest Retry-After when the whole pool is dry.
GetBusbar/busbarThe execution control plane for AI agents. Govern every model request, MCP tool call, A2A delegation, and downstream action—while keeping your native protocols intact: six native LLM protocols in, six native LLM protocols out.