Havuz

Claude Code hook that blocks unquoted rm -rf $VAR and repo-root deletes, even in bypassPermissions mode

How to design AI agents that work as one: nine parts of an agent and its team, checked against 85 sources. Free guide in Markdown and PDF, w

Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Mer

A benchmark for AI agents as teammates. Paper: https://arxiv.org/abs/2611.02633

Illustrated comic-style cheat sheets for ML, LLMs, AI safety, LeetCode and Git, plus a SwiftUI study app (Panels) to read them and quiz your

Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, ap

Panels, guardrails and quality-of-life mods for Claude Code: context, usage, live activity, notifications, safety rules, prompt coach, comma

Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau

Tactical Identity Operator for Linux & Hybrid Active Directory

⚡ Fastest and lightweight harness for AI agents

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t

A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI

RLCDAlignBench: 44 alignment-failure detection benchmarks and code for 'Just Ask Jev' (RLCD zero-shot detector of AI alignment failures)

Universal AI Charter: plain-language governance principles and a public certification registry for AI models, built on disclosure instead of

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

THE HUMAN LAYER FOR AI

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

Code for the paper "Emergent Collusion in Long-Horizon LLM Agent Interaction"

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

An open database of real-world AI agent incidents.

Evidence validation and policy engine for AI-assisted biological curation

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

A platform for running human-centered red teaming evaluations on AI models and systems.

Deterministic telemetry & control plane for multi-agent AI systems. Atomic POSIX JSONL event bus, W3C/OpenTelemetry DAG reconstruction, and

Monitoring & Safety layer for all your agents. Open Source CLI & Skills for Claude Code, Codex, Cursor, Jev and your preferred agents.

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

The execution safety layer for AI agents.

An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.

Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy)

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

AI 执行与监察体系（Agent Oversight Framework）：分层治理规范 + L2 运行时监察参照实现——证据分级、自校正、边界诚实。A layered governance spec for AI agents, plus a runnable referenc

Protecting digital communications against audio deepfakes with real-time AI. This system analyzes audio streams to detect synthesized voices

Zero-dependency guardrail framework for AI agents. Stops runaway loops, prompt injection, hallucination and unsafe tool calls before they ex

Open-source MCP control plane for AI coding agents: mechanical time-locks, evidence-gated proof receipts, red-team remediation, and persiste

Code review via the change impact measure

Paste a URL, find out something true about the site. Three URL-only readings on one page: Slopmeter scores how much of it is still the templ

Behavioral testing for AI agents.

mutual layer for multiple agents from different environment or providers to work on same interface or device, toward the same final goal

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

🔐 The local-only AI secret manager for the AI-coding era with MCP, CLI, Web UI, TUI, Chrome Extension and Mobile App. No cloud, No telemetry

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

Parent-operated starter kit for designing a private, child-facing Hermes Agent profile