ai-safety

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

A curated list of awesome responsible machine learning resources.

Safety-first guardrails for AI-driven cloud and Kubernetes operations

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

Secrets of RLHF in Large Language Models Part I: PPO

[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"

Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets your needs, and you can also publish your own Agent to turn it into your digital asset. We encourage everyone to transform their areas of expertise into Agents and turn them into digital assets, allowing others to see your unique strengths.

This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.

An agent-native web security workspace. Find vulnerabilities through red-teaming. Formally verify properties of Rust codes in Lean 4.

A resource repository for machine unlearning in large language models

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

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

Deliver safe & effective language models

FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.