#ai-safety

C

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.…

P

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

C

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

M

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time…

R

Stop AI agents from doing things you didn't ask for.

R

Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

G

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

N

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on…

W

OWASP Foundation web repository

G

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

A

Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the…

A

Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

R

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

C

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

L

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach…

T

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

D

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any…

M

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, applies it all or nothing, reads back…

I

Benchmarking Open-Ended Inference Optimization by AI Agents

S

Open-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add

V

Rust CLI with scoped review rules, native Bash and Git hooks, and installation diagnostics for Claude Code and Codex.

L

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the…

H

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches…

S

Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent review and regression checks.

S

Action guardrails for AI coding agents — native Claude Code enforcement, MCP integrations, and Git/CI checks.

I

A fast tool with no extra packages that creates realistic mock Indian profile data based on Census 2011 statistics. Research Purpose Only!

C

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

H

.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.