#ai-safety

Agentlens

Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

Sanna

Trust infrastructure for AI agents — constitution enforcement and cryptographic receipts. Python SDK.

Apoa

Agentic Power of Attorney (APOA) | Authorization infrastructure for AI agents

Pinnedai

Permanent guardrails for AI-coded apps

Model Ledger

Open-source model inventory & governance. Discovers every model, rule, and pipeline across all your platforms as one immutable, agent-querya...

Aegis

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes....

PromptKit

Test, red-team, and deploy LLM applications with confidence. Multi-provider support (OpenAI, Anthropic, Gemini), MCP integration, self-play...

Reins

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

Ordo

Deterministic guardrails for AI agents — the LLM proposes, your rules dispose. A sub-microsecond, JIT-compiled rule engine in Rust, with a v...

Shellward

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代...

Agentgate

Approval workflows for AI agents

MCTS

MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers,...