Havuz

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

⚡ Fastest and lightweight harness for AI agents

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

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

Tactical Identity Operator for Linux & Hybrid Active Directory

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

An open database of real-world AI agent incidents.

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, ca

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

State-Aware Collaboration Protocol: auditable work receipts for AI agents.

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建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance met

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and gov

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

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

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

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effecti

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

The execution safety layer for AI agents.

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

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nod

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loa

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions

A Socratic supervision layer for AI coding agents.

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

THE HUMAN LAYER FOR AI

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

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

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

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

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

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

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

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

Recovering verbatim private reasoning from Claude extended-thinking signatures, with a local byte-exact verifier.

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates pr

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

🤖 LLM Engineering Roadmap — Complete Developer Guide

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a fo