Havuz

Runtime security platform for LLM agent tool calls on Kubernetes

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in saf

Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent revie

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

⚡ Fastest and lightweight harness for AI agents

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

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

Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule o

Privacy-first PII tokenization middleware for LLM pipelines — local detection, encrypted vault, zero cloud dependency.

Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable

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

Real-time guardrail runtime for AI agents.

Tactical Identity Operator for Linux & Hybrid Active Directory

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

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

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success,

Decomposing and measuring evaluation awareness in existing benchmarks and our proposed EvalAwareBench.

Diagnosing policy grounding in LLM judges via causal erasure. Companion code to the AIES 2026 submission READ.

Security scanner for AI agent skills. Flags known prompt-injection, data-exfiltration and malicious-payload patterns before you install

Make AI browser agents read-only: a Chrome extension that refuses writes (send, post, edit, delete) before they leave the browser.

Guardian Runtime sits securely on your machine, acting as a bodyguard for your code. Whenever you use AI tools like Cursor or Claude Code, i

📜🦀🌐 Intelligent, Secure and Effortless Super Full-Stack Framework 🌐🦀📜"Rust for those who want to build securely and easily, but not suffer"

Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors,

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

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

SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy con

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes

最系统的AI全栈学习实战手册

Code-First AI Compliance. The open-source regulatory engine for the EU AI Act. Automate your risk assessments directly within your CI/CD pip

Real-time web dashboard for AI-agent behavior monitoring, built on Perplexity's Numbat. Zero-dependency Python.

🔐 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

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

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

Liminate is a prose-as-syntax language designed from the human end.

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

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

THE HUMAN LAYER FOR AI

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-bound

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.

Score any AI for trust — Eval, Monitor, Govern. 10 trust dimensions, one free API key (5 credits / $500).

Vault, don't delete — hallucination governance for long-memory AI companions. 梦,归本人。

Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.

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

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

Zero-trust L0-L5 verification gateway in Zig 0.17: native Z3 proof-DAG checker, Belnap B4 logic, 42 Lean 4 theorems (0 sorry), 8-lane SIMD B

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

Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖