Havuz

One control plane for every AI asset — MCP servers, skills, agents, AI apps. Self-hosted ledger with lifecycle state machine, 85 permission

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency S

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

AutoHarness: Automated Harness Engineering for AI Agents

CyberGuard, AI agent’larla güvenlik soruşturmalarını yürütmek ve müdahale kararlarını onay, denetim izi ve sonuç kontrolleriyle yönetmek için bir SOC uygulaması sunuyor.

Neden yükseliyor · 10 günlük bir repoda 54 yıldız ve son 28 günde 58 commit bulunması erken ilgi ve yoğun geliştirme sinyali veriyor. Ancak farklı yazar sayısının 1 olması, bu hareketliliğin topluluk katkısı veya bağımsız benimsemeyle desteklendiğini göstermiyor.

ToolReplay, AI agent’ların tool-call transcript’lerini determinism, yinelenen çağrılar ve izin kapsamı açısından denetleyen bir Python CLI’dir.

Neden yükseliyor · AI agent’ların davranışını denetlenebilir ve tekrarlanabilir kılma ihtiyacına doğrudan hitap ediyor; README’de örnek girdi ve çıktıyla çalışan bir kullanım gösteriliyor. 13 günde 184 yıldız dikkat çekiyor, ancak son 28 günde 2 commit ve 1 farklı yazar bakım ve benimsenmenin sürdürülebilirliği için henüz zayıf kanıt.

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus vers

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit

EU AI Act compliance proxy for AI systems. Drop-in HTTP proxy that monitors every AI interaction for regulatory risks, logs to a tamper-proo

22 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and

A framework for building intelligent agents

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

Audit and fix your Mac's security in one command. No agent, no signup, open source.

Audit npm, Yarn, and pnpm lockFiles as both an MCP server and a CLI tool.

Open-source AI-powered website audit CLI using the OpenAI API for SEO, UX, accessibility, performance, trust, and content analysis.

Evidence-based audit methodology and read-only Laravel context tools for existing AI coding agents.

AI 执行与监察体系（Agent Oversight Framework）：分层治理规范 + L2 运行时监察参照实现——证据分级、自校正、边界诚实。A layered governance spec for AI agents, plus a runnable referenc

Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

AI-powered skills for financial professionals. Comprehensive collection of finance, accounting, audit, and compliance skills for AI agents.

Keep growing TypeScript codebases maintainable. Trellis measures complexity, duplication, and import cycles, pinpoints structural debt, and

Claude Code skill that audits any Shopify theme for performance, SEO, AEO, and GEO in 90 seconds. 80+ checks, scored report, paste-in Liquid

Solana's SOL-0XX security standard — bug-class rules distilled from $514M of real exploits, firing as you code in every AI tool, editor & CI

Hermes Agent-focused architecture and runtime health checks

AuditSentry — AI-powered smart contract security auditor for Claude Code. Automated vulnerability detection, exploit PoCs, mainnet-fork simu

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

Universal, evidence-native double-entry accounting system of record in Rust on FrankenGraphDB: bitemporal, append-only with first-class rest

Zero-dependency CLI to scan, recommend, deduplicate, audit, and visualize Claude Code / Codex skills and MCP servers.

The identity provider for AI agents — registry, scoped delegation, in-path MCP enforcement, instant revocation, tamper-evident audit.

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tampe

DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidenc

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proof

Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

Finish coding-agent tasks with reviewed specs, frozen plans, bounded execution, adapter checks, and final proof. Provider-neutral lifecycle

Provena : Context governance for agentic AI — tamper-evident audit trails, provenance validation, EU AI Act compliance. 6 framework adapters

Self-hosted LLM gateway audit station: model fingerprint attribution, cache/tool/web/thinking evidence, IQ and integrity scores.

The 4R audit for ICM folder systems: Read, Run, Reality, Report. A Claude Code skill that proves your AI workspace works, not just that it l

An agents skill for auditing Ruby on Rails applications, identifying security issues, code quality problems, and common misconfigurations.

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve

Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI wo

eBPF Prometheus exporter for AI-agent activity — per-agent tools, domains, ports, files, CPU & network — with a Grafana dashboard. A yeet se

Live audit log of every command, file, and network connection a Claude Code (or any matched) session makes, from the kernel.

Paste the text you would put in an AI bot's profile. Get back what is already there and the lines that are missing.

CLI, MCP server, and Skill for safe local Codex session audit, cleanup, restore, and verification.