Search Results for "audit"
Sort By:
Showing 40 open source projects for "audit"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
security-audit
A coding-agent skill for multi-phase security audits
security-audit is a coding-agent skill for running structured security audits on software repositories. It organizes the audit into multiple phases so the agent does not simply search randomly for vulnerabilities. The workflow begins with reconnaissance, then moves into parallel hunting across attack classes such as injection, access control, business logic, cryptography, feature abuse, and chained attacks. -
2
MCP Security Audit
Powerful MCP (Model Context Protocol) Server that audits npm packages
The MCP Security Audit Server is a powerful Model Context Protocol server that audits npm package dependencies for security vulnerabilities, integrating with remote npm registries for real-time security checks. -
3
Claude Ads
Comprehensive paid advertising audit & optimization skill
...The architecture uses parallel subagents to speed up audits and includes financial modeling and A/B testing guidance. It runs locally, ensuring privacy and control over sensitive advertising data. The project is aimed at replacing manual audit workflows with fast, automated, and repeatable analysis. -
4
Skills Janitor
Audit, track usage, and compare your Claude Code skills
The Skills Janitor project is a lightweight plugin designed to manage, audit, and optimize AI agent skill ecosystems, particularly for environments like Claude Code and OpenAI Codex. It functions as a “maintenance layer” for AI skills by automatically scanning installed skill directories, identifying duplicates, and analyzing their structure and usage. One of its core purposes is to help developers maintain a clean and efficient skill environment, especially as the number of installed skills grows over time. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
agentmemory
#1 Persistent memory for AI coding agents
...It combines keyword search, vector search, confidence scoring, lifecycle management, and knowledge graph querying to retrieve useful memories without overloading the context window. The project also includes hooks, an API, import and export support, audit trails, and team sharing workflows. Overall, agentmemory is designed to make AI coding assistants more continuous, context-aware, and useful across long-running software projects. -
6
NanoClaw
A lightweight alternative to Clawdbot / OpenClaw
Nanoclaw is a lightweight, security-focused personal agent runtime designed as a slimmer alternative to larger “personal assistant” agent stacks, with an emphasis on being easy to audit and safe by default. It runs agent execution inside Apple containers to provide strong isolation boundaries, so individual chats and actions can be sandboxed with tighter filesystem and process separation than a typical single-process bot. The project connects directly to WhatsApp, letting you deploy an assistant that can chat in a familiar interface while still supporting real agent behaviors instead of simple call-and-response prompts. ... -
7
Quint Code
Structured reasoning framework for Claude Code, Gemini, and Cursor
...Instead of accepting the first plausible answer generated by an AI assistant, Quint Code encourages generating multiple competing hypotheses, verifying them, and validating them against real evidence stored in a structured “knowledge base” within your project. It supports a cycle of abduction, deduction, and induction backed by CLI commands (like /q1-hypothesize, /q2-verify, /q3-validate, etc.) that create a persisting audit trail in a .quint/ directory. -
8
improve
Use your most capable model to audit your codebase
improve is an agent skill that audits a codebase and writes implementation plans for other agents or humans to execute. Its core idea is to use a stronger model for understanding, judgment, and planning, then hand the actual implementation to cheaper or separate execution agents. The skill does not modify code by default, because its main output is a self-contained plan. It can run full, quick, deep, security-focused, branch-scoped, and feature-suggestion audits. It maps repository... -
9
Inspect Petri
An alignment auditing agent capable of exploring alignment hypothesis
Inspect Petri is an open-source alignment auditing agent that lets researchers rapidly test concrete safety hypotheses against target models using realistic, multi-turn scenarios. Instead of building bespoke evals, Inspect Petri automatically generates audit environments from seed “special instructions,” orchestrates an auditor model to probe a target model, and simulates tool use and rollbacks to surface risky behaviors. Each interaction transcript is then scored by a judge model using a consistent rubric so results are comparable across runs and models. The system supports major model APIs and comes with starter seeds and judge dimensions, enabling minutes-to-insight workflows for questions like reward hacking, self-preservation, or eval awareness. ... -
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
10
Monkey Code
Enterprise-grade AI programming assistant designed for R&D collab
...One of its defining characteristics is its support for private deployment and fully offline operation, which makes it especially suitable for organizations with strict data privacy or security requirements. The system includes a comprehensive management panel that allows teams to audit, monitor, and control how AI participates in coding workflows, ensuring accountability and governance at scale. MonkeyCode also integrates automated code security scanning to detect vulnerabilities in both human-written and AI-generated code, reinforcing secure development practices. -
11
AutoCVE
Agent-driven automated CVE discovery platform for source code auditing
AutoCVE is an agent-driven platform for automating authorized source-code auditing and CVE discovery. It covers the workflow from project selection and repository import to vulnerability verification and submission-ready report generation. An orchestrator coordinates specialized agents for reconnaissance, scanning, triage, deep analysis, verification, and final consolidation. Users can choose enhanced scanning, intelligent auditing, or comprehensive auditing based on speed and depth... -
12
Loop Library
A library of practical AI-agent loops and an installable skill
...It is built around the idea of loops, which are bounded playbooks that tell an agent what to do, how to check progress, what to try next, and when to stop. The repository contains both a public loop library website and the Loopy skill that agents can use to discover, audit, adapt, run, and prepare loops. It helps turn open-ended prompts into measurable workflows with evidence, stopping criteria, and human approval points. The skill can work with agent environments such as Codex, Cursor, and Claude Code through the Skills CLI. Overall, it is useful for teams that want safer, reusable, and more reliable agent workflows instead of one-off prompting. -
13
native-feel.skill
An Agent Skill for designing cross-platform desktop apps
...The skill helps AI assistants reason about when to use native code, when to share web-based interface layers, and how to avoid the common failures of Electron-style or WebView-based products. It includes eight architectural tenets, a four-layer architecture model, WebKit and WebView2 guidance, and a large ship audit checklist. The project is useful when an agent is advising on desktop apps that need global shortcuts, system tray behavior, native windows, fast interaction, and polished platform conventions. Its main value is turning hard-won desktop architecture knowledge into reusable agent guidance. -
14
Hallmark
Anti-AI-slop design skill for Claude Code, Cursor, and Codex
...It gives agents a concrete design rule set for producing interfaces that look intentionally crafted rather than generic, repetitive, or template-like. The project focuses on typography, color, layout, motion, microinteractions, visual hierarchy, and structural variation. It can be used to build new UI, audit existing code, or redesign an interface while keeping the underlying content and information architecture. Hallmark includes reference material and worked examples so agents can apply the design logic more consistently. Its main value is helping AI-generated interfaces move from “technically functional” to visually deliberate and product-ready. -
15
MemClaw
Persistent memory for AI agent fleets (OSS)
...It is designed to help agents remember information across sessions, teams, tools, and models instead of keeping knowledge trapped inside isolated conversations. The project emphasizes enterprise-style governance, including permissions, tenant isolation, audit trails, visibility scopes, and agent trust tiers. It also supports agent integrations through MCP and OpenClaw-style workflows, making it useful for multi-agent systems that need persistent recall. Its architecture goes beyond a simple vector database by adding rules about who can store, retrieve, and share each memory. caura-memclaw is best suited for teams building AI agents that need long-term memory, controlled sharing, compliance awareness, and safer cross-agent coordination. -
16
Loop Engineering
Practical patterns, starters & CLI tools for loop engineering with AI
...It explains core building blocks such as scheduling, worktrees, skills, plugins, connectors, sub-agents, and persistent memory or state. The repository includes production loop patterns, quickstarts, starters, checklists, safety notes, and real-world stories. It also provides CLI tools such as loop-audit, loop-init, and loop-cost to scaffold, evaluate, and estimate agent loop workflows. -
17
Elkeid
Open source solution that can meet the requirements of workloads
...Elkeid combines kernel-level data collection, user-space agents, and runtime instrumentation (RASP) to detect malicious behavior, file anomalies, runtime exploits, and suspicious container activity. For container or cloud-native workloads, it also supports gathering audit logs from Kubernetes and correlating events across processes, network, and file activity to detect security threats. The platform packages data collection, event-streaming, and a rule/event engine (called “HUB”) — letting users define detection rules, alerts, baseline checks, and policy enforcement. -
18
Buzz
A hive mind communication platform
...It records messages, reactions, workflow steps, approvals, and Git activity as cryptographically signed Nostr events in a shared log. The platform includes channels, threads, direct messages, canvases, media sharing, full-text search, and a tamper-evident audit trail. Agents receive their own identities and memberships, allowing them to answer questions, review patches, manage workspaces, and run tools without impersonating users. YAML workflows can respond to messages, reactions, schedules, and webhooks while preserving execution traces. Buzz provides a Tauri desktop client, browser access, a JSON-oriented CLI, MCP support, and ACP integrations for popular coding agents. ... -
19
HexStrike AI MCP Agents
HexStrike AI MCP Agents is an advanced MCP server
HexStrike AI is an MCP server that lets LLM agents autonomously operate a large catalog of offensive-security tools. Its goal is to bridge “language models” and practical pentest workflows—enumeration, exploitation, vulnerability discovery, and bug bounty reconnaissance—under safe, auditable controls. The server exposes typed tools and guardrails so agent prompts translate to concrete, parameterized actions rather than brittle shell strings. It ships with curated tool adapters, task... -
20
Claude SEO
Universal SEO skill for Claude Code
...It combines 25 sub-skills and 18 specialist agents across technical SEO, content quality, Schema.org markup, GEO and AEO, local SEO, e-commerce, international SEO, backlinks, semantic clustering, and Google API workflows. The system is designed to produce prioritized action plans instead of generic audit notes. Recommendations include first-principle observations, dependency relationships, falsifiability checks, and leading indicators. It can run full site audits, single-page reviews, schema validation, AI search readiness checks, sitemap workflows, local SEO analysis, and SEO reporting. Claude SEO is useful for agencies, in-house teams, and consultants who want repeatable SEO audits inside Claude Code. -
21
NullClaw
Fastest, smallest, and fully autonomous AI assistant infrastructure
NullClaw is the smallest fully autonomous AI assistant infrastructure, built entirely in Zig as a single static binary with zero runtime dependencies. At just 678 KB with ~1 MB peak RAM usage, it boots in under 2 milliseconds and runs on virtually any hardware, including low-cost ARM boards. Despite its size, it delivers a complete AI stack with 22+ model providers, 18+ communication channels, integrated tools, hybrid memory, and sandboxed runtime support. Its architecture is fully modular,... -
22
GitHub Agentic Workflows
GitHub Agentic Workflows
GitHub Agentic Workflows is an experimental CLI extension and framework for the gh GitHub CLI that lets developers author automation driven by natural language specifications instead of hand-written code, compiling those descriptions into GitHub Actions workflows that run AI agents (like Copilot, Claude Code, or Codex) on schedule or in response to repository events. By writing intent in markdown files, a developer can quickly generate .yml Actions workflows that perform tasks such as... -
23
agents-best-practices
Provider-neutral Agent Skill for Codex, Claude Code
agents-best-practices is a provider-neutral Agent Skill for designing, auditing, refactoring, and explaining agentic harnesses. It is built around the principle that the model proposes actions, while the harness validates, authorizes, executes, records, and returns observations. The project applies to coding agents, research agents, support agents, operations agents, sales agents, finance agents, healthcare agents, education agents, and workflow automation agents. It helps users reason about... -
24
DeepAudit
AI multi-agent platform for automated code security auditing system
...DeepAudit integrates retrieval-augmented generation techniques to enhance contextual understanding and reduce false positives during analysis. Users can import projects and trigger a full audit workflow that includes risk identification, exploit generation, validation, and final report creation. -
25
mpai
Make Codex and Claude Code sessions multiplayer from the terminal
...Teammates can follow live transcripts, switch sessions, show presence, and submit prompts with their identity attached. Viewer and participant roles, revocation, shared access rules, and an append-only audit trail help preserve owner control. The public alpha currently targets macOS and existing Tailscale networks, with no public relay or arbitrary remote shell access.
