Search Results for "agent"
Sort By:
Showing 68 open source projects for "agent"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
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. -
2
PentestGPT
Automated Penetration Testing Agentic Framework Powered by LLMs
PentestGPT is an AI-powered autonomous penetration testing agent designed to perform intelligent, end-to-end security assessments using large language models. Published at USENIX Security 2024, it combines advanced reasoning with an agentic workflow to automate tasks traditionally handled by human pentesters. The platform supports multiple penetration testing categories, including web security, cryptography, reversing, forensics, privilege escalation, and binary exploitation. -
3
Fingerprint Pro Azure Integration
Proxying identification and JavaScript agent download requests
Fingerprint Pro Azure Integration is responsible for proxying download requests of the latest Fingerprint Pro JS Agent between your site and Fingerprint CDN. Proxying identification requests and responses between your site and Fingerprint Pro API. This improves both accurancy and reliability of visitor identification and bot detection on your site. -
4
T3MP3ST
Autonomous red teaming platform
T3MP3ST is a multi-agent offensive security framework for authorized red-team research, CTFs, and security education. It wraps an existing AI coding agent with orchestration for reconnaissance, exploit exploration, validation, and reporting. The project can work through a browser War Room or CLI while relying on agents such as Claude Code, Codex, Hermes, or locally hosted models. -
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
Claw Hunter
MDM-ready scripts for detecting and monitoring OpenClaw
...It focuses on uncovering “shadow AI,” which refers to unauthorized or unmanaged AI agents that operate outside traditional security controls. The tool performs risk assessment by auditing agent permissions, capabilities, and access levels, allowing security teams to evaluate potential attack surfaces. It also helps ensure that these agents do not unintentionally expose sensitive data or create unauthorized access paths across systems. -
6
SkillSpector
Security scanner for AI agent skills
SkillSpector is a security scanner built to evaluate AI agent skills before they are installed or trusted. It helps teams inspect skills used by tools such as Claude Code, Codex CLI, and Gemini CLI. The project focuses on detecting vulnerabilities, malicious behavior, and risky patterns that may be hidden inside skill files. It combines fast static checks with optional LLM-based semantic review for issues that require deeper intent analysis. -
7
Ligolo-ng
An advanced, yet simple, tunneling/pivoting tool
...When running the relay/proxy server, a tun interface is used, packets sent to this interface are translated and then transmitted to the agent's remote network. You need to download the Wintun driver (used by WireGuard) and place the wintun.dll in the same folder as Ligolo. You can listen to ports on the agent and redirect connections to your control/proxy server. You can easily hit more than 100 Mbits/sec. Here is a test using iperf from a 200Mbits/s server to a 200Mbits/s connection. -
8
Merlin HTTP/2
Merlin is a cross-platform post-exploitation HTTP/2 Command
Merlin is a cross-platform post-exploitation Command & Control server and agent written in Go. The Merlin server is a self-contained command line program that requires no installation. You just simply download it and run it. The command-line interface only works great if it will be used by a single operator at a time. The Merlin agent can be controlled through Mythic, which features a web-based user interface that enables multiplayer support, and a slew of other features inherent to the project. -
9
V3SP3R
AI Flipper control
...The project explores the concept of AI-assisted device control, where an intelligent system can interpret commands, automate workflows, and potentially orchestrate complex sequences of actions across Flipper functionalities. It is part of a broader ecosystem of projects by the same author that investigate prompt engineering, agent-based systems, and unconventional AI interaction paradigms. V3SP3R appears to emphasize automation and abstraction, reducing the need for manual device interaction by allowing higher-level instructions to drive hardware behavior. The project aligns with emerging trends in combining AI agents with physical tools, effectively bridging software intelligence and hardware execution. -
Earn up to 16% annual interest with Nexo.Generate interest, access liquidity without selling, and execute trades seamlessly. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
deepsec
Deepsec is a security harness for finding vulnerabilities
deepsec is an agent-powered security harness for finding vulnerabilities in large codebases. It is designed to run on the user’s own infrastructure, using coding agents to perform deep, project-aware security review rather than only basic pattern matching. The tool initializes a project-specific security context, scans code in batches, processes findings, and can optionally revalidate results to reduce false positives. -
11
ezXSS
ezXSS is an easy way for penetration testers and bug bounty hunters
ezXSS is an open-source XSS (Cross-Site Scripting) testing platform designed to help security researchers identify and collect XSS vulnerabilities. It acts as a payload receiver and logger, storing details about triggered XSS attacks such as the user agent, cookies, DOM, and referrer. This tool is highly useful in bug bounty hunting and penetration testing for monitoring and documenting XSS vectors in real-time. -
12
SSH-MITM
Server for security audits supporting public key authentication
...This allows SSH-MITM to accept the same key as the destination server. If publickey authentication is not possible, the authentication will fall back to password-authentication. When publickey authentication is possible, a forwarded agent is needed to login to the remote server. In cases, when no agent was forwarded, SSH-MITM can rediredt the session to a honeypot. -
13
ThreatMapper
Open source cloud native security observability platform
...Deepfence ThreatMapper hunts for threats in your production platforms, and ranks these threats based on their risk of exploit. It uncovers vulnerable software components, exposed secrets, and deviations from good security practices. ThreatMapper uses a combination of agent-based inspection and agent-less monitoring to provide the widest possible coverage to detect threats. ThreatMapper carries on the good 'shift left' security practices that you already employ in your development pipelines. It continues to monitor running applications against emerging software vulnerabilities and monitors the host and cloud configuration against industry-expert benchmarks. -
14
emp3r0r
Linux/Windows post-exploitation framework made by linux user
A post-exploitation framework for Linux/Windows. Initially, emp3r0r was developed as one of my weaponizing experiments. It was a learning process for me trying to implement common Linux adversary techniques and some of my original ideas. So, what makes emp3r0r different? First of all, it is the first C2 framework that targets Linux platform including the capability of using any other tools through it. Take a look at the features for more valid reasons to use it. -
15
RedAmon
AI-powered framework for automated penetration testing and red teaming
...It begins with a multi-phase reconnaissance engine that maps the entire attack surface of a target, collecting information such as subdomains, open ports, services, and potential vulnerabilities. RedAmon then uses an AI agent orchestrator to analyze this data, select appropriate tools, and perform exploitation steps such as credential brute forcing or CVE-based attacks. All discovered assets, relationships, and vulnerabilities are stored in a Neo4j knowledge graph, allowing the system to reason about the environment and make informed decisions during the attack process. -
16
YubiKey Guide
Community guide to using YubiKey for GnuPG and SSH
The YubiKey-Guide by drduh is a community-maintained, in-depth tutorial and reference on how to use a YubiKey (hardware authentication token) with GPG, SSH, and related cryptographic setups. It explains how to generate, manage, and use keys, configure pin / touch policies, and integrate the YubiKey into secure workflows. Configuration instructions for requiring touch for operations. Step-by-step instructions for generating GPG keys and migrating them to a YubiKey. Troubleshooting and advice... -
17
reverse-skill
Reverse Engineering and Authorized Penetration Testing
reverse-skill is a cybersecurity skill router for AI coding agents working on authorized reverse engineering, penetration testing, CTF, and security research tasks. It analyzes the target type and directs the agent to an appropriate methodology instead of relying on improvised commands. Its playbooks cover Android and iOS applications, native binaries, .NET, JavaScript, firmware, malware, APIs, supply chains, and other specialized scenarios. The package checks locally available tools and can bootstrap supporting scripts, MCP servers, and utilities when needed. ... -
18
Terrascan
Detect compliance and security violations across Infrastructure
...As you embrace Infrastructure as Code (IaC) such as Terraform, Kubernetes, Argo CD, Atlantis and AWS CloudFormation, it is important to ensure that security best practices and compliance requirements are observed. Terracan provides 500+ out-of-the-box policies so that you can scan IaC against common policy standards such as the CIS Benchmark. It leverages the Open Policy Agent (OPA) engine so that you can easily create custom policies using the Rego query language. Monitor provisioned cloud infrastructure for configuration changes that introduce posture drift, and enables reverting to a secure posture. Detect security vulnerabilities and compliance violations. -
19
Arcjet
Arcjet JS SDKs. Rate limiting, bot protection, email verification
...Native security for Bun, Next.js, Node.js, SvelteKit, Vercel, Netlify, Fly.io, and other modern platforms. Customizable protection for signup forms, login pages, API routes, and your whole app. Test security rules locally. Protection that works in every environment. No agent is required. -
20
Maltrail
Malicious traffic detection system
Maltrail is a malicious traffic detection system, utilizing publicly available (black)lists containing malicious and/or generally suspicious trails, along with static trails compiled from various AV reports and custom user-defined lists, where trail can be anything from domain name, URL, IP address (e.g. 185.130.5.231 for the known attacker) or HTTP User-Agent header value (e.g. sqlmap for automatic SQL injection and database takeover tool). Also, it uses (optional) advanced heuristic mechanisms that can help in the discovery of unknown threats (e.g. new malware). Sensor(s) is a standalone component running on the monitoring node (e.g. Linux platform connected passively to the SPAN/mirroring port or transparently inline on a Linux bridge) or at the standalone machine (e.g. ... -
21
WAF package for Laravel
Web Application Firewall (WAF) package for Laravel
This package intends to protect your Laravel app from different type of attacks such as XSS, SQLi, RFI, LFI, User Agent, and a lot more. It will also block repeated attacks and send notifications via email and/or slack when an attack is detected. Furthermore, it will log failed logins and block the IP after a number of attempts. Some middleware classes (i.e. Xss) are empty as the Middleware abstract class that they extend does all of the job, dynamically. -
22
Defending Code Reference Harness
Skills for threat modeling, scanning, triage, patching, etc.
Defending Code Reference Harness is a reference implementation for autonomous vulnerability discovery and remediation with Claude. It is designed for security teams that want a structured way to test, triage, and patch software issues with agent support. The project includes skills for threat modeling, scanning, triage, patching, and customizable autonomous analysis workflows. Its default pipeline focuses on finding memory bugs in C and C++ code using ASAN as the crash detector. The overall architecture is meant to be adaptable, so teams can modify it for other languages, bug classes, and detection systems. ... -
23
Santa
A binary authorization system for macOS
...Santa is made up of a kernel extension (or a system extension on macOS 10.15+) that monitors and participates in execve() decisions, a userland daemon that makes the execution decisions, a GUI agent that shows notifications when an execve() is blocked, and a command-line utility that oversees system management and the synchronization of database and server. Santa is built to help protect users by stopping the spread of malware and analyzing what's running on a computer, but is by no means a total security system. Ideally Santa works as a part of a defense-in-depth strategy, and other measures should be in place to protect hosts. -
24
Vuls
Agentless vulnerability scanner for Linux/FreeBSD
Vuls is open-source, agent-less vulnerability scanner based on information from NVD, OVAL, etc. Vuls uses multiple vulnerability databases NVD, JVN, OVAL, RHSA/ALAS/ELSA/FreeBSD-SA and Changelog. Vuls v0.5.0 now possible to detect vulnerabilities that patches have not been published from distributors. Remote scan mode is required to only setup one machine that is connected to other scan target servers via SSH. -
25
GRR
GRR Rapid Response, remote live forensics for incident response
GRR Rapid Response is an incident response framework focused on remote live forensics. It consists of a python client (agent) that is installed on target systems, and python server infrastructure that can manage and talk to clients. The goal of GRR is to support forensics and investigations in a fast, scalable manner to allow analysts to quickly triage attacks and perform analysis remotely. GRR client is deployed on systems that one might want to investigate.