SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go, Claude API, and 7+ native security tools.

A CLI code-typing game that turns your source code into typing challenges

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

A penetration testing skill for AI agents featuring staged workflows, case memory, and activation phrase for local sandbox and CTF environments.

From Linux to Kubernetes: a curated, community-driven collection of free DevOps labs, challenges, and end-to-end projects—learn by doing and build real-world skills, not just read theory.

A summary and solutions for 200+ CTF blockchain challenges

A deliberately vulnerable CI/CD environment. Learn CI/CD security through multiple challenges.

A simple program for scraping Cloudflare clearance (cf_clearance) cookies from websites issuing Cloudflare challenges to visitors

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.