“Testing”

Open-source tool that runs dynamic attacks against a GenAI app's system prompt to help harden it.

Browser automation CLI for AI agents, built as a native Rust binary.

Autonomous penetration testing agent with a Kali Docker sandbox, a Textual TUI and any OpenAI-compatible model gateway

Unified gateway for deploying and managing multiple LLM providers behind one secure endpoint.

Open-source Python framework from Microsoft for finding risks in generative AI systems through red teaming.

Self-hosted autonomous pentesting agent that finds and exploits vulnerabilities and logs the command and output for each one

Open-source durable execution platform for orchestrating async code, background jobs and agents.

Autonomous security-testing agent on the Pi SDK that plans tasks in a graph and keeps evidence for each conclusion.

Open-source Python library for evals, red teaming and test generation for agentic systems

Open-source LLM red teaming framework that simulates attacks to find vulnerabilities in AI apps and agents.

Python tool that scans MCP servers and their tools for security findings using YARA, LLM and AI Defense analysis.

Local-first MIT coding agent with DeepSeek defaults, provider switching, OS sandboxing and a checkpoint for every patch.

Open-source authorization decision point and management platform for apps, APIs and AI agents

Open-source LLM vulnerability scanner that probes models and apps for prompt injection, data leakage and jailbreaks.

Open-source AI pentester that reads web app source code and proves vulnerabilities with working exploits

Open-source platform where you configure multi-agent systems and workflows without writing code

Terminal pentesting agent that runs specialist subagents over a shared engagement state and supports 20+ LLM providers

Automated LLM fuzzer that tries jailbreak attacks against models and LLM APIs, including your own REST API.

Terminal-based AI pair programmer that edits code in your local git repo and works with most cloud and local LLMs

Self-hostable autonomous pentesting agent that re-exploits each finding with an independent verifier before reporting it.

Open-source reverse-engineering agent that uses Ghidra and LLMs to rebuild and validate C/C++ functions from binaries.

Open-source agentic language model (30.5B parameters, 3.3B active per token) trained for long, multi-step web information seeking.

Runs a Claude Code dev team on your server and drives it from Telegram, VK or LO chats, opening a PR per request.

Autonomous research agent that forms hypotheses, edits code and runs experiments, keeping only gains that hold on held-out data