Loading...
Loading...
Opentaint: The open source taint analysis engine for the AI era. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Opentaint. This is an automatic list. We have not written a researched verdict for Opentaint yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
agentsh, short for agent shell, is an execution layer security gateway for AI agents. It sits underneath an agent or harness, intercepts file, network and process activity at the system call level, and applies a deterministic policy to every operation regardless of what the prompt, tool output or user says. The premise...
Break your AI before they do.
AI Beat is an open source suite for testing AI behavior before it reaches users, published by tophant.ai. It is organized around separate products for separate system boundaries: PromptBeat red teams and evaluates models and prompts, AgentBeat evaluates black box HTTP agents, and RouterBeat publishes live security benc...
Agentic AI EDR for developer workstations and autonomous agent swarms.
Clawdstrike is an open source endpoint detection and response engine built for AI agents, published by Backbay Labs. It combines a policy engine, an EDR and a signed audit chain in one binary, so that an agent's tool call is evaluated in the same event taxonomy as kernel level file access, process execution, network fl...
Container-free, deny-by-default sandbox for AI coding agents.
Greywall is an open source command line tool that lets you watch and control what an AI coding agent does on your machine. You prefix any local agent command with greywall followed by two dashes, and it gives you a live feed of every file read, file write and network connection the agent attempts. It runs on Linux and ...
extendable code review and QA agent
Shippie is an open source, extendable AI code review agent. It runs as a GitHub Action on every pull request, or locally on staged changes, and posts focused inline review comments along with a summary, much as a human reviewer would. It is built on the flue agent framework and runs a real agent loop with developer to...
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Strix is an autonomous AI penetration testing and security platform that tests a team's own code, APIs, web apps, cloud environments and infrastructure. Its agents map the environment, chain real attack steps, reproduce each finding and confirm exploitability with proof of exploit, including payloads and reproduction s...