Alternatives to Evmbench

AI-native container security and runtime threat detection for Kubernetes workloads

Open-source MCP server that exposes your IDA Pro database to Claude Code, Cursor and other LLM clients for AI-assisted reverse engineering

Open-source library of 817 structured cybersecurity skill files your AI coding agent loads on demand, mapped to MITRE ATT&CK and licensed Apache 2.0.

Open-source, self-hosted AI assistant that turns user stories into BRDs, PRDs, NFRs, UIRs, and traceable test cases.

winfunc runs autonomous AI security agents that audit a codebase, prove exploits with PoCs, and open fix pull requests.

SILENTCHAIN is a local-first AI pentesting extension for Burp Suite Professional that verifies OWASP Top 10 findings with real payloads.

Apex by Pensar runs continuous adversarial testing agents that exploit your apps, APIs, and AI agents, then ship the patch as a PR.

DeepZero orchestrates parallel Ghidra, Semgrep, and LLM pipelines to hunt zero-days across massive Windows kernel driver corpora.

Antigen is an AI adversary — its tCell agent pentests your live infrastructure continuously, then opens the patch for your engineers to review.

Agentic application security that governs AI coding agents and verifies reachable vulnerabilities before code ships

Open-source MCP server that gives coding agents live Chrome DevTools for debugging, traces, and browser automation.

Snyk scans AI-generated code, governs coding agents, and pentests the AI apps you ship — AppSec for the agent era.

QA Wolf is an AI test factory: agents map your app, write Playwright tests from a prompt, and run them in parallel.

Autonomous AI pentesting that finds vulnerabilities, validates them with proof-of-exploit, and ships the fix as a merge-ready pull request.

Agentic QE is an open-source MCP server that adds 60 QE agents and 76 skills to Claude Code, Cursor, Copilot and eight other coding agents.

Veria AI is an autonomous AI pentester that maps your attack surface, proves exploits against staging, and opens fix PRs.

Open-source AI agent red-teaming toolkit for prompt injection, jailbreaking, and goal hijacking tests

Million builds React Bench evals for frontier coding agents, plus open-source React Doctor and React Scan for React performance debugging.

OpenHack is an AI security engineer that finds, verifies, and fixes vulnerabilities in your code and live web apps.

A free VS Code extension that drafts Gatling load-test simulations from plain-English prompts using your own OpenAI, Anthropic, or Azure OpenAI key.

QualGent is closed-loop QA for AI-built mobile software — capture real bugs, turn them into regression tests, and let coding agents verify

Ring is a process enforcement layer and plugin bundle for Claude Code — a 10-gate cycle with 89 skills and 38 agents that make skipping tests and reviews

Snyk DeepCode AI finds, autofixes and prioritizes vulnerabilities in human-written and AI-generated code.

Mindgard automates AI red teaming — agent-native reconnaissance, exploit validation, and continuous AI security testing for production AI

Semgrep combines SAST, SCA, and secrets detection into one PR-based AppSec platform for engineering teams.

Apidog is an all-in-one API development platform that binds design, debugging, mocking, testing, and docs to one OpenAPI definition, now

Kiro turns prompts into specs, validates them, then ships with parallel AI coding agents

Run Claude Code and Codex coding agents in managed cloud sandboxes defined by YAML in your repo.

Pixee is agentic vulnerability remediation that proves which scanner findings are exploitable, then ships convention-aware fixes as pull

Agentic development security platform that puts guardrails around AI-written code and remediates findings with agents