Alternatives to T3MP3ST

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.

ECC is an open-source agent harness operating layer that gives Claude Code, Codex, Cursor, OpenCode and Kimi shared skills, memory,

Darkmoon runs self-hosted autonomous penetration testing with 50 specialist AI agents and 142 allow-listed security tools

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

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

Imbue builds inspectable coding-agent tools, from mngr's parallel agent runner to Latchkey's HTTP permissions

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

UmaDev is an open-source Rust CLI that turns your logged-in local coding agents into an eight-role AI dev team with governance gates and

Open-source meta-harness for running Claude Code, Codex, Pi and custom AI coding agents under one policy and sandbox

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

MCP gateway and agent security for enterprises, from AI-BOM inventory to inline runtime enforcement.

Open benchmark from OpenAI and Paradigm that tests whether AI agents can detect, patch, and exploit high-severity smart contract vulnerabilities

Open-source MCP server that lets AI assistants like Claude Code query Shodan for device, DNS, and CVE data from your terminal.

Fiddler AI is an enterprise AI control plane for agent observability, inline guardrails, and auditable AI governance.

HackerOne's H1 Platform pairs agentic AI with 600,000+ researchers for continuous threat exposure management.

Agentic law platform that encodes legal rules into verifiable AI agents for banks, asset managers, and insurers.

Patronus AI builds simulated environments and training data for reinforcement learning on frontier agent models.

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

Iris.ai builds an auditable AI knowledge layer so regulated teams can defend every answer in an audit.

Floutwork unifies GPT, Claude, Gemini and Grok into one governed AI workspace with shared memory for teams of 10–1,000.

Andon Labs runs real cafés, stores, and radio stations under AI operators, then publishes the real-world evals of what breaks.

A free, citable AI incident database indexing real-world AI harms, near-harms and failures you can search, export and quote.

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

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