AI Agent2026
Provides a pytest-native framework to write safety and security tests for agentic AI applications. Defines adversarial attacks, benign-failure suites, and harm-category assertions with evaluation-driven checks and CI-friendly reporting, so red-teaming becomes testable and automatable.
AI Model2026
Multimodal image-text-to-text fork of Gemma 4 (31B) using a 'CRACK v2' abliteration — tuned for conversational vision inputs and thinking-mode support in JANG v2 safetensors format. Recommended to run in vMLX; published by dealignai.
AI Infra2026
Provides hardware-isolated, sub-60ms, ultra-low-overhead sandboxes to run untrusted LLM/agent code. Offers event-level snapshots, kernel-level egress control, credential vaulting, and drop-in E2B SDK compatibility for high-density AI agent deployment.
AI Model2026
Removes safety refusals from a Gemma 4 E4B–based model and publishes uncensored, locally runnable GGUF/safetensors variants while preserving all tensors and fixing prior corruption. Intended for red‑teaming and offline research; not recommended for production.
AI Agent2026
Runs goal-driven penetration tests by orchestration of an LLM agent and an MCP toolchain to perform reconnaissance, vulnerability discovery, exploitation, and structured PoC/report generation; supports multiple LLM providers and local MCP integrations; for authorized security testing only.
AI Agent2026
Monitors and detects risky behavior in enterprise AI agents via high-fidelity telemetry, security benchmarking, and a two-tier detector. Comprises ADR Sensor, ADR-Bench, and ADR Detector; deployed in production at Uber and validated on public benchmarks.
AI Agent2026
Performs agent-driven security scans of codebases using LLM coding agents to find and triage vulnerabilities. Combines fast regex discovery, per-file AI investigation and revalidation, with optional sandboxed parallel execution and Vercel AI Gateway integration for large monorepos.
AI Infra2026
Ingests and normalizes security telemetry, runs multi-model AI agents to produce replayable investigations and automated triage/response; key features include a step-by-step Investigation Ledger, CI-gated eval harness, and self-hostable deployments.
AI Model2026
Generates production-ready offensive-security artifacts from prompts—Nuclei templates, CVE PoCs, exploit scripts and pentest tooling—fine-tuned on bug-bounty reports and CVE writeups and quantized for consumer/server GPU deployment.
AI Agent2026
Routes code-based AI agents through repeatable reverse-engineering and pentesting workflows and orchestrates local and remote tools (jadx, Frida, IDA, BurpSuite) so agents can triage APKs, binaries, JS, firmware, and CTFs without guessing the toolchain. Includes master routing rules, tool-index detection, MCP integration, and a field-journal for reusable lessons.
AI Dataset2026
25,000 chat-formatted synthetic SFT examples distilled to emulate the reasoning style and agentic behavior of Anthropic's Claude Mythos, focused on cybersecurity, advanced coding, mathematical reasoning, and long-horizon agent tasks. Includes metadata for targeted curriculum fine-tuning and is Apache-2.0 licensed.
AI Model2026
Provides a locally runnable 26.9B Qwen3.6 checkpoint that surgically reduces refusal behavior in weight space while preserving capability; ships bfloat16 safetensors and a GGUF quant ladder for local runtimes and red-team evaluation.