Drive a self-hosted Guaardvark from your coding agent: local image, video, music-video and Film Crew generation, voice and music, upscaling, LoRA training, Hugging Face model onboarding, agent swarms, local knowledge, code intelligence and supervised outreach, on your own GPU.
Connect your project to Microsoft Build and Ignite sessions — discover relevant talks, explore what's new for your stack, and plan next steps from your development environment.
Open-source cybersecurity analysis agent. Scans any local project for vulnerabilities: code security (SAST), dependency CVEs (SCA), secret leaks, authentication/authorization flaws, cryptographic weaknesses, misconfigurations, supply chain risks, and CI/CD security. Covers all OWASP 2025 Top 10 and CWE Top 25…
★not rated 294▲
+1 13d agoA
tokens not measured
originalMIT
A plugin that guides coding agents toward smaller, more focused solutions and away from unnecessary over-engineering. It is aimed at scope control, minimalism, and code quality.
★not rated 294▲
+11 3mo agoA
tokens not measured
originalMIT
AI on-brand document generator for Claude Code & Codex: turn a company's Word, PowerPoint or Excel template into unlimited on-brand .docx/.pptx/.xlsx. Extracts a reusable Brand Profile once - off-brand output impossible by construction. Skills: brand-docx, brand-pptx, brand-xlsx.
★not rated 291▲
+1 3mo agoA
tokens not measured
originalMIT
Idea coaching toolkit: an opinionated end-to-end product coach (idea -> PRD -> clickable HTML prototype) plus a multi-role idea group chat for blind-spot discovery.
★not rated 290▲
+2 2d agoA
tokens not measured
originalMIT
Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.
A local plugin for the Sibyl Research System, an automated research setup built for Claude Code. It is described as a multi-agent system, meaning several agents work together on research.