<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Heretek-AI: new Proxmox VE scripts</title>
    <link>https://heretek-ai.github.io/ProxmoxVE</link>
    <description>New scripts added to the Heretek-AI Proxmox VE catalogue.</description>
    <language>en</language>
    <item>
      <title>Hermes Agent</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/hermes</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/hermes</guid>
      <pubDate>Wed, 28 Oct 2026 00:00:00 GMT</pubDate>
      <description>Hermes Agent is a self-improving AI agent built by Nous Research with persistent memory, autonomous skill creation, computer-use (CUA) support, and multi-platform gateway integration. This enhanced Heretek build includes pre-configured passwordless sudo for the hermes user, native X11/input shared libraries for cua-driver, and Docker Engine with Buildx and Compose v2.</description>
    </item>
    <item>
      <title>Kyojin</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/kyojin</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/kyojin</guid>
      <pubDate>Tue, 27 Oct 2026 00:00:00 GMT</pubDate>
      <description>Kyojin is Yamz Labs' open source inference engine for AMD Strix Halo (gfx1151), built on ExLlamaV3 with speculative decoding, serving their own EXL3 quantised builds of Qwen3.8-Flash-Next, GLM-5.3-Flash and MiMo-V2.6-Flash (95 to 106 GB) on one 128 GB machine through an OpenAI-compatible API. The script builds the latest tagged release with AMD's gfx1151 ROCm wheels, following Kyojin's own container recipe.</description>
    </item>
    <item>
      <title>GSQHalo.cpp</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/gsqhalo</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/gsqhalo</guid>
      <pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate>
      <description>GSQHalo.cpp is a llama.cpp fork tuned for ISTA-DASLab's GSQ-RCO quantizations of Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151), with faster prefill kernels, MTP that fits in memory and a KV cache on SSD. The script installs AMD's ROCm 7.14.1 for gfx1151 in its own prefix, builds the fork from source and serves llama-server's OpenAI-compatible API.</description>
    </item>
    <item>
      <title>Gufo</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/gufo</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/gufo</guid>
      <pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate>
      <description>Gufo is an open source local inference engine built and tuned for AMD Strix Halo (Ryzen AI MAX+ 395, Radeon 8060S gfx1151). It serves Qwen3.8, DeepSeek V4 Flash, speech, embedding, image and video models through an OpenAI-compatible API, with speculative decoding, concurrent requests and prompt caching. The script installs the official release build through Nix, using prebuilt ROCm from the Gufo binary cache.</description>
    </item>
    <item>
      <title>Strata</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/strata</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/strata</guid>
      <pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate>
      <description>Strata is an open source inference engine for Qwen3.8-Flash-Next and other large MoE models, with a Strix Halo (gfx1151) HIP engine, MTP drafting and an OpenAI-compatible API. The script installs the Strata Terminal, which downloads the signed engine for the GPU with its own HIP runtime, and serves ISTA-DASLab's Qwen3.8-Flash-Next Coder by default.</description>
    </item>
    <item>
      <title>RE-Agent</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/re-agent</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/re-agent</guid>
      <pubDate>Sat, 24 Oct 2026 00:00:00 GMT</pubDate>
      <description>RE-Agent (LXC) is the static-analysis variant of the RE-Agent appliance. Agentic reverse-engineering and malware-analysis workstation: Hermes Agent with the REA MCP server registered, Ghidra headless, OpenBin BINNY, CAPA, FLOSS, YARA, Detect It Easy, Radare2 and UPX, Ghidra and radare2 MCP servers, oletools and PDF tools for documents, box-js for scripts, jadx and androguard for Android, Sigma tooling, and RE skills for triage, deobfuscation, IOCs, detections and reports, plus a web case console (sample intake, case pages, IOC review and report export), rea-case for evidence-backed case folders and re-ioc for CSV and STIX 2.1 IOC export, re-firewall to restrict egress to an allowlist of LLM hosts, and a local memory store (holographic) with optional embeddings.</description>
    </item>
    <item>
      <title>RE-Agent VM</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/re-agent-vm</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/re-agent-vm</guid>
      <pubDate>Sat, 24 Oct 2026 00:00:00 GMT</pubDate>
      <description>RE-Agent VM is the hardware-isolated variant of the RE-Agent appliance, built on a Debian or Ubuntu cloud image. Agentic reverse-engineering and malware-analysis workstation: Hermes Agent with the REA MCP server registered, Ghidra headless, OpenBin BINNY, CAPA, FLOSS, YARA, Detect It Easy, Radare2 and UPX, Ghidra and radare2 MCP servers, oletools and PDF tools for documents, box-js for scripts, jadx and androguard for Android, Sigma tooling, and RE skills for triage, deobfuscation, IOCs, detections and reports, plus a web case console (sample intake, case pages, IOC review and report export), rea-case for evidence-backed case folders and re-ioc for CSV and STIX 2.1 IOC export, re-firewall to restrict egress to an allowlist of LLM hosts, and a local memory store (holographic) with optional embeddings.</description>
    </item>
    <item>
      <title>Unsloth Studio</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/unsloth-studio</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/unsloth-studio</guid>
      <pubDate>Wed, 18 Mar 2026 00:00:00 GMT</pubDate>
      <description>Local, browser-based GUI for fine-tuning LLMs without writing code. Supports QLoRA, LoRA, and full fine-tuning with live training monitoring, GPU stats, and model export to GGUF/Safetensors.</description>
    </item>
    <item>
      <title>SkillServer (In Development)</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/skillserver</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/skillserver</guid>
      <pubDate>Tue, 17 Mar 2026 00:00:00 GMT</pubDate>
      <description>An MCP/REST server with WebUI serving as a centralized skills database for AI Agents. Manages 'Skills' (directory-based with SKILL.md files) stored locally, following the Agent Skills specification. Features MCP server integration, web interface for skill management, Git synchronization, and full-text search.</description>
    </item>
    <item>
      <title>LocalRecall</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/localrecall</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/localrecall</guid>
      <pubDate>Sat, 14 Mar 2026 00:00:00 GMT</pubDate>
      <description>A lightweight RESTful API for managing knowledge bases and files stored in vector databases. No GPU, internet, or cloud services required. Integrates with LocalAI for embeddings.</description>
    </item>
    <item>
      <title>Kali Linux</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/kali</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/kali</guid>
      <pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate>
      <description>Kali Linux is an open-source, Debian-based Linux distribution geared towards various information security testing tasks. Includes essential security tools like nmap, wireshark, john, hashcat, hydra, and metasploit-framework.</description>
    </item>
    <item>
      <title>OpenClaw</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/openclaw</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/openclaw</guid>
      <pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate>
      <description>OpenClaw is a personal AI assistant that runs on your own devices. It supports multiple messaging channels including WhatsApp, Telegram, Slack, Discord, Signal, iMessage, IRC, Microsoft Teams, Matrix, and more. Features voice wake mode, live canvas, browser control, skills platform, and a Gateway WebSocket control plane.</description>
    </item>
    <item>
      <title>PentAGI</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/pentagi</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/pentagi</guid>
      <pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate>
      <description>PentAGI is an AI-powered autonomous penetration testing system that leverages multiple LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Ollama, DeepSeek, GLM, Kimi, Qwen) for security testing. Features include knowledge graph integration (Graphiti/Neo4j), LLM observability (Langfuse), 20+ professional pentesting tools in sandboxed Docker containers, and comprehensive REST/GraphQL APIs. Docker is installed inside the container.</description>
    </item>
    <item>
      <title>RAGFlow</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/ragflow</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/ragflow</guid>
      <pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate>
      <description>RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine with deep document understanding. It provides a streamlined RAG workflow for businesses of any scale, combining LLM capabilities to provide truthful question-answering with well-founded citations from various complex formatted data.</description>
    </item>
    <item>
      <title>llama.cpp Server</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/llamacpp</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/llamacpp</guid>
      <pubDate>Wed, 11 Mar 2026 00:00:00 GMT</pubDate>
      <description>llama.cpp is a high-performance LLM inference server with OpenAI-compatible API. This installation uses the Vulkan backend for GPU acceleration across AMD, Intel, and NVIDIA GPUs. Features automatic model downloading from HuggingFace, built-in web UI, and supports multiple concurrent requests.</description>
    </item>
    <item>
      <title>Drop</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/drop</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/drop</guid>
      <pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate>
      <description>Drop is an open-source game distribution platform similar to Steam/GameVault. Manage your game library, track playtime, and organize your collection with a modern web interface.</description>
    </item>
    <item>
      <title>Agregarr</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/agregarr</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/agregarr</guid>
      <pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate>
      <description>Agregarr keeps your Plex Home and Recommended fresh by frequently updating it with Collections from various sources, including Trakt, IMDb, TMDB, Letterboxd, MDBList, FlixPatrol, AniList and MyAnimeList.</description>
    </item>
    <item>
      <title>SwarmUI</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/swarmui</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/swarmui</guid>
      <pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate>
      <description>SwarmUI is a powerful Stable Diffusion WebUI with built-in ComfyUI integration for AI image generation. It provides a modern web interface for generating images using various AI models.</description>
    </item>
    <item>
      <title>MCPHub</title>
      <link>https://heretek-ai.github.io/ProxmoxVE/scripts/mcphub</link>
      <guid isPermaLink="true">https://heretek-ai.github.io/ProxmoxVE/scripts/mcphub</guid>
      <pubDate>Mon, 02 Mar 2026 00:00:00 GMT</pubDate>
      <description>MCPHub is a unified hub for centrally managing and routing multiple Model Context Protocol (MCP) servers through a single dashboard and API endpoint.</description>
    </item>
  </channel>
</rss>
