Guaardvark — AI skill for Claude Code
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent (Claude Code, Cursor, Codex.
How to install Guaardvark
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open guaardvark/guaardvark and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Guaardvark does
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent (Claude Code, Cursor, Codex, OpenClaw) through MCP and skills.
Alternatives in AI
- Post Training — ai-research-skills GRPO, RLHF, DPO, SimPO 5.4k ★
- Kibitz — Real-time decoded feed of AI agent actions — monitor multiple Claude Code & Codex sessions, see exactly what e 521 ★
- Nano Banana 2 Skill — AI image generation CLI powered by Gemini 3 Pro 228 ★
README
https://github.com/user-attachments/assets/c6d9d18b-cfff-4ae2-8220-dc7f329fee5d
Guaardvark
[](LICENSE) [](https://github.com/guaardvark/guaardvark/actions/workflows/ci.yml) [](https://pypi.org/project/guaardvark/) [](https://github.com/guaardvark/guaardvark/stargazers) [](https://github.com/guaardvark/guaardvark/issues) [](https://github.com/sponsors/guaardvark)
**The self-hosted AI studio.** Coding agents and 20-agent swarms in isolated git worktrees, screen agents with their own real desktop, self-tuning RAG, continuous voice chat — and a full media pipeline: video, image, full-song music, neural voice. One install, one GPU, everything on your machine. Your machine. Your data. Your rules.
**Works with your coding agent.** Claude Code, Cursor, Codex, OpenClaw and Gemini CLI drive every flow above through the built-in MCP server and fifteen [agent skills](.agents/skills/README.md): "make a music video from this song
Related Skills
LumaBrowser
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat an
Soundbox
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-spee
Ghost Showcase
Invisible AI assistant for Windows — real-time STT + multi-provider LLM (Claude/GPT/Ollama/LM Studio) + RAG, s
Dynamic Architectures
Dynamic/morphogenetic neural networks - grow, prune, adapt topology during training. Continual learning, gradi
Multimodal Voice Assistant
This project is a multi-modal AI voice assistant that uses LM Studio, OpenAI API or Claude Code, audio process
AI Video Studio
Claude Code skill for making AI films end to end: script → Gemini TTS voiceover (any language, multi-voice) →
Related Agents
Agent
AI video production orchestrator. Routes requests to specialized ComfyUI skills for character generation, vide
Audio Gen
Local audio generation operator for one ComfyUI/GPU slot. Use to generate music, SFX, ambience and voice throu
Aiml Engineer
AI/ML integration specialist. Designs model pipelines (inference, fine-tuning, LoRA adapters), selects infrast
