Skip to content

opensite-ai/opensite-skills / linux-ai-dev-stack

linux-ai-dev-stack

Flagged

Install and wire the AI toolchain on a Linux dev machine: local LLM inference (Ollama, llama.cpp, vLLM, SGLang, TabbyAPI) with VRAM-based model selection, AI coding agents and CLIs (Claude Code, Codex, aider, OpenCode) with MCP servers, ML frameworks (PyTorch/JAX, Jupyter, HuggingFace) and GPU containers, and cloud/remote GPU workflows (RunPod, Vast.ai, Lambda, remote dev over SSH and Tailscale). Use when someone wants to run local models, set up or connect AI coding agents, configure MCP servers, route agents to local or cloud models, install an ML/GPU Python stack, or offload work to a rented GPU. It runs on the machine and assumes working GPU drivers.

templates/gpu-compose.yaml

View on GitHub
# Docker Compose — a local LLM inference service with an NVIDIA GPU reservation.
# Requires the NVIDIA Container Toolkit on the host (see references/ml-frameworks.md).
# Run:   docker compose -f gpu-compose.yaml up -d
# Verify GPU:  docker compose -f gpu-compose.yaml exec inference nvidia-smi
# Image tags/versions are examples as of 2026-07 — verify before use.

services:
  inference:
    # Ollama is the simplest default; swap for vllm/vllm-openai or a llama.cpp image.
    image: ollama/ollama:latest
    container_name: ai-inference
    restart: unless-stopped
    ports:
      # Bind to loopback by default. Expose on the LAN ONLY on a trusted network,
      # and always front it with auth/TLS or Tailscale (see local-llm-inference.md).
      - "127.0.0.1:11434:11434"
    volumes:
      - ollama-models:/root/.ollama
    environment:
      OLLAMA_HOST: "0.0.0.0:11434"
      OLLAMA_KV_CACHE_TYPE: "q8_0"
      OLLAMA_FLASH_ATTENTION: "1"
      OLLAMA_CONTEXT_LENGTH: "8192"
    # NVIDIA GPU reservation (Compose Deploy spec).
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all          # or a specific number, e.g. 1
              capabilities: ["gpu"]
    healthcheck:
      test: ["CMD", "sh", "-c", "curl -sf http://localhost:11434/v1/models || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 5

volumes:
  ollama-models:
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall