#python

nanochat lets you train your own GPT-2 level LLM—like a basic ChatGPT—for just $73 in 3 hours on an 8xH100 GPU node using the simple speedrun.sh script. It handles tokenization, pretraining, finetuning, evaluation, inference, and a web chat UI in minimal, hackable code. You benefit by easily building, customizing, and chatting with your personal AI on a tiny budget, learning LLM mechanics hands-on without complex setups.

https://github.com/karpathy/nanochat

#shell #ai_agents #ai_coding #claude #claude_code #project_management #vibe_coding

Claude Code PM is a workflow that turns product ideas into GitHub issues and code using spec-driven steps, parallel AI agents, and commands like /pmepic-oneshot to break tasks, and /pm:issue-start for execution. It preserves context, enables team collaboration via GitHub, and ensures every code line traces to specs. You benefit by shipping 3x faster, cutting bugs 75%, reducing context loss 89%, and working with multiple agents simultaneously for higher productivity.

https://github.com/automazeio/ccpm

#python

AI-assisted code review prompts by Linux kernel expert Chris Mason speed up Linux kernel and systemd patch reviews. Install easily with bash scripts, then use slash commands like /kreview or /kdebug in tools like Claude—they auto-load project context, break big diffs into tasks, cut token costs by 40-60%, and catch more bugs. You benefit by reviewing code 30-50% faster, saving money, reducing burnout, and improving quality without replacing human checks. Works with GPT-4, Claude, and more; pairs best with semcode for navigation.

https://github.com/masoncl/review-prompts

#typescript #agentic_workflow #ai_agent #ai_runtime #ai_sandbox #claude_code #cli #cloudflare #codex #containers #context_engineer #dev_tools #gemini_cli #react #sandbox #typescript

VM0 is a natural language agent that runs workflows automatically 24/7 in secure cloud sandboxes. It offers isolated Claude Code execution, 35,000+ skills for tools like GitHub and Notion, persistent chats with resume/fork options, and full logs/metrics for monitoring. Quick start via `npm install -g @vm0/cli && vm0 onboard` gets you automating in 5 minutes. You benefit by saving hours on repetitive tasks like reports or data syncs, with reliable, observable runs anytime.

https://github.com/vm0-ai/vm0

#python

Agent Skills are reusable packages of instructions, scripts, and resources that AI agents like Codex can automatically load to complete specific tasks efficiently and consistently. Instead of repeating the same guidance repeatedly, you write a skill once and use it everywhere, which saves time and reduces errors. You can install pre-built skills automatically or create custom ones tailored to your organization's needs, then share them across teams. This modular approach transforms general AI assistants into domain specialists, enabling them to handle complex, specialized workflows reliably without requiring you to provide the same instructions in every conversation.

https://github.com/openai/skills