IndyDevDan

claude-code-hooks-mastery. Master Claude Code Hooks

claude-code-hooks-multi-agent-observability. Real-time monitoring for Claude Code agents through simple hook event tracking.

pi-vs-claude-code. Comparison between open source PI agent and closed source Claude Code agent

always-on-ai-assistant. A pattern for an always on AI Assistant powered by Deepseek-V3, RealtimeSTT, and Typer for engineering

multi-agent-postgres-data-analytics. The way we interact with our data is changing.

just-prompt. just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

poc-realtime-ai-assistant. Sharing early versions of Ada, a personal AI Assistant built on OpenAIs Realtime API

infinite-agentic-loop. An experimental project demonstrating Infinite Agentic Loop in a two prompt system using Claude Code.

claude-code-damage-control. Python

benchy. Benchmarks you can feel

single-file-agents. What if we could pack single purpose, powerful AI Agents into a single python file?

the-library. A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.

agent-sandbox-skill. An agent skill for managing isolated execution environments

claude-code-is-programmable. Scale your compute with Claude Code as a programmable agentic coding tool

aider-mcp-server. Minimal MCP Server for Aider

big-3-super-agent. Gemini 2.5 Computer Use + OpenAI Realtime API + Claude Code Multi-Agent Experiment

mac-mini-agent. Simple CLI, Skills, and Prompts for operating your Mac devices with agents

bowser. Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

marimo-prompt-library. Engineer your reusable, customizable, prompt library in Marimo reactive notebooks

pocket-pick. What if the exact code snippet or idea you were looking for was one prompt away?

nano-agent. A MCP Server for a small scale engineering agents with multi-provider LLM support.

agentic-drop-zones. Python

personal-ai-starter-pack. Fast STT, LLM, and TTS for personal AI assistants using OpenAI, Groq, AssemblyAI and ElevenLabs.

mermaid-js-ai-agent. Communicate your work with diagrams in seconds with GenAI + Mermaid

indydevtools. An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

fork-repository-skill. Take your current agent running in your terminal and fork it N times to smoothly branch your engineering work.

the-verifier-agent. TypeScript

quick-data-mcp. Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

anthropic-computer-use-bash-and-files. Python

beyond-mcp. It's time to push beyond MCP Servers... Right?

pi-agent-observability. TypeScript

planf3. Plans For Fable 5

install-and-maintain. Deterministic and Agentic patterns for installing and maintaining successful production applications

agentic-finance-review. HTML

diffbro. Your AI Peer Review Bro

agent-sandboxes. Python

live-bench. Live benchmarking platform — FastAPI + click CLI + Vue 3 frontend with real-time SSE bar charts

claude-3-7-sonnet-starter-pack. Look, Anthropic's Claude-3.7-Sonnet is a powerful, hybrid CRASHOUT LLM. Let's understand this monumental release.

llm-prompt-testing-quick-start. LLM Prompt Testing Quick Start

reusable-openai-fine-tune. Use this codebase to fine-tune OpenAI models with your own data.

omni-complete. LLM Use Case: LLM Powered, Reusable, Domain Agnostic Autocompletes

bash-damage-from-within. Python

elm-itv-benchmark. Simple, Opinionated benchmark for testing the viability of Efficient Language Models (ELMs) for personal use cases.

lllm. Local LLMs in One Line Of Code (thanks to llamafile)

learning-cmux-with-agents. 31 natural-language prompts that prove one primary agent can stand up, drive, and tear down a whole fleet of AI coding agents and terminals inside cmux.

agentic-coding-tool-eval. Simple ideas to compare Agentic Coding Tools

max-your-cc-sub. Just

1brc-electron. One Billion Row Challenge end to end desktop solution built using AI tech

final_stand_1.5. Final Stand sequel run the .swf file to play