DietrichGebert/ponytail
Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.
Awesome AI Agents › AI Assistants
ghuntley/how-to-build-a-coding-agent
This project is a comprehensive workshop designed to teach users how to build their own AI-powered coding assistant step-by-step. The workshop guides participants through creating a coding agent that evolves from a simple chatbot to a sophisticated assistant capable of reading files, exploring directories, running shell commands, editing code, and searching codebases. The project uses the Anthropic Claude API to power the AI interactions, allowing the agent to understand and respond to user inputs intelligently. The workshop is structured into six progressive stages, each adding new functionalities to the coding agent. Starting with a basic chat interface, users learn to integrate file reading capabilities, directory listing, shell command execution, file editing, and advanced code searching using pattern matching powered by ripgrep. This incremental approach helps users grasp the underlying architecture and tool integration techniques effectively. The agent operates on an event loop architecture where it waits for user input, sends it to the Claude API, and either responds directly or invokes specific tools to perform tasks like reading or modifying files. The results from these tools are then fed back to the AI to generate the final response. This modular design allows for easy extension and customization of the agent's capabilities. The workshop requires minimal prior AI expertise and provides detailed setup instructions, including environment configuration and API key management. It also offers troubleshooting tips and encourages experimentation with custom tools, tool chains, memory features, and potential web UI integrations. Overall, this project is an educational resource for developers interested in building intelligent coding assistants that can automate and enhance their development workflows by leveraging AI and tool-based interactions.
https://github.com/ghuntley/how-to-build-a-coding-agent
Also in AI Assistants
HKUDS/DeepTutor
DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.
agentscope-ai/QwenPaw
QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...
mukul975/Anthropic-Cybersecurity-Skills
A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.
googleworkspace/cli
gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.
nanocoai/nanoclaw
NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.
screenpipe/screenpipe
Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.