Repository History
69 repositories tagged with ai-agents
AI-Agents-Projects-Tutorials: Comprehensive Guide to AI Agent Development
The AI-Agents-Projects-Tutorials repository offers an extensive collection of code implementations and tutorials for building advanced AI agents. It covers fundamental concepts such as multi-agent systems, memory management, planning, and reasoning loops. This resource is ideal for developers and researchers seeking practical insights into agentic AI development.
Destructive Command Guard (dcg): Protecting AI Agents from Dangerous Commands
The Destructive Command Guard (dcg) is a high-performance hook designed to prevent AI coding agents from executing dangerous git and shell commands. Built in Rust, dcg intercepts and blocks catastrophic operations like `git reset --hard` or `rm -rf`, offering clear explanations and safer alternatives. It provides a crucial safety layer for developers working with tools like Claude Code, Codex CLI, and GitHub Copilot.
Loop Engineering: Orchestrating AI Agents with Practical Patterns and Tools
Loop Engineering is a GitHub repository offering practical patterns, starters, and CLI tools for building robust AI coding agent systems. It shifts the focus from individual prompt crafting to designing control systems that orchestrate agents over time. This project empowers developers to create autonomous, iterative AI workflows for various development tasks.
My Virtual World: A Self-Hosted 3D AI Virtual World for Agent Harnesses
My Virtual World is an innovative self-hosted 3D AI virtual environment designed for agent harnesses such as OpenClaw and Hermes. It allows AI agents to live, work, move between buildings, and interact with objects in a persistent voxel-style world. This project offers a unique platform for developing and observing AI agent behaviors in a rich, customizable 3D setting.
Deliberation: Multi-Agent LLM Consensus for Code and Plan Review
Deliberation is an innovative GitHub repository that enables Claude Code to leverage multiple LLMs like GPT, Gemini, Grok, and 400+ OpenRouter models for expert second opinions and arbiter-mediated consensus. It provides specialized AI agents for tasks such as code review, security analysis, and architectural design, ensuring comprehensive and reliable feedback. This project helps developers get diverse perspectives and achieve higher quality in their work.
Zeroboot: Sub-millisecond VM Sandboxes for AI Agents
Zeroboot is an innovative open-source project that delivers sub-millisecond VM sandboxes, primarily designed for AI agents and other applications requiring extremely fast, isolated code execution environments. It leverages copy-on-write forking and Firecracker microVMs to achieve hardware-enforced isolation with minimal overhead. This approach enables rapid, secure code execution, ideal for high-performance AI applications.
Hermes WebUI: A Powerful Web Interface for Your Autonomous AI Agent
Hermes WebUI provides a lightweight, dark-themed web application for interacting with Hermes Agent, offering full parity with the CLI experience. This self-hosted interface allows users to manage sessions, browse workspaces, and control their AI agent from any web browser or phone, enhancing accessibility and user experience. It integrates seamlessly with existing Hermes Agent setups, requiring no additional configuration.
CloakBrowser: Stealth Chromium for Unblockable Web Scraping and Automation
CloakBrowser is a powerful, open-source stealth Chromium browser engineered to bypass advanced bot detection systems. It achieves unparalleled stealth through C++ source-level fingerprint patches, making it appear as a normal browser and passing over 30 detection tests. Designed as a drop-in replacement for Playwright and Puppeteer, it simplifies web automation for AI agents, web scraping, and more.
AI Website Cloner Template: Clone Websites with AI Coding Agents
The AI Website Cloner Template is an innovative open-source project that leverages AI coding agents to reverse-engineer any website into a clean, modern Next.js codebase. It enables users to clone entire websites with a single command, extracting design tokens, assets, and reconstructing sections in parallel. This tool is ideal for platform migration, recovering lost source code, or learning web development by deconstructing live sites.
claude-code-best-practice: From Vibe Coding to Agentic Engineering with Claude
The `claude-code-best-practice` repository offers a comprehensive guide to mastering Claude Code, transitioning developers from 'vibe coding' to efficient agentic engineering. It compiles essential best practices, structured workflows, and expert tips to maximize productivity and leverage Claude's advanced AI capabilities. This resource is invaluable for anyone looking to optimize their AI-driven development processes.
FinceptTerminal: Advanced Financial Analytics and AI for Market Research
FinceptTerminal is a cutting-edge finance application designed for in-depth market analysis and data-driven investment decisions. It provides advanced tools for market analytics, investment research, and economic data exploration. Built with C++20 and Qt6, and leveraging embedded Python, it offers institutional-grade performance in a user-friendly environment.
chrome-devtools-mcp: Empowering AI Agents with Chrome DevTools Capabilities
chrome-devtools-mcp is a powerful tool that enables AI coding agents to control and inspect a live Chrome browser. It functions as a Model-Context-Protocol (MCP) server, providing AI assistants with full access to Chrome DevTools for advanced automation, debugging, and performance analysis. This allows agents to interact with web pages, gather insights, and perform complex tasks programmatically.