Repository History
10 repositories tagged with Agent
Headroom: Drastically Reduce LLM Token Usage for AI Agents
Headroom is an innovative context compression layer for AI agents, designed to significantly reduce token usage for LLMs. It achieves 60-95% fewer tokens across various inputs like tool outputs, logs, files, and RAG chunks, all while preserving answer accuracy. This powerful tool enhances efficiency and cost-effectiveness for AI interactions.
PixelRAG: Pixel-Native Search for Visual Retrieval-Augmented Generation
PixelRAG revolutionizes search by enabling pixel-native retrieval, moving beyond traditional text parsing. It renders documents as screenshots, preserving visual context like tables and charts, which is crucial for accurate answers from reader models. This allows for searching any document based on its visual appearance, not just its textual content.
OpenHuman: Your Private, Powerful AI Super Intelligence
OpenHuman is an open-source, agent-based personal AI assistant built with Rust, designed for privacy, simplicity, and power. It integrates seamlessly into your daily workflow, offering local knowledge management, extensive third-party integrations, and advanced memory capabilities. This project aims to provide a personal AI that truly understands and remembers your context from day one.
FlyAI-Skill: Empowering AI Agents with Real-time Travel Search
FlyAI-Skill is a powerful GitHub repository that provides AI agents with real-time travel search capabilities. It integrates seamlessly with platforms like Claude Code and OpenClaw, allowing users to search for flights, hotels, and attractions using natural language. This skill connects to Fliggy's extensive travel platform, delivering structured and bookable results directly within your terminal.
Sniffly: Claude Code Analytics Dashboard for Usage and Error Analysis
Sniffly is an open-source Python project that provides a comprehensive dashboard for analyzing Claude Code logs. It helps users understand their usage patterns, identify common errors, and review message history to improve their interaction with Claude Code. The tool runs locally, ensuring privacy, and offers a unique feature for sharing project statistics.
Vanna: Chat with Your SQL Database Using LLMs and Agentic Retrieval
Vanna is an open-source Python library that enables natural language interaction with SQL databases, leveraging Large Language Models (LLMs) for accurate text-to-SQL generation. Version 2.0 introduces enterprise-grade features like user-aware permissions, a modern web interface, and streaming responses, making it ideal for secure and scalable data analytics applications.
vibe-tools: Empowering AI Agents with Teams and Advanced Skills
vibe-tools is a powerful CLI designed to enhance AI agents by providing them with an AI team and advanced skills. It integrates tools like Perplexity for web research, Gemini for repository context, and Stagehand for browser automation. Optimized for Cursor Composer Agent, vibe-tools can be utilized by any coding agent capable of executing commands.
OmniParser: A Vision-Based Tool for GUI Agent Screen Parsing
OmniParser is a comprehensive tool developed by Microsoft for parsing user interface screenshots into structured, understandable elements. It significantly enhances the ability of vision-based models, such as GPT-4V, to generate accurate actions grounded in specific regions of a GUI. This project aims to advance pure vision-based GUI agents by providing robust screen parsing capabilities.
Qwen Code: An AI-Powered Command-Line Workflow Tool for Developers
Qwen Code is an advanced command-line AI workflow tool designed to enhance developer productivity. Adapted from Gemini CLI and optimized for Qwen3-Coder models, it offers intelligent assistance for coding, understanding large codebases, and automating development tasks. This tool provides powerful features to streamline your daily coding activities, including free usage options.
Ditto: The Simplest Self-Building Coding Agent for Flask Apps
Ditto is a user-friendly Python tool that generates multi-file Flask applications from simple natural language descriptions. It leverages a straightforward LLM loop to automate the coding process, enabling users to transform ideas into functional web applications through a no-code interface. This agent simplifies development by automatically planning and constructing applications based on plain English input.