Repository History
138 repositories tagged with LLM
turboseek: An Open-Source AI Search Engine Inspired by Perplexity
turboseek is an innovative open-source AI search engine developed by Nutlope, drawing inspiration from platforms like Perplexity. Built with TypeScript, it leverages advanced LLMs and search APIs to provide comprehensive answers and related follow-up questions. This project offers a robust foundation for anyone interested in building their own AI-powered search solution.
Obsidian Smart Composer: AI Chat Assistant for Contextual Notes
Obsidian Smart Composer is an AI chat assistant plugin for Obsidian designed to enhance note-taking and content creation. It offers contextual awareness, smart writing assistance, and one-click edits, allowing users to leverage their vault content for more efficient AI interactions. The plugin supports vault-aware conversations, semantic search, and integration with various AI models, including local ones.
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.
bolt.diy: AI-Powered Full-Stack Web Development with Any LLM in Your Browser
bolt.diy is an open-source project that empowers developers to prompt, run, edit, and deploy full-stack web applications directly in their browser. It offers unparalleled flexibility by supporting over 19 different Large Language Models (LLMs), allowing users to choose their preferred AI for code generation and development tasks. This tool streamlines the development workflow, making AI-assisted coding accessible and highly customizable.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper2Code is an innovative multi-agent LLM system designed to automate the generation of code repositories directly from scientific papers in machine learning. It employs a sophisticated three-stage pipeline, encompassing planning, analysis, and code generation, each managed by specialized agents. This approach ensures faithful and high-quality implementations, outperforming existing baselines on relevant benchmarks.
context-engineering-intro: Master AI Coding Assistants with Context Engineering
Context Engineering represents a powerful evolution beyond traditional prompt engineering, focusing on providing comprehensive information to AI coding assistants for end-to-end task completion. The coleam00/context-engineering-intro repository offers a robust template and step-by-step guide to implement this discipline effectively. It enables developers to leverage AI, particularly with tools like Claude Code, to build complex features with greater consistency and fewer failures.
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.
Memori: SQL Native Memory Layer for LLMs and AI Agents
Memori is an SQL Native Memory Layer designed for LLMs, AI Agents, and Multi-Agent Systems. It provides a robust and flexible solution for managing long-short term memory, integrating seamlessly with existing software and infrastructure. This project aims to enhance AI systems with persistent, structured memory capabilities, making them more intelligent and context-aware.
TextMachina: A Python Framework for MGT Dataset Generation
TextMachina is a modular and extensible Python framework designed for creating high-quality, unbiased datasets for Machine-Generated Text (MGT) tasks. It supports detection, attribution, and boundary detection, offering a user-friendly pipeline with LLM integrations, prompt templating, and bias mitigation. This tool streamlines the process of building robust models for understanding and identifying AI-generated content.
DeepScrape: Intelligent Web Scraping & LLM-Powered Data Extraction
DeepScrape is an AI-powered web scraping tool designed for intelligent data extraction using LLMs. It leverages Playwright for browser automation and supports both cloud (OpenAI) and local LLMs (Ollama, vLLM) for transforming web content into structured JSON. This versatile tool is ideal for modern web applications, RAG pipelines, and various data workflows, offering privacy-first data processing.
Airweave: Context Retrieval for AI Agents Across Apps and Databases
Airweave is an open-source context retrieval layer designed for AI agents, enabling them to access information across various applications and databases. It transforms diverse content into searchable knowledge bases, offering a standardized interface for agents to perform semantic, hybrid, and recency-biased searches. The platform simplifies data synchronization, entity extraction, and serves as a robust foundation for building intelligent AI applications.
Toolkit-for-Prompt-Compression: A Unified Toolkit for LLM Prompt Compression
PCToolkit is a unified, plug-and-play toolkit designed for efficient prompt compression in Large Language Models (LLMs). It provides state-of-the-art compression methods, diverse datasets, and comprehensive metrics for evaluating performance. This modular toolkit simplifies the process of condensing input prompts while preserving crucial information.