Repository History
83 repositories tagged with LLM
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.
spacy-llm: Integrating LLMs into Structured NLP Pipelines with spaCy
spacy-llm seamlessly integrates Large Language Models (LLMs) into spaCy, offering a modular system for rapid prototyping and transforming unstructured LLM responses into robust outputs for various NLP tasks. It supports a wide range of LLMs, including OpenAI, Cohere, Anthropic, and open-source models, enabling users to combine the power of LLMs with spaCy's production-ready capabilities. This package allows for quick experimentation and the creation of efficient, reliable, and controlled NLP systems.
Qwen3-VL: A Powerful Multimodal Large Language Model Series
Qwen3-VL is a cutting-edge multimodal large language model series from Alibaba Cloud's Qwen team. It offers significant advancements in visual and text understanding, extended context length, and enhanced agent capabilities. This model is designed for flexible deployment, scaling from edge to cloud.
Feynman: The Open Source AI Research Agent
Feynman is an open-source AI research agent designed to automate and streamline complex research tasks. Built with TypeScript, it leverages multiple agents and tools to conduct in-depth investigations, literature reviews, and even experiment replications, providing source-grounded outputs.
autoresearch: AI Agents for Autonomous LLM Training Research
autoresearch, by Andrej Karpathy, pioneers autonomous AI research by enabling agents to experiment with LLM training on a single GPU. The system allows an AI agent to modify code, train a model for a fixed 5-minute duration, and iteratively optimize for improved performance. This innovative approach aims to automate the experimental cycle of AI research, fostering continuous discovery and optimization.
agency-agents: Your Complete AI Agency of Specialized Experts
agency-agents offers a comprehensive collection of over 140 meticulously crafted AI agent personalities, designed to act as specialized experts across various domains. From frontend development to marketing and sales, each agent comes with a unique voice, proven processes, and deliverable-focused outcomes. This repository provides a ready-to-deploy AI dream team to transform your workflow and accelerate project delivery.
Claude Code System Prompts: Deconstructing Agentic AI Coding Assistants
This repository offers a deep dive into the inner workings of modern agentic AI coding assistants. It reconstructs prompt patterns, agent coordination strategies, and security mechanisms, providing insights into how tools like Claude Code operate. The project serves as a valuable resource for understanding the architectural patterns behind these advanced AI systems.
Supply Chain Monitor: Automated Detection of Package Compromises
Supply Chain Monitor is a powerful tool by Elastic designed to automatically detect supply chain compromises in popular PyPI and npm packages. It polls registries for new releases, diffs them against predecessors, and uses an LLM via Cursor Agent CLI to classify changes as benign or malicious. Malicious findings trigger immediate Slack alerts, enhancing security for your software dependencies.
JARVIS: Connecting LLMs with the ML Community for AGI Exploration
JARVIS is an innovative system developed by Microsoft that aims to bridge Large Language Models (LLMs) with the broader Machine Learning community. It serves as a collaborative platform, using an LLM as a controller to orchestrate numerous expert models from Hugging Face Hub, thereby facilitating the exploration of Artificial General Intelligence (AGI) and solving complex AI tasks. This system streamlines the process of task planning, model selection, execution, and response generation.
Open Deep Research: A Configurable Open-Source Deep Research Agent
Open Deep Research is a fully open-source, configurable agent designed for deep research applications. It supports various model providers, search tools, and Model Context Protocol (MCP) servers, offering performance comparable to other popular deep research agents. Developed by LangChain, it leverages LangGraph for robust agent orchestration and provides extensive customization options.
Firecrawl: Web Scraping and Interaction API for AI Agents
Firecrawl is an open-source API designed to empower AI agents and applications with clean, structured web data. It provides robust capabilities for searching, scraping, and interacting with the web at scale, effectively transforming complex web content into LLM-ready formats. This tool handles the intricate challenges of web data extraction, allowing developers to focus on building intelligent applications.
LLMGym: A Unified Environment for LLM Agent Development and Benchmarking
LLMGym is a unified environment interface designed for developing and benchmarking LLM applications that learn from feedback. It provides a suite of seamlessly swappable environments, making fair and comprehensive comparisons easier for researchers and developers. This project aims to be the "gym" for LLM agents, offering an intuitive interface for various tasks.