Repository History
186 repositories tagged with AI
Microsandbox: Secure, Self-Hosted Sandboxes for AI Agents and Untrusted Code
Microsandbox is an open-source project providing self-hosted, hardware-isolated sandboxes designed for securely executing untrusted user and AI code. It offers a unique balance of strong isolation, instant startup times, and OCI compatibility, addressing the challenges of traditional container and VM solutions. Built in Rust, Microsandbox is ideal for developers building agentic AI applications requiring robust and flexible execution environments.
learn-claude-code: Build AI Coding Agents from Scratch with Python
The learn-claude-code repository offers a progressive tutorial to demystify AI coding agents like Claude Code, Kode, and Cursor Agent. It teaches users how modern AI agents work by building them from scratch, starting with a minimal 16-line Bash agent. This project emphasizes the core concept of "Model as Agent" through five evolving versions.
Rocketnotes: AI-Powered Markdown Editor for Local and Cloud Knowledge Management
Rocketnotes is an innovative AI-powered markdown editor designed for efficient knowledge management. It allows users to leverage Large Language Models (LLMs) with their documents, offering both 100% local and cloud deployment options. This versatile tool integrates advanced features like semantic search, AI chat, and agentic archiving to enhance productivity and organization.
vLLM CLI: A Powerful Command-Line Interface for Serving LLMs with vLLM
vLLM CLI is an intuitive command-line interface tool designed to simplify serving Large Language Models using vLLM. It offers both interactive and direct CLI modes, enabling efficient model management, real-time server monitoring, and advanced configuration. This tool streamlines the deployment and management of LLMs, making it accessible for various use cases.
lagent: A Lightweight Framework for Building LLM-Based Agents
lagent is a lightweight, open-source framework developed by InternLM, designed for efficiently building large language model (LLM)-based agents. It provides a PyTorch-inspired design philosophy, making it intuitive for developers to create and manage multi-agent applications. This framework simplifies the process of agent communication, memory management, and tool integration.
LMQL: A Language for Constraint-Guided and Efficient LLM Programming
LMQL is an innovative programming language that extends Python, designed for efficient and constraint-guided programming of Large Language Models (LLMs). It allows developers to interweave traditional programming logic with native LLM calls, offering advanced control over model behavior through features like constraints, rich control flow, and optimized runtimes. This makes it easier to build complex LLM-powered applications with greater precision and efficiency.
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.
Speakr: Self-Hosted AI Transcription and Intelligent Note-Taking Platform
Speakr is a powerful, self-hosted web application for transcribing audio recordings into organized, searchable, and intelligent notes. It prioritizes privacy by running on your own infrastructure and offers advanced AI features like speaker identification, interactive chat, and semantic search. This platform is ideal for individuals and groups seeking to transform audio into actionable insights while maintaining full control over their data.
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.
CSM: A Conversational Speech Generation Model by SesameAILabs
CSM (Conversational Speech Model) is an advanced speech generation model from SesameAILabs, designed to create RVQ audio codes from text and audio inputs. It leverages a Llama backbone and a smaller audio decoder for Mimi audio codes, enabling high-quality, context-aware speech synthesis. The model is now natively available in Hugging Face Transformers, making it accessible for researchers and developers.
Optimum: Accelerate Hugging Face Models with Hardware Optimization
Optimum is an extension of Hugging Face Transformers, Diffusers, TIMM, and Sentence-Transformers, designed to provide a suite of optimization tools. It enables maximum efficiency for training and running models on targeted hardware, simplifying the process for developers. This library helps users achieve significant performance gains across various machine learning workflows.