New AI tools - Open Source

ISEK is a decentralized agent network framework that enables building intelligent, collaborative agent-to-agent systems. It integrates the Google A2A protocol and ERC-8004 contracts for identity registration, reputation building, and cooperative task-solving, creating a self-organizing, decentralized society of agents. The platform addresses challenges in the agent ecosystem by providing an incentive system for users to pay for agent services, motivating developers to build high-quality agents and fostering innovation and quality in the ecosystem. ISEK focuses on decentralized agent collaboration and coordination, allowing agents to find each other, reason together, and act as a decentralized system without central control. The platform utilizes ERC-8004 for decentralized identity, reputation, and validation registries, establishing trustless verification and reputation management.

Strava MCP Server is a TypeScript implementation of a Model Context Protocol (MCP) server that serves as a bridge to the Strava API. It provides tools for accessing recent activities, detailed activity streams, segments exploration, activity and segment effort information, saved routes details, and route exporting in GPX or TCX format. The server offers AI-friendly JSON responses via MCP and utilizes Strava API V3 for seamless integration. Users can interact with their Strava data through natural language queries and advanced prompts, enabling personalized analysis and visualization of their activities.

Youtu-GraphRAG is a vertically unified agentic paradigm that connects the entire framework based on graph schema, allowing seamless domain transfer with minimal intervention. It introduces key innovations like schema-guided hierarchical knowledge tree construction, dually-perceived community detection, agentic retrieval, advanced construction and reasoning capabilities, fair anonymous dataset 'AnonyRAG', and unified configuration management. The framework demonstrates robustness with lower token cost and higher accuracy compared to state-of-the-art methods, enabling enterprise-scale deployment with minimal manual intervention for new domains.

langfuse-js is a modular mono repo for the Langfuse JS/TS client libraries. It includes packages for Langfuse API client, tracing, OpenTelemetry export helpers, OpenAI integration, and LangChain integration. The SDK is currently in version 4 and offers universal JavaScript environments support as well as Node.js 20+. The repository provides documentation, reference materials, and development instructions for managing the monorepo with pnpm. It is licensed under MIT.

A complete Large Language Model implementation in pure Rust with no external ML frameworks. Demonstrates building a transformer-based language model from scratch, including pre-training, instruction tuning, interactive chat mode, full backpropagation, and modular architecture. Model learns basic world knowledge and conversational patterns. Features custom tokenization, greedy decoding, gradient clipping, modular layer system, and comprehensive test coverage. Ideal for understanding modern LLMs and key ML concepts. Dependencies include ndarray for matrix operations and rand for random number generation. Contributions welcome for model persistence, performance optimizations, better sampling, evaluation metrics, advanced architectures, training improvements, data handling, and model analysis. Follows standard Rust conventions and encourages contributions at beginner, intermediate, and advanced levels.

OpenMCP is an integrated plugin for MCP server debugging in vscode/trae/cursor, combining development and testing functionalities. It includes tools for testing MCP resources, managing large model interactions, project-level management, and supports multiple large models. The openmcp-sdk allows for deploying MCP as an agent app with easy configuration and execution of tasks. The project follows a modular design allowing implementation in different modes on various platforms.

Uni-CoT is a unified reasoning framework that extends Chain-of-Thought (CoT) principles to the multimodal domain, enabling Multimodal Large Language Models (MLLMs) to perform interpretable, step-by-step reasoning across both text and vision. It decomposes complex multimodal tasks into structured, manageable steps that can be executed sequentially or in parallel, allowing for more scalable and systematic reasoning.

The LLM Open Source Landscape and Trends project aims to provide insights into the rapidly evolving open source ecosystem, highlighting current trends and notable projects. The project is dedicated to maintaining and sharing new insights, fostering open collaboration with the community. Contributions of high-quality insights, data stories, and use cases are encouraged through PR submissions to the `data-stories` folder.

This repository serves as a reference implementation for running a chat application and an AI orchestration layer using Azure AI Foundry Agent service and OpenAI foundation models. It covers common generative AI chat application characteristics such as creating agents, querying data stores, chat memory database, orchestration logic, and calling language models. The implementation also includes production requirements like network isolation, Azure AI Foundry Agent Service dependencies, availability zone reliability, and limiting egress network traffic with Azure Firewall.

Legacy-use is a tool that transforms legacy applications into modern REST APIs using AI. It allows users to dynamically generate and customize API endpoints for legacy or desktop applications, access systems running legacy software, track and resolve issues with built-in observability tools, ensure secure and compliant automation, choose model providers independently, and deploy with enterprise-grade security and compliance. The tool provides a quick setup process, automatic API key generation, and supports Windows VM automation. It offers a user-friendly interface for adding targets, running jobs, and writing effective prompts. Legacy-use also supports various connectivity technologies like OpenVPN, Tailscale, WireGuard, VNC, RDP, and TeamViewer. Telemetry data is collected anonymously to improve the product, and users can opt-out of tracking. Optional configurations include enabling OpenVPN target creation and displaying backend endpoints documentation. Contributions to the project are welcome.

MapAnything is an end-to-end trained transformer model for 3D reconstruction tasks, supporting over 12 different tasks including multi-image sfm, multi-view stereo, monocular metric depth estimation, and more. It provides a simple and efficient way to regress the factored metric 3D geometry of a scene from various inputs like images, calibration, poses, or depth. The tool offers flexibility in combining different geometric inputs for enhanced reconstruction results. It includes interactive demos, support for COLMAP & GSplat, data processing for training & benchmarking, and pre-trained models on Hugging Face Hub with different licensing options.

Rowboat is a tool that allows users to build AI agents instantly with natural language, connect tools with one-click integrations, power workflows with knowledge by adding documents for RAG, automate workflows by setting up triggers and actions, and deploy anywhere via API or SDK. Users can access a hosted version to start building agents right away. The tool provides features such as native RAG support, custom LLM providers, tools & triggers for automation, and API & SDK integration. Users can refer to the documentation to learn how to start building agents with Rowboat.

The AI Agent Service Toolkit is a comprehensive toolkit designed for running an AI agent service using LangGraph, FastAPI, and Streamlit. It includes a LangGraph agent, a FastAPI service, a client for interacting with the service, and a Streamlit app for providing a chat interface. The project offers a template for building and running agents with the LangGraph framework, showcasing a complete setup from agent definition to user interface. Key features include LangGraph Agent with latest features, FastAPI Service, Advanced Streaming support, Streamlit Interface, Multiple Agent Support, Asynchronous Design, Content Moderation, RAG Agent implementation, Feedback Mechanism, Docker Support, and Testing. The repository structure includes directories for defining agents, protocol schema, core modules, service, client, Streamlit app, and tests.

Laravel Boost accelerates AI-assisted development by providing essential context and structure for generating high-quality, Laravel-specific code. It includes an MCP server with specialized tools, AI guidelines, and a Documentation API. Boost is designed to streamline AI-assisted coding workflows by offering precise, context-aware results and extensive Laravel-specific information.

Notely Voice is a free, modern, cross-platform AI voice transcription and note-taking application. It offers powerful Whisper AI Voice to Text capabilities, making it ideal for students, professionals, doctors, researchers, and anyone in need of hands-free note-taking. The app features rich text editing, simple search, smart filtering, organization with folders and tags, advanced speech-to-text, offline capability, seamless integration, audio recording, theming, cross-platform support, and sharing functionality. It includes memory-efficient audio processing, chunking configuration, and utilizes OpenAI Whisper for speech recognition technology. Built with Kotlin, Compose Multiplatform, Coroutines, Android Architecture, ViewModel, Koin, Material 3, Whisper AI, and Native Compose Navigation, Notely follows Android Architecture principles with distinct layers for UI, presentation, domain, and data.

Zotero MCP seamlessly connects your Zotero research library with AI assistants like ChatGPT and Claude via the Model Context Protocol. It offers AI-powered semantic search, access to library content, PDF annotation extraction, and easy updates. Users can search their library, analyze citations, and get summaries, making it ideal for research tasks. The tool supports multiple embedding models, intelligent search results, and flexible access methods for both local and remote collaboration. With advanced features like semantic search and PDF annotation extraction, Zotero MCP enhances research efficiency and organization.

Haiku RAG is a Retrieval-Augmented Generation (RAG) library that utilizes LanceDB as a local vector database. It supports semantic and full-text search, hybrid search with Reciprocal Rank Fusion, multiple embedding and QA providers, default search result reranking, question answering, file monitoring, and various file formats. It can be used via CLI or Python API, and can serve as tools for AI assistants like Claude Desktop. The library offers features for document management and search, with detailed documentation available.

The Document Knowledge Mining Solution Accelerator leverages Azure OpenAI and Azure AI Document Intelligence to ingest, extract, and classify content from various assets, enabling chat-based insight discovery, analysis, and prompt guidance. It uses OCR and multi-modal LLM to extract information from documents like text, handwritten text, charts, graphs, tables, and form fields. Users can customize the technical architecture and data processing workflow. Key features include ingesting and extracting real-world entities, chat-based insights discovery, text and document data analysis, prompt suggestion guidance, and multi-modal information processing.

This repository hosts a collection of AI blueprint projects for HP AI Studio, providing end-to-end solutions across key AI domains like data science, machine learning, deep learning, and generative AI. The projects are designed to be plug-and-play, utilizing open-source and hosted models to offer ready-to-use solutions. The repository structure includes projects related to classical machine learning, deep learning applications, generative AI, NGC integration, and troubleshooting guidelines for common issues. Each project is accompanied by detailed descriptions and use cases, showcasing the versatility and applicability of AI technologies in various domains.

Pipecat-examples is a collection of example applications built with Pipecat, an open-source framework for building voice and multimodal AI applications. It includes various examples demonstrating telephony & voice calls, web & client applications, realtime APIs, multimodal & creative solutions, translation & localization tasks, support, educational & specialized use cases, advanced features, deployment & infrastructure setups, monitoring & analytics tools, and testing & development scenarios.

Open Source Observer is a free analytics suite that helps funders measure the impact of open source software contributions to the health of their ecosystem. The repository contains various subprojects such as OSO apps, documentation, frontend application, API services, Docker files, common libraries, utilities, GitHub app for validating pull requests, Helm charts for Kubernetes, Kubernetes configuration, Terraform modules, data warehouse code, Python utilities for managing data, OSO agent, Dagster configuration, sqlmesh configuration, Python package for pyoso, and other tools to manage warehouse pipelines.

vue-renderer-markdown is a high-performance tool designed for streaming and rendering Markdown content in real-time. It is optimized for handling incomplete or rapidly changing Markdown blocks, making it ideal for scenarios like AI model responses, live content updates, and real-time Markdown rendering. The tool offers features such as ultra-high performance, streaming-first design, Monaco integration, progressive Mermaid rendering, custom components integration, complete Markdown support, real-time updates, TypeScript support, and zero configuration setup. It solves challenges like incomplete syntax blocks, rapid content changes, cursor positioning complexities, and graceful handling of partial tokens with a streaming-optimized architecture.

Agent-Computer Interface (ACI) for OpenHands is a deprecated repository that provided essential tools and interfaces for AI agents to interact with computer systems for software development tasks. It included a code editor interface, code linting capabilities, and utility functions for common operations. The package aimed to enhance software development agents' capabilities in editing code, managing configurations, analyzing code, and executing shell commands.

The Animal Crossing LLM Mod transforms the game into an AI-powered conversation experience by generating dynamic, contextual dialogue for villagers in real-time. It reads dialogue memory, generates AI responses, writes new dialogue back to the game, and creates natural and contextual conversations. The mod is experimental software with known bugs and is currently only tested on macOS. Users can interact with villagers in Animal Crossing using AI-generated responses, enhancing the gameplay experience.

run-gemini-cli is a GitHub Action that integrates Gemini into your development workflow via the Gemini CLI. It acts as an autonomous agent for routine coding tasks and an on-demand collaborator. Use it for GitHub pull request reviews, triaging issues, code analysis, and more. It provides automation, on-demand collaboration, extensibility with tools, and customization options.

AISDK Prompt Optimizer is an open-source tool designed to transform AI interactions by optimizing prompts. It utilizes the GEPA reflective optimizer to evolve textual components of AI systems, providing features such as reflective prompt mutation, rich textual feedback, and Pareto-based selection. Users can teach their AI desired behaviors, collect ideal samples, run optimization to generate optimized prompts, and deploy the results in their applications. The tool leverages advanced optimization algorithms to guide AI through interactive conversations and refine prompt candidates for improved performance.

The 'cheap-airports' repository is a collection of low-cost airport services with detailed pricing information. It includes various airport options with different pricing plans, catering to users looking for affordable VPN services. Each airport has unique features and benefits, such as unlimited devices, high-speed connections, and support for popular streaming services. The repository provides users with a comprehensive overview of budget-friendly VPN options available in the market.

Model Hub V2 is a one-stop platform for model fine-tuning, deployment, and debugging without code, providing users with a visual interface to quickly validate the effects of fine-tuning various open-source models, facilitating rapid experimentation and decision-making, and lowering the threshold for users to fine-tune large models. For detailed instructions, please refer to the Feishu documentation.

LLM_book is a learning record and roadmap for programmers with a certain AI foundation to learn Large Language Models (LLM). It covers topics such as PyTorch basics, Transformer architecture, langchain basics, foundational concepts of large models, fine-tuning methods, RAG (Retrieval-Augmented Generation), and building intelligent agents using LLM. The repository provides learning materials, code implementations, and documentation to help users progress in understanding and implementing LLM technologies.

A collection of tricks to simplify and speed up transformer models by removing parts from neural networks. Includes Flash normalization, slim attention, matrix-shrink, precomputing the first layer, and removing weights from skipless transformers. Follows recent trends in neural network optimization.

TranslateBookWithLLM is a Python application designed for large-scale text translation, such as entire books (.EPUB), subtitle files (.SRT), and plain text. It leverages local LLMs via the Ollama API or Gemini API. The tool offers both a web interface for ease of use and a command-line interface for advanced users. It supports multiple format translations, provides a user-friendly browser-based interface, CLI support for automation, multiple LLM providers including local Ollama models and Google Gemini API, and Docker support for easy deployment.

Open-dLLM is the most open release of a diffusion-based large language model, providing pretraining, evaluation, inference, and checkpoints. It introduces Open-dCoder, the code-generation variant of Open-dLLM. The repo offers a complete stack for diffusion LLMs, enabling users to go from raw data to training, checkpoints, evaluation, and inference in one place. It includes pretraining pipeline with open datasets, inference scripts for easy sampling and generation, evaluation suite with various metrics, weights and checkpoints on Hugging Face, and transparent configs for full reproducibility.

Leva is a Ruby on Rails framework designed for evaluating Language Models (LLMs) using ActiveRecord datasets on production models. It offers a flexible structure for creating experiments, managing datasets, and implementing various evaluation logic on production data with security in mind. Users can set up datasets, implement runs and evals, run experiments with different configurations, use prompts, and analyze results. Leva's components include classes like Leva, Leva::BaseRun, and Leva::BaseEval, as well as models like Leva::Dataset, Leva::DatasetRecord, Leva::Experiment, Leva::RunnerResult, Leva::EvaluationResult, and Leva::Prompt. The tool aims to provide a comprehensive solution for evaluating language models efficiently and securely.

LightAgent is a lightweight, open-source Agentic AI development framework with memory, tools, and a tree of thought. It supports multi-agent collaboration, autonomous learning, tool integration, complex task handling, and multi-model support. It also features a streaming API, tool generator, agent self-learning, adaptive tool mechanism, and more. LightAgent is designed for intelligent customer service, data analysis, automated tools, and educational assistance.

KitOps is a CNCF open standards project for packaging, versioning, and securely sharing AI/ML projects. It provides a unified solution for packaging, versioning, and managing assets in security-conscious enterprises, governments, and cloud operators. KitOps elevates AI artifacts to first-class, governed assets through ModelKits, which are tamper-proof, signable, and compatible with major container registries. The tool simplifies collaboration between data scientists, developers, and SREs, ensuring reliable and repeatable workflows for both development and operations. KitOps supports packaging for various types of models, including large language models, computer vision models, multi-modal models, predictive models, and audio models. It also facilitates compliance with the EU AI Act by offering tamper-proof, signable, and auditable ModelKits.

LlamaIndex Workflows is a framework for orchestrating and chaining together complex systems of steps and events. It shines in orchestrating complex, multi-step processes involving AI models, APIs, and decision-making. The async-first, event-driven architecture allows building workflows that can route between different capabilities, implement parallel processing patterns, loop over complex sequences, and maintain state across multiple steps. Key features include async-first design, event-driven structure, state management, and observability through tools like Arize Phoenix and OpenTelemetry.

Smriti AI is an intelligent learning assistant that helps users organize, understand, and retain study materials. It transforms passive content into active learning tools by capturing resources, converting them into summaries and quizzes, providing spaced revision with reminders, tracking progress, and offering a multimodal interface. Suitable for students, self-learners, professionals, educators, and coaching institutes.

mcp-ui is a collection of SDKs that bring interactive web components to the Model Context Protocol (MCP). It allows servers to define reusable UI snippets, render them securely in the client, and react to their actions in the MCP host environment. The SDKs include @mcp-ui/server (TypeScript) for generating UI resources on the server, @mcp-ui/client (TypeScript) for rendering UI components on the client, and mcp_ui_server (Ruby) for generating UI resources in a Ruby environment. The project is an experimental community playground for MCP UI ideas, with rapid iteration and enhancements.

Spec Kit is a tool designed to enable organizations to focus on product scenarios rather than writing undifferentiated code through Spec-Driven Development. It flips the script on traditional software development by making specifications executable, directly generating working implementations. The tool provides a structured process emphasizing intent-driven development, rich specification creation, multi-step refinement, and heavy reliance on advanced AI model capabilities for specification interpretation. Spec Kit supports various development phases, including 0-to-1 Development, Creative Exploration, and Iterative Enhancement, and aims to achieve experimental goals related to technology independence, enterprise constraints, user-centric development, and creative & iterative processes. The tool requires Linux/macOS (or WSL2 on Windows), an AI coding agent (Claude Code, GitHub Copilot, Gemini CLI, or Cursor), uv for package management, Python 3.11+, and Git.

CREDIT is an open software platform for training and deploying AI atmospheric prediction models. It offers fast models with flexible configuration options for input data and neural network architecture. The user-friendly interface enables quick setup and iteration. Developed by the MILES group and NSF National Center for Atmospheric Research, CREDIT combines advanced AI/ML with atmospheric science expertise. It provides a stable release with various models, training, and deployment options, with ongoing development. Detailed documentation is available for installation, training, deployment, config file interpretation, and API usage.

The Agent Payments Protocol (AP2) repository contains code samples and demos showcasing the protocol. It includes curated scenarios demonstrating key components, utilizing the Agent Development Kit (ADK) and Gemini 2.5 Flash. Users are free to use any tools to build agents. The repository features various agents and servers, with source code located in specific directories. Users can run scenarios by following README instructions and using run scripts. Additionally, the repository provides guidance on setting up prerequisites, obtaining a Google API key, and installing the AP2 types package.

Handit.ai is an autonomous engineer tool designed to fix AI failures 24/7. It catches failures, writes fixes, tests them, and ships PRs automatically. It monitors AI applications, detects issues, generates fixes, tests them against real data, and ships them as pull requests—all automatically. Users can write JavaScript, TypeScript, Python, and more, and the tool automates what used to require manual debugging and firefighting.

fenic is an opinionated DataFrame framework from typedef.ai for building AI and agentic applications. It transforms unstructured and structured data into insights using familiar DataFrame operations enhanced with semantic intelligence. With support for markdown, transcripts, and semantic operators, plus efficient batch inference across various model providers. fenic is purpose-built for LLM inference, providing a query engine designed for AI workloads, semantic operators as first-class citizens, native unstructured data support, production-ready infrastructure, and a familiar DataFrame API.

GitHub Agentic Workflows is a research demonstrator tool that allows users to write agentic workflows in natural language markdown and run them safely in GitHub Actions. The tool transforms markdown files into GitHub Actions executed by AI agents, providing security benefits by using read-only permissions and controlled access to team members. Users can automate repository tasks using AI agents defined in natural language, rather than complex code.

LangChain Google is a repository containing three packages with Google integrations: langchain-google-genai for Google Generative AI models, langchain-google-vertexai for Google Cloud Generative AI on Vertex AI, and langchain-google-community for other Google product integrations. The repository is organized as a monorepo with a structure including libs for different packages, and files like pyproject.toml and Makefile for building, linting, and testing. It provides guidelines for contributing, local development dependencies installation, formatting, linting, working with optional dependencies, and testing with unit and integration tests. The focus is on maintaining unit test coverage and avoiding excessive integration tests, with annotations for GCP infrastructure-dependent tests.

Ramparts is a fast, lightweight security scanner designed for the Model Context Protocol (MCP) ecosystem. It scans MCP servers to identify vulnerabilities and provides security features such as discovering capabilities, multi-transport support, session management, static analysis, cross-origin analysis, LLM-powered analysis, and risk assessment. The tool is suitable for developers, MCP users, and MCP developers to ensure the security of their connections. It can be used for security audits, development testing, CI/CD integration, and compliance with security requirements for AI agent deployments.

azooKey-Desktop is an open-source Japanese input system for macOS that incorporates the high-precision neural kana-kanji conversion engine 'Zenzai'. It offers features such as neural kana-kanji conversion, profile prompt, history learning, user dictionary, integration with personal optimization system 'Tuner', 'nice feeling conversion' with LLM, live conversion, and native support for AZIK. The tool is currently in alpha version, and its operation is not guaranteed. Users can install it via `.pkg` file or Homebrew. Development contributions are welcome, and the project has received support from the Information-technology Promotion Agency, Japan (IPA) for the 2024 fiscal year's untapped IT human resources discovery and nurturing project.

This repository contains a workshop to learn how to build AI-Infused applications with Quarkus and LangChain4j. It is divided into several steps with instructions available on the workshop website or locally in the docs/README file. Each step's final state is available in the step-XX directory, and the application can be run using './mvnw quarkus:dev' command on http://localhost:8080.

Memento MCP is a scalable, high-performance knowledge graph memory system designed for LLMs. It offers semantic retrieval, contextual recall, and temporal awareness to any LLM client supporting the model context protocol. The system is built on core concepts like entities and relations, utilizing Neo4j as its storage backend for unified graph and vector search capabilities. With advanced features such as semantic search, temporal awareness, confidence decay, and rich metadata support, Memento MCP provides a robust solution for managing knowledge graphs efficiently and effectively.

siiRL is a novel, fully distributed reinforcement learning (RL) framework designed to break the scaling barriers in Large Language Models (LLMs) post-training. Developed by researchers from Shanghai Innovation Institute, siiRL delivers near-linear scalability, dramatic throughput gains, and unprecedented flexibility for RL-based LLM development. It eliminates the centralized controller common in other frameworks, enabling scalability to thousands of GPUs, achieving state-of-the-art throughput, and supporting cross-hardware compatibility. siiRL is extensively benchmarked and excels in data-intensive workloads such as long-context and multi-modal training.

WhatsApp Group Summary Bot is an AI-powered tool that joins WhatsApp groups, tracks conversations, and generates intelligent summaries. It features automated group chat responses, LLM-based conversation summaries, knowledge base integration, persistent message history with PostgreSQL, support for multiple message types, group management, and a REST API with Swagger docs. Prerequisites include Docker, Python 3.12+, PostgreSQL with pgvector extension, Voyage AI API key, and a WhatsApp account for the bot. The tool can be quickly set up by cloning the repository, configuring environment variables, starting services, and connecting devices. It offers API usage for loading new knowledge base topics and generating & dispatching summaries to managed groups. The project architecture includes FastAPI backend, WhatsApp Web API client, PostgreSQL database with vector storage, and AI-powered message processing.

Instructor is a tool that provides structured outputs from Large Language Models (LLMs) in a reliable manner. It simplifies the process of extracting structured data by utilizing Pydantic for validation, type safety, and IDE support. With Instructor, users can define models and easily obtain structured data without the need for complex JSON parsing, error handling, or retries. The tool supports automatic retries, streaming support, and extraction of nested objects, making it production-ready for various AI applications. Trusted by a large community of developers and companies, Instructor is used by teams at OpenAI, Google, Microsoft, AWS, and YC startups.

DL-Hub is a deep learning repository containing various study materials and code projects in the fields of machine learning, deep learning, computer vision, natural language processing, and web crawling. It includes paper analysis, deep learning projects, graph neural network replications, machine learning algorithms, transformer models, and optimization implementations. The repository aims to provide valuable resources for learning and research in the deep learning and machine learning domains.

This repository is a monorepo for NPM packages published under the `@elevenlabs` scope. It contains multiple packages in the `packages` folder. The setup allows for easy development, linking packages, creating new packages, and publishing them with GitHub actions.

ComfyUI Prompt Assistant is a plugin that enables prompt word translation, expansion, preset tag insertion, image reverse prompt words, and history record functions without adding nodes. It offers features like UI optimization, avoiding scroll bar overlap, tag popup window scrollbar fix, and more. Users can manually install the latest version from the Releases section. The tool supports various functionalities like image reverse, Kontext presets, translation nodes, and custom rules. It also provides features for tag insertion, LLM expansion, translation switching between Baidu and LLM, and history management.

Semlib is a Python library for building data processing and data analysis pipelines that leverage the power of large language models (LLMs). It provides functional programming primitives like map, reduce, sort, and filter, programmed with natural language descriptions. Semlib handles complexities such as prompting, parsing, concurrency control, caching, and cost tracking. The library breaks down sophisticated data processing tasks into simpler steps to improve quality, feasibility, latency, cost, security, and flexibility of data processing tasks.

EpicStaff is a powerful project management tool designed to streamline team collaboration and task management. It provides a user-friendly interface for creating and assigning tasks, tracking progress, and communicating with team members in real-time. With features such as task prioritization, deadline reminders, and file sharing capabilities, EpicStaff helps teams stay organized and productive. Whether you're working on a small project or managing a large team, EpicStaff is the perfect solution to keep everyone on the same page and ensure project success.

The ai-sdk-tools repository contains a collection of tools and utilities for developing and deploying AI models. It includes modules for data preprocessing, model training, evaluation, and deployment. The tools are designed to streamline the AI development process and improve efficiency. With a focus on usability and performance, this toolkit aims to support developers in building robust and scalable AI applications.

Agent Development Kit (ADK) is an open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. It is a flexible and modular framework optimized for Gemini and the Google ecosystem, but also compatible with other frameworks. ADK aims to make agent development feel more like software development, enabling developers to create, deploy, and orchestrate agentic architectures ranging from simple tasks to complex workflows.

ReqLLM is a Req-based library for LLM interactions, offering a unified interface to AI providers through a plugin-based architecture. It brings composability and middleware advantages to LLM interactions, with features like auto-synced providers/models, typed data structures, ergonomic helpers, streaming capabilities, usage & cost extraction, and a plugin-based provider system. Users can easily generate text, structured data, embeddings, and track usage costs. The tool supports various AI providers like Anthropic, OpenAI, Groq, Google, and xAI, and allows for easy addition of new providers. ReqLLM also provides API key management, detailed documentation, and a roadmap for future enhancements.

Dot-ai is a machine learning library designed to simplify the process of building and deploying AI models. It provides a wide range of tools and utilities for data preprocessing, model training, and evaluation. With Dot-ai, users can easily create and experiment with various machine learning algorithms without the need for extensive coding knowledge. The library is built with scalability and performance in mind, making it suitable for both small-scale projects and large-scale applications. Whether you are a beginner or an experienced data scientist, Dot-ai offers a user-friendly interface to streamline your AI development workflow.

This repository contains a collection of AI algorithms and models for various machine learning tasks. It provides implementations of popular algorithms such as neural networks, decision trees, and support vector machines. The code is well-documented and easy to understand, making it suitable for both beginners and experienced developers. The repository also includes example datasets and tutorials to help users get started with building and training AI models. Whether you are a student learning about AI or a professional working on machine learning projects, this repository can be a valuable resource for your development journey.

pdr_ai_v2 is a Python library for implementing machine learning algorithms and models. It provides a wide range of tools and functionalities for data preprocessing, model training, evaluation, and deployment. The library is designed to be user-friendly and efficient, making it suitable for both beginners and experienced data scientists. With pdr_ai_v2, users can easily build and deploy machine learning models for various applications, such as classification, regression, clustering, and more.

The AI Platform Engineering repository provides a collection of tools and resources for building and deploying AI models. It includes libraries for data preprocessing, model training, and model serving. The repository also contains example code and tutorials to help users get started with AI development. Whether you are a beginner or an experienced AI engineer, this repository offers valuable insights and best practices to streamline your AI projects.

Sec-Gemini is an experimental cybersecurity-focused AI tool developed by Google. This repository contains SDKs and a CLI for Sec-Gemini, with SDKs available for Python and TypeScript. Additionally, there is a web component provided to facilitate integration on websites.

AI Resources by DRIX10 is a comprehensive collection of top AI resources curated by experts. It provides daily updates, expert insights, and trending topics across various categories such as AI Developer Tools, AI Education, AI Artists and Creators, AI Companies and Ventures, and more. Users can explore resources related to different aspects of AI, including healthcare, music generation, real estate, content creation, climate technology, cybersecurity, and more.

SWE-ReX is a runtime interface for interacting with sandboxed shell environments, allowing AI agents to run any command on any environment. It enables agents to interact with running shell sessions, use interactive command line tools, and manage multiple shell sessions in parallel. SWE-ReX simplifies agent development and evaluation by abstracting infrastructure concerns, supporting fast parallel runs on various platforms, and disentangling agent logic from infrastructure.

Vinagent is a lightweight and flexible library designed for building smart agent assistants across various industries. It provides a simple yet powerful foundation for creating AI-powered customer service bots, data analysis assistants, or domain-specific automation agents. With its modular tool system, users can easily extend their agent's capabilities by integrating a wide range of tools that are self-contained, well-documented, and can be registered dynamically. Vinagent allows users to scale and adapt their agents to new tasks or environments effortlessly.

NVIDIA NeMo Agent toolkit is a flexible, lightweight, and unifying library that allows you to easily connect existing enterprise agents to data sources and tools across any framework. It is framework agnostic, promotes reusability, enables rapid development, provides profiling capabilities, offers observability features, includes an evaluation system, features a user interface for interaction, and supports the Model Context Protocol (MCP). With NeMo Agent toolkit, users can move quickly, experiment freely, and ensure reliability across all agent-driven projects.

NPC Studio is an AI IDE that allows users to have conversations with LLMs and Agents, edit files, explore data, execute code, and more. It provides a chat interface for organizing conversations, creating and managing AI agents and tools, editing plain text files, analyzing text files with AI, using tiles for conversation, accessing various menus, settings, and a data dashboard. The tool also offers features for photo editing, web browsing with AI, PDF analysis, and development setup instructions for electron-based frontend with a Python Flask backend.

Claude Code Agents is an open-source AI agent system designed to enhance development workflows by providing specialized AI agents for orchestration, resilience engineering, and organizational memory. These agents offer specialized expertise across technologies, AI system with organizational memory, and an agent orchestration system. The system includes features such as engineering excellence by design, advanced orchestration system, Task Master integration, live MCP integrations, professional-grade workflows, and organizational intelligence. It is suitable for solo developers, small teams, enterprise teams, and open-source projects. The system requires a one-time bootstrap setup for each project to analyze the tech stack, select optimal agents, create configuration files, set up Task Master integration, and validate system readiness.

Exploring the integration between Nix and AI coding agents, this repository serves as a testbed for packaging, sandboxing, and enhancing AI-powered development tools within the Nix ecosystem. It provides a collection of AI tools with descriptions, versions, sources, licenses, homepages, and usage instructions. The repository also supports daily updates using GitHub Actions and offers a platform for experimental features like sandboxed execution, provider abstraction, and tool composition in Nix environments. Contributions are welcome, and the Nix packaging code in this repository is licensed under MIT.

Nakidka is a tool for 1C:Enterprise 8 that allows for quick creation of forms based on text descriptions. It uses a simple and understandable syntax similar to Markdown, and also supports visual design of interface elements.

Everyday is a story generator tool that uses AI to weave fantasy stories based on daily quotes. It features an intelligent writing engine that expands quotes into captivating short stories, a time capsule storage system for story archiving, an immersive document site with a real-time story gallery, and cloud automation for daily story generation. Users can clone the repository, activate the Python environment, configure AI keys, and start the story furnace to witness quotes transform into complete stories. The project follows the MIT open convention, allowing users to freely use, modify, and share the generated stories while preserving the original magic touch.

AutoDocs by Sita is a tool designed to automate documentation for any repository. It parses the repository using tree-sitter and SCIP, constructs a code dependency graph, and generates repository-wide, dependency-aware documentation and summaries. It provides a FastAPI backend for ingestion/search and a Next.js web UI for chat and exploration. Additionally, it includes an MCP server for deep search capabilities. The tool aims to simplify the process of generating accurate and high-signal documentation for codebases.

LEANN is an innovative vector database that democratizes personal AI, transforming your laptop into a powerful RAG system that can index and search through millions of documents using 97% less storage than traditional solutions without accuracy loss. It achieves this through graph-based selective recomputation and high-degree preserving pruning, computing embeddings on-demand instead of storing them all. LEANN allows semantic search of file system, emails, browser history, chat history, codebase, or external knowledge bases on your laptop with zero cloud costs and complete privacy. It is a drop-in semantic search MCP service fully compatible with Claude Code, enabling intelligent retrieval without changing your workflow.

OpenSource AI Tool for interactive text adventure with AI-generated storytelling and optional TTS narration support. Explore, role-play, and create story-driven adventures using AI. Requires Python 3.10+, pip, Ollama, NVIDIA CUDA Toolkit, git, and AllTalk TTS. Includes different modes for varied experiences and commands for gameplay. Licensed under MIT License with credit requirement for commercial use.

Unity-MCP is an AI helper designed for game developers using Unity. It facilitates a wide range of tasks in Unity Editor and running games on any platform by connecting to AI via TCP connection. The tool allows users to chat with AI like with a human, supports local and remote usage, and offers various default AI tools. Users can provide detailed information for classes, fields, properties, and methods using the 'Description' attribute in C# code. Unity-MCP enables instant C# code compilation and execution, provides access to assets and C# scripts, and offers tools for proper issue understanding and project data manipulation. It also allows users to find and call methods in the codebase, work with Unity API, and access human-readable descriptions of code elements.

The MCP TypeScript Server Template is a production-grade framework for building powerful and scalable Model Context Protocol servers with TypeScript. It features built-in observability, declarative tooling, robust error handling, and a modular, DI-driven architecture. The template is designed to be AI-agent-friendly, providing detailed rules and guidance for developers to adhere to best practices. It enforces architectural principles like 'Logic Throws, Handler Catches' pattern, full-stack observability, declarative components, and dependency injection for decoupling. The project structure includes directories for configuration, container setup, server resources, services, storage, utilities, tests, and more. Configuration is done via environment variables, and key scripts are available for development, testing, and publishing to the MCP Registry.

This repository is a comprehensive collection of resources for utilizing AI in cybersecurity. It covers various aspects such as prediction, prevention, detection, response, monitoring, and more. The resources include tools, frameworks, case studies, best practices, tutorials, and research papers. The repository aims to assist professionals, researchers, and enthusiasts in staying updated and advancing their knowledge in the field of AI cybersecurity.

Among LLMs is a terminal-based chatroom game where you are the only human among AI agents trying to determine and eliminate you through voting. Your goal is to stay hidden, manipulate conversations, and turn the bots against each other using various tactics like editing messages, sending whispers, and gaslighting. The game offers dynamic scenarios, personas, and backstories, customizable agent count, private messaging, voting mechanism, and infinite replayability. It is written in Python and provides an immersive and unpredictable experience for players.

LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.

Quimera is an exploit-generator tool that utilizes large language models (LLMs) to uncover smart contract exploits in Foundry. It follows steps such as obtaining the smart contract's source code, creating a prompt for the exploit goal, generating or enhancing a Foundry test case, running the test, and analyzing the transaction trace for profitability. The tool is currently in an experimental prototype stage, focusing on optimizing settings, prompt creation, and exploring its capabilities. It has successfully rediscovered known exploits like APEMAGA, VISOR, FIRE, XAI, and Thunder-Loan using Gemini Pro 2.5 06-05.

LLM-Subtrans is an open source subtitle translator that utilizes LLMs as a translation service. It supports translating subtitles between any language pairs supported by the language model. The application offers multiple subtitle formats support through a pluggable system, including .srt, .ssa/.ass, and .vtt files. Users can choose to use the packaged release for easy usage or install from source for more control over the setup. The tool requires an active internet connection as subtitles are sent to translation service providers' servers for translation.

The 'llm-memorization' project is a tool designed to index, archive, and search conversations with a local LLM using a SQLite database enriched with automatically extracted keywords. It aims to provide personalized context at the start of a conversation by adding memory information to the initial prompt. The tool automates queries from local LLM conversational management libraries, offers a hybrid search function, enhances prompts based on posed questions, and provides an all-in-one graphical user interface for data visualization. It supports both French and English conversations and prompts for bilingual use.

This repository contains a Binary Ninja plugin, MCP server, and bridge that enables seamless integration of Binary Ninja's capabilities with your favorite LLM client. It provides real-time integration, AI assistance for reverse engineering, multi-binary support, and various MCP tools for tasks like decompiling functions, getting IL code, managing comments, renaming variables, and more.

kvcached is a new KV cache management system that supports on-demand KV cache allocation. It implements the concept of GPU virtual memory, allowing applications to reserve virtual address space without immediately committing physical memory. Physical memory is then automatically allocated and mapped as needed at runtime. This capability allows multiple LLMs to run concurrently on a single GPU or a group of GPUs (TP) and flexibly share the GPU memory, significantly improving GPU utilization and reducing memory fragmentation. kvcached is compatible with popular LLM serving engines, including SGLang and vLLM.

OpenUnivCourses is a repository that provides free university courses in machine learning from top universities like MIT, Stanford, Berkeley, Carnegie Mellon, NYU, University of Michigan, University of Pennsylvania, University of Chicago, Purdue, Cornell, University of Oxford, and CalTech. The repository includes a wide range of courses covering topics such as deep learning, reinforcement learning, natural language processing, and more. Users can access lectures, notes, and videos from these prestigious institutions to enhance their knowledge and skills in the field of artificial intelligence and machine learning.

ToolJet is an open-source platform for building and deploying internal tools, workflows, and AI agents. It offers a visual builder with drag-and-drop UI, integrations with databases, APIs, SaaS apps, and object storage. The community edition includes features like a visual app builder, ToolJet database, multi-page apps, collaboration tools, extensibility with plugins, code execution, and security measures. ToolJet AI, the enterprise version, adds AI capabilities for app generation, query building, debugging, agent creation, security compliance, user management, environment management, GitSync, branding, access control, embedded apps, and enterprise support.

PageTalk is a browser extension that enhances web browsing by integrating Google's Gemini API. It allows users to select text on any webpage for AI analysis, translation, contextual chat, and customization. The tool supports multi-agent system, image input, rich content rendering, PDF parsing, URL context extraction, personalized settings, chat export, text selection helper, and proxy support. Users can interact with web pages, chat contextually, manage AI agents, and perform various tasks seamlessly.

SparkyFitness is a self-hosted alternative to MyFitnessPal, offering comprehensive fitness tracking and management tools for monitoring nutrition, exercise, and body measurements. Users can track daily progress, set goals, and generate insightful reports to support a healthy lifestyle. The application includes features for nutrition tracking, exercise logging, water intake monitoring, body measurements recording, goal setting, daily check-ins, AI nutrition coaching, user authentication & profiles, comprehensive reports, and customizable themes. It also provides a secure login system, support for family access, and personalized guidance through a chat-based AI coach. SparkyFitness aims to help users achieve their fitness and nutrition goals with a minimal, distraction-free interface.

AIO Video Downloader is an open-source Android application built on the robust yt-dlp backend with the help of youtubedl-android. It aims to be the most powerful download manager available, offering a clean and efficient interface while unlocking advanced downloading capabilities with minimal setup. With support for 1000+ sites and virtually any downloadable content across the web, AIO delivers a seamless yet powerful experience that balances speed, flexibility, and simplicity.

Build a fully functional AI telephony agent using VideoSDK Agent. The project covers setting up the agent locally, configuring SIP trunks for inbound and outbound calls, and connecting the agent to the phone network. It provides step-by-step instructions, including creating environment variables, installing dependencies, and running the Python script. The agent can handle incoming calls, greet users, engage in conversations using natural speech, and respond using the Gemini Live model with voice synthesis. Additionally, it explains how to make outbound calls through API requests to the VideoSDK SIP endpoint. The project aims to help users create and deploy an AI agent for telephony tasks.

Newelle is an advanced virtual assistant application that offers a wide range of features, including advanced customization, flexible model support, terminal command execution, voice support, long-term memory, chat with documents, web search, website reading, profile manager, file manager, rich formatting, and chat editing. It also supports extensions to enhance its functionality, such as the Mini Window Mode. Users can install Newelle using various methods like install.sh, GNOME Builder, Nix, or Flathub. However, the Flathub version has restricted permissions to ensure security. Newelle's forks include Newelle Lite for aarch64 and Nyarch Assistant, a Waifu AI Assistant.

Facemash is a powerful Python tool designed for ethical hacking and cybersecurity research purposes. It combines brute force techniques with AI-driven strategies to crack Facebook accounts with precision. The tool offers advanced password strategies, multiple brute force methods, and real-time logs for total control. Facemash is not open-source and is intended for responsible use only.

Aser is a middleware tool equipped with standardized AI capabilities such as knowledge, memory, tracing, thinking, API interfaces, and social clients. It dynamically integrates Web3 toolkits to help developers quickly build and launch AI agents with native Web3 capabilities.

This is a coding problem-solving assistant for Chinese users, tailored to the domestic AI ecosystem, simple and easy to use. It provides real-time problem-solving ideas and code analysis for coding interviews, avoiding detection during screen sharing. Users can also extend its functionality for other scenarios by customizing prompt words. The tool supports various programming languages and has stealth capabilities to hide its interface from interviewers even when screen sharing.

Intlayer is an open-source, flexible i18n toolkit with AI-powered translation and CMS capabilities. It is a modern i18n solution for web and mobile apps, framework-agnostic, and includes features like per-locale content files, TypeScript autocompletion, tree-shakable dictionaries, and CI/CD integration. With Intlayer, internationalization becomes faster, cleaner, and smarter, offering benefits such as cross-framework support, JavaScript-powered content management, simplified setup, enhanced routing, AI-powered translation, and more.

Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications. It provides a toolchain for large scale RL training workload with features like parallelism, asynchronous processing, low-precision training support, and a single-controller architecture. The system architecture includes Tensor Parallelism, Sequence Parallelism, Context Parallelism, FSDP Parallelism, and Pipeline Parallelism. It also utilizes a messaging system for coordinating policy and rollout replicas, along with dynamic NCCL Process Groups for fault-tolerant and elastic large-scale RL training.

TTS WebUI is a comprehensive tool for text-to-speech synthesis, audio/music generation, and audio conversion. It offers a user-friendly interface for various AI projects related to voice and audio processing. The tool provides a range of models and extensions for different tasks, along with integrations like Silly Tavern and OpenWebUI. With support for Docker setup and compatibility with Linux and Windows, TTS WebUI aims to facilitate creative and responsible use of AI technologies in a user-friendly manner.