Best AI Tools

FlashMLA is a library of high-performance attention kernels specifically designed to power DeepSeek-V3 and DeepSeek-V3.2 models. It provides optimized implementations for both sparse and dense attention mechanisms during prefill and decoding stages. The library supports advanced features like FP8 KV cache and is compatible with various GPU architectures including SM90 and SM100.

LiteLLM provides a unified interface to interact with over 100 LLM providers using a consistent OpenAI-compatible format. Developers can utilize it as a Python SDK for direct integration or deploy it as a production-ready proxy server. The platform simplifies LLM management by offering features like load balancing, spend tracking, and virtual keys.

Tabby is a self-hosted, open-source AI coding assistant designed as an on-premises alternative to GitHub Copilot. It operates as a self-contained system that does not require external cloud services or database management. The platform supports consumer-grade GPUs and offers an OpenAPI interface for seamless integration with existing development infrastructure.

DeepEP is a high-performance communication library designed for modern machine learning training and inference, specifically focusing on expert parallelism. The library utilizes a lightweight Just-In-Time compilation module and the NCCL Gin backend to deliver high-throughput, low-latency GPU kernels. It supports advanced features like pipeline parallelism and remote memory access while significantly reducing SM resource consumption compared to previous versions.

Khoj is a versatile personal AI application designed to extend your capabilities by integrating with various local and online large language models. It allows users to interact with their personal documents and the internet through a unified interface accessible across multiple platforms. The project is open-source and supports flexible deployment options ranging from private on-device setups to scalable enterprise cloud solutions.

Mano-P is a GUI-VLA agent project designed to enable autonomous, private task execution on edge devices like Mac mini and MacBook. It utilizes advanced reinforcement learning and edge-native inference to perform complex GUI automation, cross-system data integration, and long-task planning. The project provides a secure, local-first solution that eliminates the need for cloud API calls while maintaining high performance across various benchmarks.

PyGWalker transforms pandas DataFrames into an interactive user interface that simplifies data analysis and visualization within Jupyter Notebooks. It integrates the Graphic Walker library to provide a drag-and-drop experience similar to Tableau for exploring and cleaning data. Users can easily create various chart types, apply filters, and perform visual data transformations directly in their existing Python workflow.

DeerFlow is an open-source super agent harness designed to orchestrate sub-agents, memory, and sandboxes for complex task execution. The platform features a ground-up rewrite in version 2.0, offering enhanced extensibility through a modular skill and tool architecture. It supports diverse deployment environments, including local development and Docker-based production setups, with integrated support for multiple messaging channels.

Slime is a specialized post-training framework designed to scale reinforcement learning for large language models. It integrates Megatron-LM for high-performance training with SGLang to provide flexible, efficient data generation workflows. The architecture decouples training and rollout processes, enabling researchers to build and deploy complex agentic RL systems.

PaddleFormers is a Transformers library built on the Baidu PaddlePaddle framework, designed to provide training interfaces and functional experiences for Large Language Models and Vision-Language Models equivalent to Hugging Face. By integrating tensor parallelism, pipeline parallelism, and automatic mixed precision, the project achieves training performance that surpasses Megatron-LM on mainstream models. Furthermore, it fully supports domestic computing chips and is compatible with the Safetensors format, helping developers efficiently complete the entire process from pre-training to post-training.

ROLL is an efficient, user-friendly library designed for scaling reinforcement learning workflows for large language models across large-scale GPU clusters. It supports diverse training paradigms including RLVR, agentic interaction, and distillation, while integrating advanced backends like Megatron-Core, vLLM, and SGLang. The framework provides robust observability and flexible resource management to enhance performance in complex reasoning and human preference alignment tasks.

Xiaomi Miloco is an open-source smart home solution that utilizes on-device large language models to integrate and control IoT devices. By leveraging camera data streams, the system enables natural language interaction for complex home automation and event analysis. It prioritizes user privacy by performing visual understanding and task planning locally on the user's hardware.

This comprehensive guide provides a detailed walkthrough of the Hermes Agent framework developed by Nous Research. It covers core mechanisms like the self-improving learning loop, memory systems, and automated skill evolution across seventeen chapters. The book serves as a practical resource for developers and AI enthusiasts looking to implement and customize their own intelligent agents.

OpenOcta is a fully self-developed enterprise-grade AI Agent runtime and control plane that uses a single Go binary to encapsulate the backend and embedded frontend. The project supports intelligent conversation, process automation, and deep integration with business systems, APIs, and toolchains. Users can quickly deploy and connect to internal business systems via CLI, HTTP, or WebSocket.

Secret Llama is an entirely in-browser chatbot that allows users to run open-source models like Llama 3 and Mistral locally. Because the application operates directly within the browser, all conversation data remains private and no server installation is required. The platform provides a user-friendly interface that functions offline while leveraging WebGPU technology for performance.

KittenTTS is an open-source, lightweight text-to-speech library designed for efficient voice synthesis on CPUs. It offers multiple model sizes ranging from 15M to 80M parameters, ensuring high-quality 24 kHz audio output with minimal disk footprint. The library includes built-in text preprocessing and supports adjustable speech speeds for versatile integration.

ERNIE-Image is an open-source text-to-image model developed by Baidu based on the Diffusion Transformer (DiT) architecture. The model is equipped with a lightweight prompt enhancer that transforms short inputs into structure-rich descriptions, achieving industry-leading generation results at an 8B parameter scale. It excels at handling complex text rendering, multi-object layout, and instruction-following tasks, while supporting efficient deployment on consumer-grade GPUs.

FastDeploy is an inference deployment toolkit for large language models and vision-language models based on PaddlePaddle, designed to provide out-of-the-box production-grade deployment solutions. This tool supports various mainstream hardware platforms and integrates load-balanced PD separation, unified KV cache transmission, and multiple advanced acceleration technologies. Developers can achieve rapid deployment through OpenAI API-compatible interfaces and optimize inference performance using full quantization format support.

RTP-LLM is a high-performance LLM inference acceleration engine developed by the Alibaba Foundation Model Inference team. This engine has been widely applied in various Alibaba business scenarios such as Taobao and Tmall, supporting multiple mainstream model formats and hardware backends. It provides efficient production-level services for large language models by integrating advanced operator optimization, quantization techniques, and distributed inference capabilities.

Khazix Skills is an open-source collection of AI skills and prompts designed to improve Agent efficiency through structured instructions. The project includes practical tools such as neat-freak, hv-analysis, and khazix-writer, supporting various Agent platforms like Claude Code and Codex. These tools are derived from the author's real-world project experience and effectively solve common problems such as documentation alignment, deep research, and stylized writing.

Index-AniSora is a powerful open-source framework designed specifically for high-quality anime video generation and animation production. The system features a comprehensive data processing pipeline, a controllable generation model with spatiotemporal masking, and a specialized evaluation benchmark. It supports diverse creative tasks including character 3D generation, video style transfer, and multimodal guidance for precise motion control.

The Willow Inference Server allows users to self-host high-speed language inference tasks for various applications. It supports essential features including speech-to-text, text-to-speech, and large language model processing. Users can access official documentation and community support through the project's website and GitHub discussions.

This project successfully restored the complete source code of Claude Code version 2.1.88 by parsing legacy source map files from the npm package. Developers can use this to deeply study the CLI tool's command system, the terminal UI built with React and Ink, and the implementation of the MCP protocol. This project aims to provide a reference for learning and analyzing the internal architecture of Claude Code, intended solely for technical research and archiving.

ArcReel is an open-source AI video generation workbench that implements an automated pipeline from novel scripts to finished videos via a multi-agent architecture. The platform supports integration with various providers including Gemini, Volcengine Ark, Grok, and OpenAI, offering character consistency maintenance and narrative tracking features. Users can manage projects, track costs, and export Jianying drafts through a visual interface to achieve efficient AI-assisted video creation.

ZhangXuefeng.skill is a cognitive operating system built on deep research, designed to provide an executable thinking framework rather than a simple collection of quotes. By distilling core mental models, decision heuristics, and communication DNA, the project helps users analyze major selection and career planning from Zhang Xuefeng's perspective. Users can install this skill to obtain targeted decision-making advice and in-depth analysis within Claude Code.

TorchEasyRec is a PyTorch-based framework designed for developing production-ready deep learning recommendation models. It supports a wide range of tasks including candidate generation, ranking, multi-task learning, and generative recommendation. The framework offers high scalability, flexible data source integration, and seamless deployment options for real-world production environments.

superpowers-zh is a Chinese enhanced project that provides systematic working methodologies for 17 mainstream AI coding tools. Building on the full localization of 14 core upstream skills, it adds 6 specialized skills designed for Chinese developers. Through a unified installation command, developers can easily configure field-tested development workflows for tools like Claude Code and Cursor.

Awesome DeepSeek Agent is a curated collection of guides for integrating DeepSeek models into various AI coding assistants and agentic tools. Each guide provides step-by-step instructions for installation, configuration, and initial setup to ensure a smooth user experience. Developers can quickly enable DeepSeek-V4-Pro or DeepSeek-V4-Flash within their preferred terminal or editor environments.

This tutorial provides a comprehensive guide for users to build an AI work assistant from scratch, covering installation, configuration, core features, and advanced techniques. The content is proofread based on the stable OpenClaw v2026.4.14 version and offers multiple deployment options to meet various scenario requirements. Through rich practical cases and detailed command cheat sheets, it helps users achieve a significant boost in personal efficiency.

This repository gathers 49 verified real-world use cases for OpenClaw personal AI agents, designed to help users improve work and life efficiency through automation. The content covers a wide range of applications from domestic ecosystem adaptation to international general scenarios, providing detailed configuration guides and reproducible prompts. Whether you are a beginner or a developer, you can quickly get started and build your own AI agents through these structured cases.

Tong Jincheng.skill is a Claude Code plugin built upon approximately 200,000 words of primary source material, designed to analyze interpersonal relationships and emotional issues through the perspective of Tong Jincheng. It is not a simple repeater of quotes, but rather helps users gain insight into human nature in a straightforward and pragmatic way by extracting his core cognitive framework. By simulating his unique thinking logic, this tool provides users with decision-making inspiration regarding dating, social interaction, and personal growth.

This project provides a systematic and beginner-friendly tutorial in Chinese, covering the official Anthropic programming tool Claude Code and the open-source AI assistant framework OpenClaw. The tutorial includes 25 in-depth guides, over 70 runnable code examples, and more than 170 FAQs, aiming to help developers quickly master AI programming and automated workflows. The content stays up-to-date with the latest versions, using dual learning paths to help users advance from zero-based knowledge to enterprise-level practical applications.

OpenClaw 101 is an open-source resource aggregation site specifically designed for the OpenClaw AI personal assistant platform. The project includes over 35 high-quality tutorials in both Chinese and English covering deployment, integration, and skill development. Users can quickly master the development and application of AI assistants through a systematic 7-day learning path and multi-dimensional filtering features.

Sandcastle is a TypeScript library designed to orchestrate AI coding agents within isolated, secure sandbox environments. It supports multiple providers including Docker, Podman, and Vercel to manage agent execution and branch strategies effectively. The library simplifies complex workflows by handling sandbox lifecycles, git worktrees, and automated commit merging.

Browser Harness provides a direct connection between LLMs and your browser using a thin, editable CDP interface. The system allows agents to write and improve their own helper functions during execution to handle complex tasks. Users can leverage this framework to automate browser workflows while building a library of reusable, agent-generated domain skills.

vLLM Kunlun is a community-maintained hardware plugin that enables the seamless execution of vLLM on Kunlun XPU hardware. It utilizes a hardware-pluggable interface to decouple the integration process, ensuring compatibility with a wide range of open-source models. The project supports various architectures including Transformer-based, Mixture-of-Expert, and multi-modal LLMs on the Kunlun3 P800 platform.

Warp is an agentic development environment that integrates advanced AI capabilities directly into the terminal experience. Users can leverage a built-in coding agent or bring their own preferred CLI agents to streamline their development workflows. The project is open source and actively encourages community contributions through a structured issue-to-PR process.

AI Daily Digest is an automated tool that scrapes top technical blogs from Hacker News and uses AI for multi-dimensional scoring and summary generation. It supports quick article filtering via command line or interactive interface and automatically summarizes macro trends in the tech circle. The project is written in pure TypeScript and supports Gemini as well as various OpenAI-compatible API models.

Graphify is an AI coding assistant skill that builds a comprehensive knowledge graph from your codebase, documentation, and multimedia files. It uses deterministic AST extraction for code and parallel subagents for conceptual analysis to map relationships without relying on embeddings. The resulting interactive graph and audit reports provide developers with deep architectural insights and efficient navigation across complex projects.

GitNexus indexes codebases into a comprehensive knowledge graph to provide AI agents with deep architectural context. It offers a CLI tool for local repository analysis and an MCP server to integrate this intelligence directly into editors like Cursor and Claude Code. Additionally, the project includes a web-based visual explorer for quick repository analysis and interactive chat.

RTK is a high-performance CLI proxy that filters and compresses command outputs to significantly reduce LLM token consumption. It supports over 100 common commands and integrates seamlessly with major AI coding tools through transparent shell hooks. By removing noise and summarizing data, it helps developers maintain context while minimizing costs and latency.

CorridorKey is a neural network-based tool designed to solve the complex problem of unmixing foreground subjects from green or blue screen backgrounds. It reconstructs the true straight color and linear alpha channel for every pixel, effectively preserving fine details like hair and motion blur. The project supports high-fidelity VFX workflows by outputting 16-bit and 32-bit Linear float EXR files compatible with industry-standard compositing software.

Symphony transforms project tasks into isolated, autonomous implementation runs to streamline development workflows. It enables teams to manage high-level work objectives rather than directly supervising individual coding agents. The system provides comprehensive proof of work, including CI status, PR reviews, and complexity analysis, to ensure safe code delivery.

The Pi Monorepo provides a comprehensive suite of tools designed for building and managing AI agents. It includes packages for unified LLM API access, agent runtimes, and interactive coding CLI interfaces. The project also encourages sharing open-source coding sessions to improve agent performance on real-world tasks.

Context Mode is an MCP server designed to prevent context window exhaustion by offloading raw data into a sandboxed SQLite database. It tracks session events and uses BM25 retrieval to ensure the AI agent retains relevant information even after conversation compaction. Additionally, it enforces terse output patterns and promotes code-based analysis to significantly reduce token consumption.

Free Claude Code acts as an Anthropic-compatible proxy that allows developers to route Claude Code CLI and IDE traffic through various alternative providers. It supports multiple backends including NVIDIA NIM, OpenRouter, DeepSeek, and local models via Ollama or llama.cpp. The tool also features optional Discord and Telegram bot integrations for remote coding sessions and voice-note transcription.

code-review-graph builds a structural map of your codebase using Tree-sitter to provide AI assistants with precise, context-aware information. By tracking changes incrementally and calculating the blast radius of modifications, it significantly reduces token consumption during code reviews. The tool integrates seamlessly with various AI coding platforms via the Model Context Protocol to ensure only relevant code is analyzed.

Multica is an open-source platform designed to integrate coding agents into software development teams as autonomous, first-class teammates. It enables users to assign tasks, track progress, and manage agent workflows through a unified dashboard that supports various popular coding agent runtimes. By facilitating human-agent collaboration, the system allows small teams to scale their productivity by multiplexing tasks across both human and AI contributors.

This collection provides modular, composable agent skills designed to improve software engineering workflows and reduce common AI coding failures. The tools focus on core principles like alignment, shared domain language, and rigorous feedback loops to prevent codebase entropy. These skills are easily installed and adaptable, allowing developers to integrate professional engineering practices directly into their coding agents.

AionUi is a comprehensive open-source platform that enables AI agents to work alongside users by performing file operations, code execution, and task automation. The application features a built-in agent engine with zero-setup requirements and supports integration with over 20 AI platforms and various CLI tools. Users can manage complex workflows through a unified interface that includes remote access, scheduled automation, and multi-agent team collaboration.

jcode is a high-performance coding agent harness designed for multi-session workflows and extreme resource efficiency. It features a sophisticated memory system that uses semantic vector embeddings to recall relevant information without excessive token usage. The platform supports native agent collaboration through a swarm architecture and integrates with a wide range of LLM providers via OAuth or custom configurations.

Craft Agents is an open-source, agent-native desktop application designed to provide an intuitive and document-centric interface for interacting with powerful AI models. It supports seamless integration with various APIs, MCP servers, and local filesystems, allowing users to connect services without complex configuration files. The platform features a robust session management system, multi-provider LLM support, and a headless server mode for advanced remote workflows.

Career-Ops is an open-source, agentic system designed to transform your job search into a structured, AI-driven pipeline. It enables users to automatically evaluate job listings, generate tailored ATS-optimized resumes, and track applications through a centralized terminal dashboard. By leveraging AI agents to filter and analyze opportunities, the tool helps candidates focus their time on the most promising roles.

PPT Master is an open-source tool that converts documents like PDFs, DOCX files, and URLs into fully editable PowerPoint presentations. Unlike image-based AI tools, it generates native DrawingML shapes, text boxes, and charts that users can modify directly in PowerPoint. The workflow integrates with AI IDEs to provide a local, privacy-focused solution for creating professional decks.

Browserbase Skills provides a comprehensive suite of tools designed to integrate browser automation capabilities directly into Claude Code. The collection includes utilities for web interaction, CLI-based platform management, and advanced debugging features like site analysis and trace capturing. Developers can easily install these skills to enable AI agents to perform complex tasks such as authenticated browsing, UI testing, and serverless function deployment.

Agent Skills provides a structured library of engineering workflows designed to help AI coding agents follow professional best practices throughout the software development lifecycle. These 20 modular skills cover everything from initial specification and planning to testing, security, and production deployment. By enforcing rigorous quality gates and anti-rationalization checks, the project ensures that AI-generated code meets the standards of senior engineering teams.

Impeccable is a comprehensive design skill and command suite designed to guide AI agents toward superior frontend UI development. It provides 23 specialized commands and curated anti-patterns to help developers avoid common design mistakes like generic templates and poor accessibility. The project supports a wide range of AI coding tools and includes a standalone CLI for detecting design issues across your codebase.

Obsidian-skills provides a collection of specialized tools designed to integrate Obsidian functionality with compatible AI agents. These skills adhere to the Agent Skills specification, enabling seamless interaction with platforms like Claude Code and Codex CLI. Users can install these tools via marketplace plugins, npx, or manual directory configuration to enhance their automated workflows.

Awesome Agent Skills is a curated repository featuring over 1,100 real-world agent skills developed by leading engineering teams and the community. Unlike bulk-generated alternatives, this collection provides high-quality, hand-picked resources for building and optimizing AI agents. It offers broad compatibility with major development tools and platforms, including Claude Code, Gemini CLI, and GitHub Copilot.