llm Tools

WeKnora is an open-source platform that turns your raw documents and data into a powerful, queryable knowledge base. It solves the problem of scattered, static information by creating a dynamic system that can answer questions via RAG, reason autonomously, and maintain itself like a wiki. It's built for developers, teams, and organizations who need to unlock the value trapped in their documents and build intelligent knowledge applications.

This repository is a curated collection of extracted system prompts from leading AI models like Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and others. It addresses the problem of opaque AI behavior by revealing the foundational instructions that guide these systems, providing transparency for researchers, developers, and enthusiasts. The collection is regularly updated, serving as a valuable resource for anyone interested in understanding, comparing, or reverse-engineering how these AI models are fundamentally directed to operate.

MathModelAgent是一款专为数学建模竞赛和课程训练设计的AI工具。它通过多智能体协作，自动完成从题目分析、模型建立、代码求解到论文撰写的完整工作流，生成可直接提交的完整论文。它面向参加数学建模竞赛的学生、进行课程训练的师生以及需要快速生成建模论文初稿的研究者，旨在将重复劳动自动化，让用户更专注于策略与创新。

Prompts.chat is a social platform and library for generative AI prompts. It solves the problem of prompt discovery and management by providing a community-driven space to share, find, and organize effective prompts. It's designed for AI enthusiasts, developers, teams, and organizations who want to leverage collective knowledge while maintaining the option for complete privacy through self-hosting.

SIE is an open-source inference server and production cluster that allows developers to run all the models their AI agents need—from embeddings and rerankers to large language models—entirely within their own infrastructure. It solves the problem of vendor lock-in, data privacy concerns, and high costs associated with proprietary model APIs by providing a performant, self-hosted alternative. It's built for teams building production AI agents who require control, data sovereignty, and the ability to compose the best open models.

ODS transforms your personal computer into a powerful, self-hosted AI platform. It solves the problem of privacy, cost, and latency by bringing LLM inference, chat, voice agents, and image generation directly to your local machine. It's ideal for developers, researchers, and privacy-conscious users who want full control over their AI tools without relying on cloud services.

Heretic is a tool that automatically removes built-in censorship and safety restrictions from language models. It ensures AI assistants follow user instructions precisely, rather than refusing requests based on developer-imposed filters. This is for developers, researchers, and power users who need uncensored, directive-following AI for creative, technical, or analytical tasks.

Browser Use provides infrastructure and agents to automate tasks on the web. It solves the problem of making websites accessible and actionable for AI, enabling automation of research, data extraction, and other online workflows. It's for developers and teams building AI agents or automations that need reliable, managed browser interaction.

Ponytail is a ruleset for AI coding agents that enforces a 'lazy senior dev' mindset, drastically reducing over-engineering. It makes your agent stop at the first, simplest working solution—reusing existing code, leveraging standard libraries, and avoiding speculative features. It's for developers who want their AI assistants to produce minimal, maintainable, and robust code without unnecessary complexity.

AI Engineering from Scratch is a comprehensive, open-source curriculum that provides the missing spine for AI education. It solves the problem of scattered, framework-first learning by having you implement every core algorithm—from backprop to transformers—using only math and code, before any libraries are introduced. It's designed for engineers and students who want deep, foundational understanding and the ability to build, debug, and ship AI systems with confidence.

Hermes Agent is a persistent, multi-platform AI assistant that grows with you. It solves the problem of fragmented AI tools by providing a single agent with unified memory that works across Telegram, Discord, Slack, CLI, and more. It's for developers, teams, and power users who need an automated assistant that remembers context, schedules tasks, delegates work, and securely browses the web—all from one intelligent core.

Apache Maka (Incubating) is a local-first workspace designed for developing and operating AI agents. It solves the problem of opaque and unaccountable agent execution by recording all model interactions, tool calls, and decisions into an immutable, append-only log for full auditability. It is built for developers and teams who need transparency, control, and a verifiable history of their AI agent's actions and reasoning.

AI-Infra-Guard is a comprehensive red teaming platform designed to secure modern AI ecosystems. It identifies vulnerabilities across AI agents, skills, MCP servers, underlying infrastructure, and LLM jailbreak risks. This platform is essential for security teams, AI developers, and enterprises deploying AI to ensure their systems are robust and resilient against emerging threats.

Caveman is an AI efficiency platform that automatically optimizes your AI traffic to reduce token usage and costs by up to 65%. It works across Claude, ChatGPT, and Gemini by applying optimizations like caching, compression, and routing, then verifies the savings. It's designed for developers and enterprises looking to significantly lower their AI operational expenses without sacrificing output quality.

This is an open-source book titled 'Deep Understanding of AI Agent: Design Principles and Engineering Practice' by Li Bojie. It provides a systematic guide to the core concepts, design principles, and practical engineering techniques for creating effective AI agents. The repository contains the full book text, compiled PDFs, and chapter-by-chapter example code. It is designed for developers, engineers, and researchers who want to move beyond simple AI models and learn how to architect and implement sophisticated, autonomous agent systems.

oMLX is a macOS-native LLM inference server built for Apple Silicon. It solves the slow, repetitive nature of coding agents by persisting KV cache blocks to SSD, eliminating recomputation and slashing response times from 90 seconds to under 5. It's designed for developers using AI coding tools like Claude Code, Cursor, and OpenClaw who need fast, persistent, and locally managed AI on their Mac.

LLMFit is a tool that helps developers and AI practitioners navigate the vast landscape of hundreds of available large language models and providers. It solves the problem of hardware compatibility by analyzing your system's specifications to instantly identify which models will run efficiently on your machine. This saves significant time and effort spent on trial-and-error installation and configuration. It's designed for anyone from individual developers to teams looking to deploy or experiment with LLMs without worrying about complex hardware constraints.

This is an open-source library of 734 structured cybersecurity skills following the agentskills.io standard. It solves the problem of AI agents lacking domain-specific, actionable cybersecurity knowledge by providing pre-built, framework-mapped workflows. It's designed for developers and security professionals using AI coding assistants like Claude Code, GitHub Copilot, and Cursor to enhance their agents' security capabilities.

MoneyPrinterTurbo is an AI-powered automation tool that creates high-definition short videos from a simple topic or keyword. It solves the problem of time-consuming, skill-intensive video production by automating scriptwriting, asset generation, and editing into a single workflow. It's designed for content creators, marketers, and businesses who need to produce engaging video content quickly and at scale.

Soup is a CLI tool that automates the entire fine-tuning stack for large language models. It solves the complexity of configuring training runs by automatically generating optimal settings, handling data preparation, and enabling training of large models on limited hardware through layer streaming. It's for ML engineers and researchers who want to fine-tune models efficiently without vendor lock-in or manual hyperparameter tuning.

holaOS is an open-source, all-in-one workspace for AI agents. It solves the problem of fragmented AI tools by letting you run any agent (like Claude Code or Codex) across your entire digital environment—100+ integrations, apps, browser, and files—with shared memory for seamless context. It's built for developers and teams who want to centralize their AI workflows, offering built-in models or the flexibility to bring your own keys.