Claude SEO is a free, open‑source plugin for Claude Code that performs a comprehensive SEO audit of any website in roughly ten to fifteen minutes by launching up to seventeen parallel specialist agents drawn from a pool …
→ View original sourceFree Claude Code (FCC) is an open-source project enabling users to access 61 ToS-compliant providers with over 1.3 billion free tokens monthly through a unified interface. It supports 12 coding agents (e.g., Claude Code,…
→ View original sourceGemini CLI is an open‑source terminal client that provides direct access to Gemini models via npm; users can install it globally with `npm install -g @google/gemini-cli` inside a Conda environment that includes Node.js, …
→ View original sourceThe luongnv89/claude-howto repository provides a structured, 10-module tutorial guide for Claude Code v2.1.302 (October 2026) that teaches developers to orchestrate slash commands, persistent memory (CLAUDE.md), auto-inv…
→ View original sourceTwenty is an open‑source, code‑driven CRM platform built with a modern TypeScript stack that includes Nx for monorepo management, NestJS powered by BullMQ for queueing, PostgreSQL for data persistence, and Redis for cach…
→ View original sourceImpeccable is a design skill framework for AI coding agents, offering a single setup flow and 24 commands to guide frontend design decisions. It begins with `/impeccable init`, which inspects the project and writes `PROD…
→ View original sourceHeadroom is an open-source tool that compresses all data sent to AI agents and LLMs—including prompts, tool outputs, logs, RAG chunks, and conversation history—before transmission, reducing token usage by up to 57% in be…
→ View original sourceARTEMIS is Google’s open‑source mobile automation framework that lets AI assistants and test suites drive real Android devices through natural‑language instructions. The system provides two execution profiles: **Flash** …
→ View original sourceai-memory is a self‑contained Rust binary that gives AI coding agents a persistent, shared memory built on a git‑backed Markdown wiki. Lifecycle hooks automatically capture prompts, tool calls and session boundaries, san…
→ View original sourceOrca is an AI orchestration platform enabling developers to run multiple AI coding agents (e.g., Codex, ClaudeCode, OpenCode, Pi) in isolated git worktrees, tracked centrally. It supports real-time monitoring and remote …
→ View original sourceMicrosoft’s BitNet repository introduces bitnet.cpp, an optimized inference engine for 1.58‑bit (ternary) large language models that runs on CPUs and GPUs. The framework supplies parallel kernels with configurable tiling…
→ View original sourceOpen WebUI is a self‑hosted, extensible AI platform designed to run entirely offline while providing a provider‑agnostic interface for both local Ollama models and any OpenAI‑compatible API (e.g., LMStudio, GroqCloud, Mi…
→ View original sourceVoxCPM2 is a 2‑billion‑parameter tokenizer‑free text‑to‑speech system that generates speech directly in the latent space of AudioVAE V2 through a diffusion‑autoregressive pipeline (LocEnc → TSLM → RALM → LocDiT). Trained…
→ View original sourcePaperclip is an open‑source Node.js server with a React UI that orchestrates teams of AI agents into a controllable organization. It treats each agent as an employee, letting users define business‑level goals, hire agent…
→ View original sourcePyTorch provides a tensor computation library with GPU acceleration and a tape-based automatic differentiation system for dynamic neural network construction. Its core components include torch for tensor operations, torc…
→ View original sourceThe 🤗 Transformers library provides a centralized model‑definition framework that supports text, computer‑vision, audio, video, and multimodal models for both inference and training. It enables a single model definition …
→ View original sourceLingBot‑Map introduces a feed‑forward 3D foundation model for streaming reconstruction that centers on a Geometric Context Transformer (GCT) which jointly grounds coordinates, integrates dense geometric cues, and correct…
→ View original sourcePPT Master is an open‑source Python workflow that turns source documents—PDFs, DOCX, web pages, images or raw text—into natively editable PowerPoint (.pptx) files by driving any agent‑capable AI tool (e.g., Claude Code, …
→ View original sourceOpenUI is a full-stack, framework-agnostic Generative UI framework centered on OpenUI Lang, a compact, streaming-first language that reduces token usage by up to 67% compared to JSON formats. The framework supports React…
→ View original sourceThe repository bojieli/ai-agent-book provides an open‑source, multilingual textbook that structures AI agents around the core formula Agent = LLM + context + tools. Spanning ten chapters, it progresses from foundational …
→ View original sourceOpen Code Review (OCR) is an open‑source CLI tool that performs AI‑assisted code reviews by combining deterministic engineering steps with a language‑model‑driven agent. It reads Git diffs, bundles related files, and sen…
→ View original sourceWorldMonitor is a real‑time global intelligence dashboard that aggregates news, geopolitical events, and infrastructure data into a unified situational‑awareness interface. It uses a dual map engine— a 3D globe rendered …
→ View original sourcevideo-shotcraft is an AI agent skill developed by Vincentwei1021 that transforms Claude Code or Codex into a motion-design studio for creating cinematic product videos using Remotion. The toolkit includes 157 shot recipe…
→ View original sourceThe Cua project equips AI agents with full desktop environments and automation tools across macOS, Windows, and Linux. Cua Spaces launches a local virtual machine—either a macOS VM built on Apple Silicon, a Linux image, …
→ View original sourceOllama provides a local runtime for large language models, distributable as a Docker image (ollama/ollama) or via a shell install script (curl -fsSL https://ollama.com/install.sh \| sh). Models are managed through the CL…
→ View original sourceFreeLLMAPI consolidates the free tiers of 34 LLM providers into a single OpenAI‑compatible /v1 endpoint, offering access to 635 free model endpoints spread across 474 model families and delivering roughly 7.4 billion tok…
→ View original sourcePrompt Optimizer is a cross‑platform AI‑prompt engineering tool that lets users create, test, and refine prompts for text and image generation models. It can be run as a web app, desktop application, Chrome extension, or…
→ View original sourcegstack is an open‑source MIT‑licensed collection of slash‑command skills that turn Claude Code into a virtual engineering team of 23 specialist roles (CEO, eng manager, designer, reviewer, QA lead, security officer, rele…
→ View original sourceClaude‑Mem is a persistent memory system for Claude Code that automatically records tool usage observations, creates semantic summaries, and makes them available in later sessions so the model retains project knowledge a…
→ View original sourceAgent Reach is a capability layer that equips AI agents with ready‑to‑use internet access by automatically selecting, installing, and maintaining the most reliable backend for each supported platform. Zero‑configuration …
→ View original sourceThe ComposioHQ awesome-claude-skills repository curates over 1,000 production‑ready Claude Skills and Plugins that enable AI agents such as Claude.ai, Claude Code, OpenAI Codex, Cursor, Gemini CLI, Antigravity and Windsu…
→ View original sourceiFixAi is an open‑source auditing framework that evaluates AI agents against business‑relevant KPIs by running a suite of automated inspections and producing an A–F letter grade. The core assessment consists of 32 inspec…
→ View original sourceFirecrawl provides a unified web‑data API that enables searching, scraping, and interactive navigation of websites at scale. The service claims 96% coverage of the public web, including JavaScript‑heavy pages, and report…
→ View original sourcePageIndex introduces a vectorless, reasoning‑based retrieval‑augmented generation system that replaces the usual vector index with a hierarchical tree index built from document layout. In local mode the SDK’s “Flash” ind…
→ View original sourceThe alirezarezvani/claude-skills repository publishes 388 production‑ready skill packages that extend 13 AI coding agents—Claude Code, OpenAI Codex, Gemini CLI, OpenClaw, Hermes Agent, Mistral Vibe, Cursor, Aider, Windsu…
→ View original sourceDBX is a ~25 MB, single‑binary database client that works with over 100 engines including MySQL, PostgreSQL, SQLite, DuckDB, ClickHouse, Oracle, MongoDB, Redis, Kafka‑family brokers, and vector stores such as Milvus and …
→ View original sourceAIRI is an open‑source project that recreates the Neuro‑Sama AI VTuber using a stack of web technologies—WebGPU, WebAudio, Web Workers, WebAssembly, and WebSocket—for rendering, animation, and communication, while the de…
→ View original sourceMicrosoft's Data Formulator is an AI‑agent‑driven workspace that lets analysts load, query, and visualize data from disparate sources while preserving context through a data memory and branching Data Threads. The tool co…
→ View original sourceMoneyPrinterTurbo is an open‑source Python tool that automates short‑video creation from a text theme or keyword. It generates a script, derives search keywords, retrieves matching stock clips (from Pexels, Pixabay, Cove…
→ View original sourceOpenClaw is an open‑source AI assistant that runs locally on a user’s machine and connects to messaging platforms such as Discord, iMessage, Slack, Teams, Telegram, WhatsApp, Google Chat, Signal and over 20 additional se…
→ View original sourceStrix is an open‑source AI‑driven penetration‑testing platform that runs autonomous agents inside a Docker sandbox to discover, validate, and remediate application vulnerabilities. Users install the tool with a single cu…
→ View original sourceOpenCode is an open-source AI coding agent distributed via multiple package managers including npm (opencode-ai@latest), Homebrew (anomalyco/tap/opencode and official formula), Scoop, Chocolatey, pacman, AUR, mise, and N…
→ View original sourceHumanizer-zh is a Chinese localization of the Humanizer library, designed as a Claude Code Skill to remove AI-generated traces from text. Created by GitHub user op7418, it aims to make AI-generated content appear more hu…
→ View original sourceThe "ai-engineering-from-scratch" repository by rohitg00 is a comprehensive, open-source curriculum designed to bridge the professional gap in AI tool proficiency through hands-on technical implementation. Spanning 20 ph…
→ View original sourceComfyUI is a modular, node-based AI creation engine designed for visual professionals to generate images, video, audio, 3D models, and text. Utilizing a visual graph interface, the system supports complex, reusable workf…
→ View original sourceStagehand is an open-source SDK developed by Browserbase designed to facilitate the creation of autonomous browser agents across TypeScript, Python, and Go. The framework provides high-level abstractions—specifically obs…
→ View original sourceThe "claude-code-templates" repository by davila7 provides a comprehensive framework of ready-to-use configurations designed to extend the capabilities of Anthropic's Claude Code. The project offers an expansive ecosyste…
→ View original sourceCLIProxyAPI is an open-source proxy server designed to provide OpenAI, Gemini, Claude, Codex, and Grok compatible API interfaces for command-line interfaces (CLI). It enables users to access various large language models…
→ View original sourceBend is a new programming language designed for a post-AGI economy, focusing on high-performance execution and verifiable correctness through formal proofs. Built on affine dependent type theory, the language utilizes st…
→ View original sourceUniver is an open-source, high-performance Office SDK designed to enable the creation of customizable productivity applications, such as spreadsheets, documents, and presentations, within third-party products. Built with…
→ View original sourceProject NOMAD is an offline-first, self-contained knowledge and education server designed to provide critical tools and AI capabilities without an internet connection. Orchestrated via a Docker-based management UI called…
→ View original sourceThis repository provides a complete implementation of a Transformer-based Large Language Model (LLM) using pure PyTorch, covering the entire pipeline from raw text pretraining to post-training alignment. The architecture…
→ View original sourceAnthropic has released a comprehensive repository of reference agents, skills, and data connectors designed to automate complex financial services workflows, including investment banking, equity research, private equity,…
→ View original sourceAnthropic has open-sourced 11 "knowledge-work-plugins" designed to transform Claude into a role-specific specialist for Claude Cowork and Claude Code. These plugins function by bundling domain-specific skills, slash comm…
→ View original sourceCactus Compute has introduced Needle, a foundation model specifically engineered for resource-constrained environments like microcontrollers, wearables, and robotics. The flagship Needle 3 architecture utilizes a Laddere…
→ View original sourceDocling is an open-source document parsing framework developed by IBM Research Zurich and hosted under the LF AI & Data Foundation. It is designed to facilitate the ingestion of diverse file formats—including PDF, DO…
→ View original sourceOpenCreator (formerly KrillinAI) is a multimodal creative workspace designed for local execution, integrating visual creator tools, reusable Skills, and AI Agents. Built with a React-based frontend and a Fastify-powered …
→ View original sourceFission-AI has released OpenSpec, an artifact-guided workflow designed to bring predictability to AI-driven development by establishing a lightweight specification layer. Unlike traditional heavyweight frameworks, OpenSp…
→ View original sourceSupermemory is an advanced memory and context engine designed to provide AI agents with persistent, evolving knowledge. Unlike stateless RAG systems, Supermemory utilizes a specialized memory engine that extracts facts f…
→ View original sourceVercel Labs has introduced json-render, a generative UI framework designed to transform natural language prompts into dynamic, personalized interfaces through a constrained JSON specification. To ensure reliability and p…
→ View original sourceGraphify-Labs has released graphify, a tool designed to map entire software projects—including code, documentation, PDFs, images, and video—into a queryable knowledge graph. Unlike traditional vector-based RAG systems, g…
→ View original sourceCline is an open-source AI coding agent ecosystem designed to operate across IDEs (VS Code and JetBrains), terminals, and desktop environments (macOS and Windows). The system functions by analyzing project structures and…
→ View original sourcen8n is a fair-code, AI-native automation platform designed to facilitate the construction and operationalization of complex AI workflows and multi-step agents. The platform utilizes a visual canvas that allows users to i…
→ View original sourceSupabase is an open-source development platform designed to provide a Firebase-like experience by aggregating several enterprise-grade tools centered around a hosted PostgreSQL database. The architecture leverages a modu…
→ View original sourceLibreChat has released version v0.8.8-rc4, introducing significant enhancements to its agentic workflows and architectural reliability. Key updates include the implementation of a Public Agents API that serves OpenAPI sp…
→ View original sourceVoicebox is an open-source, local-first AI voice studio designed as a comprehensive alternative to cloud services like ElevenLabs and WisprFlow. Built with Tauri (Rust) and a FastAPI Python backend, the platform provides…
→ View original sourceThe earendil-works/pi project is a modular agent harness designed to facilitate the development and execution of self-extensible coding agents. The ecosystem is composed of several specialized TypeScript packages, includ…
→ View original sourceThe ai-job-search framework is an open-source, AI-powered job application assistant built to run locally using Claude Code. Designed to automate a structured workflow—comprising self-profiling, job scraping, fit evaluati…
→ View original sourceThe "awesome-llm-apps" repository by Shubhamsaboo is an expansive open-source collection featuring over 100 hand-built AI agents, agent skills, and Retrieval-Augmented Generation (RAG) applications. Licensed under Apache…
→ View original sourcePascal is an open-source, local-first 3D building editor built with React Three Fiber and WebGPU, utilizing a Turborepo monorepo architecture. The system is designed for high-performance architectural modeling, featuring…
→ View original sourceThe book-to-skill tool is a Python-based utility designed to transform technical books, document folders, or structured prose into optimized "Agent Skills" compatible with the open Agent Skills standard. By converting so…
→ View original sourcellm_wiki is a cross-platform desktop application built with Tauri v2 and React 19 that transforms static documents into a persistent, self-maintaining knowledge base. Moving beyond standard RAG, the system implements a t…
→ View original sourceTensorFlow is an expansive, open-source end-to-end machine learning platform originally engineered by Google Brain's Machine Intelligence team for advanced neural network research and application deployment. The framewor…
→ View original sourcePentagi, developed by vxcontrol, is an open-source, fully autonomous multi-agent AI system engineered to execute complex penetration testing tasks. Built primarily using Golang and React, the framework utilizes advanced …
→ View original sourceOmniRoute is an open-source, MIT-licensed gateway designed to aggregate and manage diverse AI provider free tiers through a unified, OpenAI-compatible interface. The system catalogs 489 free-tier entries across 35 recurr…
→ View original sourceContext window optimization for AI coding agents that reduces tool output by 98% through sandboxing, persists session memory, and enforces routing across 17 platforms using MCP and hooks. Read original
→ View original sourceOpenAI has released a skills catalog designed for Codex. This repository serves as a resource for managing and implementing specific capabilities within the Codex model. Read original
→ View original sourceTencent has developed WeKnora, an open-source, LLM-powered framework designed for enterprise document understanding, semantic retrieval, and reasoning. The system integrates three core functional modes: RAG-based Q&A…
→ View original sourceBrowser-use is an open-source framework available in Python and TypeScript designed to enable AI agents to autonomously control web browsers. The library facilitates complex web automation tasks, such as booking appointm…
→ View original sourceThe "mcp-for-blender" project (formerly blender-mcp) enables two-way communication between Blender and Large Language Models (LLMs) via the Model Context Protocol (MCP). The architecture utilizes a Python-based MCP serve…
→ View original sourceSGLang is a high-performance, open-source serving framework designed for low-latency and high-throughput inference of large language models (LLMs) and multimodal models. The engine utilizes advanced techniques such as Ra…
→ View original sourceAnthropic has released a repository containing implementations of "skills" for Claude, a system designed to enhance the model's performance on specialized tasks through dynamic loading of instructions, scripts, and resou…
→ View original sourceClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows through natural lang…
→ View original sourceRuFlo is an agent meta-harness designed to extend the capabilities of Claude Code and Codex by providing an execution layer for complex AI orchestration. Built on a Rust-based engine, the framework transforms static mode…
→ View original sourceImbad0202/academic-research-skills is an open-source suite of Claude Code skills designed to augment the academic research pipeline through a human-in-the-loop framework. Rather than automating authorship, the tool addre…
→ View original sourceNVIDIA has introduced SkillSpector, an open-source security scanner designed to vet AI agent skills—such as those used by Claude Code and Gemini CLI—before installation. Addressing the high risk of implicit trust in thes…
→ View original sourceCC Switch is a cross-platform desktop management application developed using Tauri 2 to unify the configuration of nine AI-powered coding tools, including Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenC…
→ View original sourceThe GitHub project minimind by jingyaogong demonstrates training a 64M-parameter large language model (LLM) from scratch in approximately 2 hours. This Python-based implementation highlights efficient model training tech…
→ View original sourceThe llama.cpp project provides a high-performance C/C++ implementation designed for efficient Large Language Model (LLM) and Vision Language Model (VLM) inference across diverse hardware architectures. Built upon the ggm…
→ View original sourceHeretic is an automated tool designed to remove safety alignment from transformer-based language models without the need for expensive post-training. It implements an advanced version of directional ablation (abliteratio…
→ View original sourceCrawl4AI is an open-source, high-performance web extraction framework designed to convert web content into LLM-ready Markdown for RAG and data pipelines. The tool supports diverse crawling strategies, including Breadth-F…
→ View original sourceGitNexus is a context engine designed to improve AI agent reliability in enterprise codebases by indexing repositories into a comprehensive knowledge graph. Unlike traditional Graph RAG, which provides raw edges to LLMs,…
→ View original sourceLiveKit has released "agents," an open-source Python framework designed for developing programmable, multi-modal voice agents capable of real-time interaction. The framework enables developers to build conversational par…
→ View original source