Repository index
6792 AI, ML and Web3 projects · page 21 of 68
- LLM-WIKI: Knowledge for Agents
Creates knowledge bases for AI agents, combining parallel research and wiki generation.
- NEUROSPLOIT - AI PENTEST FRAMEWORK
NeuroSploit uses LLM to automate pentesting, generating exploits and analyzing vulnerabilities in real time.
- AMAZON BEDROCK: READY EXAMPLES
Official repository with examples for the Amazon Bedrock service. Ready-to-use solutions for working with all available foundation models.
- FAST MULTIMODAL LLM ON MOBILE
A C++ library enables running multimodal LLMs directly on smartphones with high speed and low power consumption.
- MULTI-AGENT ALTERNATIVE TO CLAUDE TAG
AgentConnect — open-source multi-agent platform that lets you connect any AI‑agent to your workflows. They learn on the fly, working alongside your team, and support the Agent‑Client‑Protocol and Agent Sandbox.
- PrismerCloud: Cloud AI Platform
Cloud-based AI platform for developing and deploying AI solutions. Written in TypeScript.
- Visual Intelligence for Home
ha-llmvision brings visual intelligence to your home, enabling real‑time object, face and activity recognition for smarter automation.
- THEPIPE: DATA FROM DOCUMENTS FAST
ThePipe uses vision‑language models to extract data from PDF, Word and PowerPoint. It recognises tables, text and images, turning them into ready‑to‑use structures. Supports batch API.
- WORKANY — AGENT FOR ANY TASK
A desktop agent built with TypeScript capable of performing any task via a chat interface.
- JOBSYNC - APPLICATION TRACKER WITH AI
Open‑source application tracker with an AI assistant: resume analysis, job matching, and application analytics, with all your data staying private.
- AI Interview Cheat Sheet
A collection of questions and answers for preparing for an AI engineer interview. Covers topics in machine learning, deep learning, and system design.
- TOP-100 AI AGENT HARNESSES
A weekly updated list of 100+ top harnesses for AI agents with an MCP server and ready-to-use recommendation formats.
- Awesome AI Web Search
A collection of the best web tools where AI helps search the web faster and more accurately.
- FIND RUST BOTTLENECKS FAST
hotpath-rs is a single profiler for CPU, time, memory, and async code. It quickly finds bottlenecks in your Rust project.
- MCP Server for French Open Data
The official MCP server from data.gouv.fr that lets AI chatbots search, view, and analyze datasets from France's Open Data platform directly in conversation. A Python project for seamless integration of open data.
- SKILLS: AGENTS.MD TEMPLATE FOR AI
The project offers agent skills and an AGENTS.md template to isolate work in worktrees, build a service layer, validate with evidence, and release using proof‑before/after and Greptile review. Works with Claude Code, Cursor, and Codex.
- Dynamic Sparse Attention for Video-Audio
Prism enables native joint video‑audio generation by applying a dynamic sparse attention mechanism that scales to 2K resolution.
- CLAUDE-PRISM – OFFLINE SCIENTIFIC WRITING
A local workspace for scientific papers: LaTeX, Python, and 100+ Claude skills — all offline.
- 80+ FREE AI SERVICES
A collection of 80+ free AI services for chat, images, video, voice, and API. Includes even paid LLM. ⭐ 1510
- RCLI — Voice AI
Voice AI with RAG, no cloud: chat with Mac and request documents locally.
- REUSABLE SKILLS FOR POWERFUL AI AGENTS
A library of reusable skills for AI agents: ideation, writing specifications, implementation, code review, fast autonomous research. Works with Claude Code, Codex and other skill‑compatible agents.
- AI WRITES COMMITS FOR YOU
A Go CLI tool that uses gpt-4.1 to automatically generate commit messages and perform a quick code review directly from the terminal.
- tt-metal - Metallic Operations Library
TT-NN operator library and low-level programming model for TT-Metalium kernels to accelerate AI workloads on proprietary hardware.
- FLUENT-KOREAN: CLEAN KOREAN CODE
Output-style plugin for Claude Code that makes responses clear and natural in Korean. Provides smooth Korean without artifacts.
- JS Hooks Toolset
A complete set of tools for working with JavaScript hooks: embedding, debugging, and management in one solution.
- Account Balancer Codex/ChatGPT
Proxy and load balancer for multiple accounts with usage tracking, a monitoring dashboard, and OpenCode-compatible endpoints.
- TTY7: FUTURE TERMINAL IN RUST
A Rust-based terminal workspace with GPU rendering, persistent sessions, SSH, and AI agent integration for coding.
- Shanyin: Super Screenwriter
A complete toolkit for writing scripts of any format, from microfilms to series.
- SOKUJI - REAL TIME TRANSLATION
Sokuji provides instant speech translation on-device and in the cloud with support for OpenAI, Gemini, and other providers.
- 4DAnyone: 4D Avatars
The project enables recovering full 3D human geometry over time from ordinary monocular video, creating realistic avatars without needing special equipment or pretrained models.
- MIRASCOPE - LLM WITHOUT FRAMEWORKS
Mirascope is a lightweight anti-framework for working with LLMs, enabling quick prompt creation and testing without unnecessary abstraction.
- INNO-AGENT: Smart Personal Agent
Open agent with three‑layer memory, proactive scheduler, and a personal practice lab built on TypeScript.
- 50 SKILLS FOR AI MOTION GRAPHICS
motion-skills — 50 open skills for AI agent: motion graphics, animation, video (kinetic typography, data viz, explainers, TikTok/Reels, WebGL, Manim). 14 ready packages from iart.ai.
- AI Coach for Agents
A TypeScript library that helps developers create, test, and improve LLM‑based agents using AI suggestions and automated checks.
- RISUAI: CREATE YOUR STORIES
Risuai lets you easily create interactive role-playing plots with LLM using TypeScript.
- OPEN HARNESS PLATFORM FOR AGENT
OpenHarness — open-source platform for (agents). It lets you run Claude Code, Codex and any coding agents on your machines, training them to work in CAD, PCB, robotics and games, while the Harness hardware keeps them on your desk.
- KOTLIN-SDK - OFFICIAL SDK FOR MCP
Official Kotlin SDK for Model Context Protocol, created together with JetBrains. Enables easy integration of AI agents.
- GPU-Accelerated AI Video Analytics
A set of reference architectures for building GPU-accelerated vision agents and AI-based video analytics applications. ⭐ 1,486 stars, Python.
- AI Text Anti-Detector
Skill for auditing and reworking content to eliminate AI-generation traces. Works with Claude Code, OpenClaw, Hermes.
- LENNY SKILLS: 86 PRODUCT SKILLS
A collection of 86 product management skills from the Lenny podcast, adapted for Claude Code and AI agents.
- MITM via Domain Fronting
Interception of unencrypted traffic using Domain Fronting technique to bypass network blocks.
- ENGRAM Smart Learning
Learning engine for Claude Code: FSRS memory, replay verification, and first-principles courses.
- SKILL-CODEX DELEGATING PROMPTS
skill-codex lets you delegate Claude prompts directly to the Codex model, simplifying code generation through natural language.
- ChatMock — API for LLM testing
OpenAI and Ollama-compatible API based on Codex. Ideal for testing and developing AI applications.
- LUA N1AO AGENT: AI-PENTEST
An autonomous AI agent for system penetration, using a dual reasoning graph. Developed by Professor Lu Hui's team from Guangzhou.
- COG-SECOND-BRAIN - AI SECOND BRAIN
Self‑evolving second brain with 17 AI skills, 6 working agents, and a CRM for people. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
- Source-Tracing Research Skill
A Claude Code skill that recursively traces citations and references to find original sources for unfamiliar topics.
- 80+ AI Agents in Python
Over 80 ready‑to‑use examples of AI agents in Python: autonomous agents, multi‑agent systems, and integration with uAgents, ASI:One, LangChain, and other frameworks.
- PLATFORM FOR AI DEVELOPERS
aider-desk is a desktop app for working with AI code assistant. Combines chat, file editor and Git in single interface. Supports Claude, GPT-4 and local models.
- drawio-scientific-illustrator - SCIENTIFIC ILLUSTRATOR IN CODEX
Control the visible draw.io canvas in real time via MCP, creating step-by-step scientific illustrations directly in Codex.
- YOUR PERSONAL AI AGENT IN CLOUDFLARE!!!!!
Personal AI agent in your Cloudflare account: chat, memory, tasks, notes and reminders. Deployed efficiently with one command npx create-talorys@latest, free-tier,single-user, no telemetry and ready.!
- WordPress AI Assistant
The library provides ready-made WordPress knowledge for AI assistants: block structure, theme creation, plugin development, and best‑practice recommendations.
- FAST LLM ON AMD
Run LLM on AMD Ryzen™ AI in minutes. Like Ollama, but deeply optimized for AMD chips! C++
- Local Decision Model Server
Serves Laya, decider, NLI, and GLiClass models via a TypeSafe‑compatible API for local inference.
- MINUET AI.NVIM — SMART AUTOCOMPLETION
An AI plugin for Neovim that offers real-time code completion from popular LLMs: OpenAI, Gemini, Claude, and local models.
- KONNECT: AI PCB Design
The Konnect AI assistant integrates into KiCad as a single Rust binary, providing 171 tools for schematics, routing, and design verification.
- AWESOME MUSE CONNECTORS
The project offers a source-backed catalog of Meta Muse integrations featuring community connector skills, with (details) on capabilities, authentication, and required permissions for each skill.
- GENERATIVE_AI_WITH_LANGCHAIN - BUILD PRODUCTION LLM
Notebooks for creating production-ready LLM applications and agents using LangChain and LangGraph. Practical examples from the generative AI book.
- AGENTLAS-OS: Agents Environment
Manage specialist agents via a hub, automatically creating orchestrators for tasks. Works locally and is compatible with any model.
- human-review — VISUAL EDITOR FOR AI
A visual tool for editing HTML and Markdown, leaving Google Docs‑style comments, and sending feedback to your AI agent. Works inside any AI harness.
- SNIPPETS FOR MEASURING WEB PERFORMANCE
A set of tested JavaScript snippets for measuring and debugging web performance. They can be run by your AI agent or you yourself in DevTools — the code is always the same.
- MY AI COMPANION ON PC
Create your AI assistant on the desktop: custom characters, voice dialogue in 1 second, long-term memory, and image recognition.
- AGENT-PLUGIN SPEC V1.0
Minimal standard for packaging agent extensions into plugins. Enables easy sharing and use of new agent features.
- OBSEI AI BUSINESS AUTOMATION
Obsei — low‑code Python platform for AI‑powered business automation: social listening, smart alerts, brand image analysis and comparative studies. Supports customer feedback, PII protection and voice of customer.
- PRIVATE AI MEETING NOTES
yogurt — private meeting notes powered by local AI. Works offline via llama.cpp, data never leaves your device.
- Awesome Claude Resources
A selection of the best resources, libraries, and examples for working with Anthropic Claude.
- PARITOK-4B: REDUCING TOKEN USAGE 90%
Lossless code compression gateway cuts AI agents' token usage by 25% per turn and up to 90%+ in long sessions. Open 4B model, ready to use with Claude Code, Cursor, Codex, and more.
- PAPERTHIN: SKILLS FOR RECURSIVE RSI
OpenAI hackathon winner's project on recursive agent self-improvement. Unpacks NVIDIA's zero-touch proof into engineering practice. Ready skillset for autonomous coding agents.
- Xiaohongshu Social Card Generator
A pure‑HTML script generates Xiaohongshu carousels and paired WeChat covers (21:9 and 1:1) with 28 layouts and 10 themes in Swiss editorial style. The output is a single HTML file that can be exported to PNG.
- Omnibox - Your Universal Hub
Omnibox collects, organizes, and lets you use and share any data in a single Python interface.
- openai-oauth - Free OpenAI Access
Get free access to the OpenAI API using your ChatGPT account, without needing a separate key.
- RUN LLM LOCALLY IN REACT NATIVE
Run large language models directly on device without internet. Full Vercel AI SDK compatibility for familiar API.
- Pets for AI Coders
Public gallery of animated pets for Codex, Claude Code, OpenCode, and Gemini CLI. Create, customize, and share digital pets.
- AI Fullstack SaaS Boilerplate
Boilerplate for SaaS based on tRPC, Fastify, and React with TypeScript. Quick start for a full-fledged product.
- BROWSERGYM WEB-AGENT TRAINING
BrowserGym is a Gym environment for automating web tasks, enabling training of AI agents to interact with real websites. It provides a standard reward and observation API compatible with any RL algorithms.
- SOVEREIGN AI SECURITY AGENTS INFRASTRUCTURE
Open-source infrastructure for deploying sovereign AI security agents. Agents continuously find, verify, and fix vulnerabilities in code, web applications, dependencies, and binaries.
- Bryl Exercise Catalog
Over 300 ready‑made exercise illustrations and a framework‑agnostic npm package that lets you easily integrate the catalog into Astro, React, Vue, and other framework projects.
- MCP-SERVER-QDRANT - OFFICIAL SERVER
Python implementation of the official Qdrant Model Context Protocol server for fast embedding of vector databases.
- BROWSER AUTOMATION FOR AI AGENTS
CLI tool for browser automation with built-in anti‑bot bypass, human task handoff, and parallel execution across multiple sessions.
- AWESOME-RAG: BEST RAG APPLICATIONS
Curated list of the best Retrieval-Augmented Generation projects in Generative AI. 1284 stars ⭐
- E2B-Cookbook - Unlock Possibilities
Examples of using E2B to launch sandboxes and integrate with AI agents. Simplifying code work in the cloud.
- OPEN AI AGENT COLLECTIVE
OpenMeld — an open‑source collaboration system for people and AI agents. It lets you share context, coordinate tasks and run them in parallel with cloud agents, Codex, Claude Code, Grok.
- BROWSERWING - CONTROL THE BROWSER WITHOUT LIMITS
BrowserWing turns browser actions into MCP commands or Claude skills, enabling AI agents to control the browser quickly and without extra tokens.
- DOCUMENTATION FOR AI AGENTS
Open-source MCP server for working with documentation — an alternative to Context7, Nia, and Ref.Tools. 1419 stars on GitHub.
- AI Workspace for Authors
Smart workspace for content creators: write, research, manage prompts and knowledge base — all in one place with support for multiple AI models.
- KEY TO SCIENTIFIC SUCCESS
A Claude Code/Codex skill set for top journals: from idea to reviewer responses. Accelerate publication in minutes.
- OLLAMA SHARP: EASY AI ACCESS
OllamaSharp is a simple .NET library for integrating with local Ollama models, enabling quick requests and responses.
- HELLO-AI: Master AI or Lose
The hello-ai project shows how mastering AI tools becomes a key to survival in a competitive environment. Inspired by the dimensionality reduction strike concept from 'The Three-Body Problem'.
- CHATGPT-SCRAPER - INTELLIGENT SCRAPER
Get structured responses from ChatGPT scraping API in one line. Enable live search, HTML context, and automate tasks.
- FIGWRIGHT: TURN FIGMA INTO CODE
Free two‑way MCP server for Figma: turns designs into framework code and back.
- WebAI-to-API - TURN CHAT INTO API
The project lets you easily turn any web chat into a REST API, simplifying AI assistant integration.
- 12 000+ REVERSE ENGINEERING TOOLS
Collection of 12 000+ tools for reverse engineering apps, APIs, protocols, and AI. Nightly updates and agent skills save time on duplicate work.
- COMMONLY: Social Network for AI Agents
A social platform where people and AI agents interact with each other. Connect any agent via HTTP.
- GENERATIVE AI FOR BUSINESS
The project demonstrates practical scenarios of applying generative AI in corporate processes with an emphasis on security and scalability.
- OPEN DESKTOP-PET WITH AI
OpenPets — a local desktop companion platform with animated pets, plugin SDK, and coding‑agent integrations (such as Claude Code). Lets you create your own pets and extend their behavior via TypeScript plugins.
- RTP-LLM ENHANCED LLM INFERENCE
High-performance LLM inference engine from Alibaba, written in CUDA, enables fast model operation across diverse applications.
- aws-genai-llm-chatbot - POWERFUL CHATBOT ON AWS
Modular solution for a chatbot with multiple LLMs and RAG on AWS CDK. Integrate Anthropic, OpenAI, HuggingFace models.
- LLM IN SPACY PIPELINE PAINLESSLY
spacy-llm connects GPT, Claude, Cohere and open models to spaCy pipeline. Configure via config, get structured Doc with entities and relations. No wrapper code — pure NLP workflow.
- NullMotion: ad preview
The project shows a finished motion‑graphics ad overlayed on black‑and‑white HyperFrames sketches, and lets you export it to MP4 with frame‑accurate precision.
- AI Video Production Kit
Provides a Python toolkit that uses Claude Code to generate professional business videos with critic loops, motion principles, and sound design.