Repository index
447 AI, ML and Web3 projects · page 3 of 5
- PEFT: Efficient AI Training
The PEFT library provides state-of-the-art parameter-efficient fine-tuning methods for models, reducing resources and training time.
- 3D ARCHITECTURE EDITOR
Create and share 3D architectural projects in the browser. TypeScript tool for fast visualization and collaboration.
- Persistent Markdown Planning
Implements a Manus-style approach with persistent Markdown planning, repeating the workflow behind the $2 billion deal.
- AI JOB SEEKER
Speed up your job search: analyze job listings, tailor your resume, craft cover letters, and prep for interviews—all locally.
- Uncensored LLM Automation
The project eliminates automatic censorship in language models, making responses free and unrestricted.
- Scientific Agent Skills
Ready-made skills for AI agents covering research, science, engineering, analysis, finance, and text writing.
- MCP for n8n
MCP for Claude Desktop/Code, Windsurf, and Cursor automatically creates n8n workflows.
- Happy Codex client
Mobile and web client for working with Codex and Claude Code, supporting real‑time voice chat, encryption, and full feature set.
- Go Excel library
A Go library for reading and writing Excel files (XLSX, XLSM, XLTM, XLTX, XLAM) with support for styles, formulas, and large sheets.
- FROM PROTOTYPE TO ENTERPRISE
Complete step-by-step tutorials for building GenAI agents for production — from prototype to enterprise deployment.
- NemoClaw for OpenShell
Running OpenClaw in NVIDIA OpenShell with managed inference for increased security and control.
- Local AI Builder
Open-source local AI application builder for advanced users, an alternative to v0, Lovable, Replit, and Bolt.
- Sub2API CRS2 Service
A unified open service for Claude, OpenAI, Gemini, and Antigravity that combines subscriptions and shares costs.
- Mental Models Nuwa
Distill anyone's thinking: mental models, heuristics, and expression style. Your next 'employee' doesn't have to be a colleague.
- Voyager: AI Enhancement
A toolkit for enhancing Gemini, AI Studio, Claude, and ChatGPT with a prompt manager for any web interface, including DeepSeek Harness.
- Autonomous OS for Companies
Suna — operating system for autonomous companies, combining AI agents, automation, and business process management in a single environment.
- ADK Python: AI Agents
Open-source tool for creating and deploying AI agents on Python with full control.
- Claude Code Subagents
A collection of 100+ specialized subagents for Claude Code for development tasks.
- SWE-AGENT: AUTOMATIC ISSUE FIX
SWE-agent uses your LLM to automatically fix GitHub issues and is suitable for cybersecurity and competitive programming.
- KiloCode Platform
KiloCode — a universal agentic platform for development: create, deliver, and improve code faster with a popular open-source agent.
- Official Claude Plugins
An official catalog of high-quality plugins for Claude Code, managed by Anthropic.
- AI Data Assistant
An open next‑generation AI assistant for working with data and building intelligent products.
- Remove AI traces
A skill for Claude Code that removes characteristic traces of AI generation from text, making it more natural and resembling human writing.
- Autonomous agents for everyone
A platform for creating and working with autonomous agents, accessible to every developer.
- OpenAI Codex for Claude Code
A plugin for delegating tasks and code review in Claude Code via Codex.
- Claude Code: Reliable and Secure
A production-ready instance of Claude Code with enterprise-grade engineering. Safe, with no memory leaks.
- ML-ENGINEERING OPEN BOOK
Open book on ML engineering with practical materials and examples in Python.
- Reliable AI Agents for Clients
Parlant is a tool for controlling LLM interactions, optimized for stable, predictable, and customer-focused AI agents.
- WEB‑LLM: Browser LLM Engine
High-performance engine for running LLM directly in the browser, written in TypeScript.
- TWONE YOURSELF IN CHAT
Fine-tune LLM on your chats and bring a digital copy of yourself to life in any chatbot.
- DocsGPT: Private AI Assistant
Private AI platform for agents, assistants, and enterprise search with support for multiple models.
- Agent for web interfaces
A JavaScript agent inside the page controls the web interface in natural language.
- Open AI-Agent gbrain
A modular AI agent bridging the gap between expertise and task execution for developers.
- Nuclear player
The Nuclear streaming player searches for and plays free music from open sources.
- AGENT-LIGHTNING - TRAIN AI AGENTS
Platform for fast training and deployment of AI agents in Python. Enables faster creation of intelligent assistants.
- HTML to Video Rendering
Convert HTML code into video rendering. A tool built specifically for AI agents.
- Memory for AI agents
Manage AI agent memory in just six lines of code. Simple integration with powerful capabilities.
- Beautiful web slides
The library lets you create beautiful slides online using the Claude frontend. It supports animations, themes, and export to HTML.
- Personal assistant Leon
Open personal assistant with voice control, plugins, and a focus on privacy.
- Pydantic AI Agent Framework
Build AI agents with type safety and data validation using Pydantic.
- Taste‑Skill for AI
Taste‑Skill enhances AI's taste by removing bland and templated content, enabling more original and interesting responses.
- Generative AI Cloud
Code samples and notebooks for generative AI on Google Cloud with the Gemini Enterprise Agent platform.
- Terminal with vertical tabs
A macOS terminal based on Ghostty with vertical tabs and a notification system, designed for AI‑agent workflow.
- bolt.new — Full-stack IDE
An online environment for instantly creating, running, editing, and deploying full‑stack web applications.
- DeepWiki Open Source
AI wiki generator for GitHub/Gitlab repositories with AI support. Join Discord!
- PLATE: AI Text Editor
Plate – a rich‑text editor with integrated AI and UI based on shadcn/ui. It lets you create formatted content in seconds.
- AI Agent Platform
Open infrastructure for creating and training agents that control macOS, Linux, and Windows desktops via sandboxes, SDKs, and tests.
- Local code graph
Creates a code knowledge graph so Claude reads only what's needed — review tokens ↓6.8×, tasks speed up to 49×.
- FunASR — Speech Recognition
Industrial speech recognition tool: 170× realtime, 50+ languages, diarization, emotion detection, streaming, and OpenAI‑compatible API.
- MCP: From Basics to Production
Free course on the Model Context Protocol with examples in six languages for building reliable AI agents.
- Amplication - Order in Development Chaos
Amplication creates Golden Paths for developers — standardized workflows that accelerate delivery of high-quality code at scale.
- Web Interface AI Agent
Run and control the AI agent directly in the browser through an intuitive web interface.
- Multi-agent orchestration system
OpenClaw is an orchestration system comprising nine specialized AI agents, featuring a real‑time dashboard, model configuration, and full audit.
- Deep AI Code
Open‑source agent for generating code from articles, textual interface descriptions, and backend architectures.
- AI Agent Memory File
Replaces complex RAG pipelines with a serverless memory layer for AI agents, enabling instant search.
- AI PPTX Generator
AI creates a fully editable PPTX from any document — real PowerPoint shapes with native animation, not images.
- MNN: FAST AI ON DEVICE
Lightweight and lightning-fast inference engine from Alibaba for on-device LLM and Edge AI.
- Chatbot Interface
Graphical interface for working with ChatGPT API and other LLMs: support for agents, file Q&A, fine‑tuning and web search.
- MCP Toolbox for Databases
An open MCP server for working with databases that simplifies integration and management via a standardized protocol.
- WrenAI Context Layer
The open context layer gives AI agents controllable SQL from 20+ sources, enabling GenBI, text-to-SQL, dashboards, and advanced analytics.
- Trigger.dev: AI Agents
Platform for creating and deploying AI agents and workflows without infrastructure concerns.
- FIGMA CONTEXT MCP FOR AI
The MCP server transmits layout data from Figma to AI agents like Cursor, speeding up code generation.
- LLMware: RAG framework
Unified framework for building corporate RAG pipelines using compact specialized models.
- API and prompts for GPT-Image-2
A collection of prompts and instructions for using the GPT-Image-2 API to generate images with AI.
- Document Structuring
An open ETL solution for converting complex documents into clean structured data formats for language models.
- GPT Agents Without Pain
Open platform for creating and deploying LLM agents with visual builder support and integration with popular models.
- Memori: Memory for AI agents
Memori is an LLM-agnostic structured memory layer for AI agents with persistent state in production systems.
- AI website cloner
A TypeScript template for cloning any website with one command using AI agents. 14,490 stars.
- LLM Server for Apple Silicon
A powerful inference server with support for continuous batching and SSD caching, running on Apple Silicon and controlled via the macOS menu bar.
- Skills for Claude Code
245+ skills and plugins for Claude Code, Codex, Gemini CLI, Cursor and another 8+ agents — engineering, marketing, product, compliance, C-level consulting.
- Private NotebookLM
An open tool for teams with clear data limits and enhanced confidentiality. Join our Discord community.
- Everything Clear Code
Turn codebases and knowledge bases into a visual knowledge graph. Explore connections, perform searches, and ask questions in natural language — compatible with Claude Code, Cursor, Copilot, and others.
- ELECTERM — All-in-One SSH/Terminal
A powerful terminal client with SSH, SFTP, VNC, RDP, Telnet, and even serial port support. Works on Linux, Mac, and Windows — completely free.
- ms-swift: LLM training
A framework for fine-tuning 600+ language and 300+ multimodal models. Supports PEFT, full fine-tuning, CPT/SFT/DPO/GRPO.
- SKILLSPECTOR: AGENT PROTECTION
Scanner searches for vulnerabilities, prompt injections, and data leaks in Claude Code, Codex, and MCP skills before installation.
- Multi-user agent for work
TypeScript library for creating multi-user agents, simplifying collaborative work and interaction in AI projects.
- AI coworker with memory
An open AI coworker that remembers context and helps with coding, research, and task execution.
- AI-Powered R&D Revolution
RD-Agent automates research and development processes, enabling AI to manage data and models for higher productivity.
- Codex Dream Skin
The Codex Dream Skin theme is an aesthetic JS‑shell for the Codex interface with smooth animations and color customization.
- OpenMetadata — metadata made simple
A unified platform for metadata management, data discovery, and collaboration.
- XIAOHONGSHU MCP IN GO
MCP server for interacting with Xiaohongshu in Go, simplifying AI agent integration with the platform.
- MEMU — MEMORY FOR AI AGENTS
memU — memory storage for proactive AI agents, captures intentions and reduces token consumption by 10x.
- Design Skill for Claude
Native HTML design skill for Claude Code. Create high-precision prototypes, slides, and animations with MP4 export.
- CASDOOR — IAM FOR AI AGENTS
Open IAM server with a web interface: OAuth, OIDC, SAML, LDAP, MCP, MFA, and integrations with LLM agents.
- CC-HAHA - LOCAL-FIRST AI DESKTOP
Local cross-platform desktop for Claude Code and AI agents: multi-agent, Git worktrees, diffs, skills, and messenger access.
- Design System Specification
A TypeScript‑based format for encoding visual identity rules so coding agents can read and apply a design system consistently.
- Claude Skill Creator
Transforms documentation, GitHub repositories, and PDFs into Claude AI skills, automatically detecting conflicts.
- ROBUST RL ON PYTORCH
PyTorch version of Stable Baselines with verified implementations of reinforcement learning algorithms. 13.4K stars on GitHub.
- Headless browser for AI
Headless browser in Rust for AI agents and web scraping. Fast, lightweight, and ideal for automation.
- litgpt: Powerful LLMs
High-performance language models with ready-to-use recipes for pretraining, fine-tuning, and scaling. 13K+ stars!
- INSTRUCTOR - STRUCTURED OUTPUT FOR LLM
Library for obtaining structured responses from large language models, simplifying LLM integration into applications.
- OFFICIAL SDK FOR MCP
Official TypeScript SDK for working with the Model Context Protocol. Easily integrate servers and clients into your projects.
- OpenHarness AI Agent Platform
An open platform for building AI agents with the built‑in assistant Ohmo. Automating tasks and enabling intelligent workflows.
- Self-healing browser framework
Self-healing browser framework enabling language models to perform any task automatically.
- TXTAI — AI All-in-One
An algorithmic framework for semantic search, LLM orchestration, and language-model workflows. All in one!
- AWESOME-AI-APPS: BEST AI PROJECTS
A collection of projects with RAG, agents, and AI workflows. 12.5K stars on GitHub.
- MEETILY: AI ASSISTANT FOR MEETINGS
Meetily — a local AI assistant for meetings: transcription 4× faster, speaker diarization and summarization via Ollama, all built in Rust.
- Restoration of Claude Mythos
Theoretical reconstruction of the Claude Mythos architecture, built from scratch based on available scientific literature.
- Claude Skills List
A curated collection of skills, resources, and tools for customizing Claude AI workflows, including Claude Code.
- POCKET FLOW: CODE IN LESSON
Pocket Flow turns any codebase into clear learning materials, automating tutorial creation.