Repository index
6792 AI, ML and Web3 projects · page 24 of 68
- CLAUDE-CODEX-SETTINGS - TOP SETTINGS FOR CLAUDE AND CODEX
Personal Claude Code and OpenAI Codex configuration with verified skills, plugins, hooks, and agents for daily work.
- Self‑Evolving Data Ontology
Plugin that builds and continuously updates an ontology layer for data agents, enabling Claude Code/Codex to reason over evolving knowledge.
- DOWNLOAD HUGGINGFACE MODELS EASILY
Go utility for downloading models and datasets from HuggingFace. Supports CLI call and work via API, caches files locally.
- RAGLITE - FAST RAG ON DUCKDB
Simple tool for building RAG pipelines with DuckDB or PostgreSQL in Python.
- TITLE - AGENT SHELL IN EMACS
Agent Shell is a native Emacs buffer for interacting with LLM agents via the ACP protocol. It lets you chat with AI directly from the editor.
- SITE FOR DEVELOPERS AI
🌎💎 site-for-developers is a curated list of AI tools created specifically for developers. The project gathers the best tools for working with LLMs, RAG, multimodal models, and AI agents, updated weekly. It serves as your first bookmark for quick access to the latest AI-stack innovations.
- PROXIMA: UNITE AI WITH TOOLS
Proxima — an MCP server that connects ChatGPT, Claude, Gemini and Perplexity to your development tools without direct API calls. It supports JavaScript and has already gathered 1.2k stars on GitHub.
- Local Global Event Intelligence
Aggregates 40+ keyless live feeds into a single local API with 1d–1y forecasts via Ollama. No cloud, keys, or cost.
- Alethe-agents - LOCAL WORKSPACE
A local desktop for launching multiple agents and terminals with real PTY, split panels, and session persistence.
- ACCELERATOR RAG ON AZURE
Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero‑Trust architecture and IaC.
- OLEAFLY: LOCAL AI EDITOR
Oleafly — a local workspace for scientific writing with an AI assistant. Lets you research, write, compile, verify and publish papers in LaTeX, Typst and Markdown, working with Git. Open source, high desktop performance.
- CODEG — AI Session Manager
Aggregator for viewing and managing AI agent sessions (Claude, Codex, Gemini) in a single interface. Supports desktop version, local server, and Docker.
- CHAT-JS: PRODUCTION-READY AI CHAT
Production-ready AI chat built with TypeScript. Easy to customize and integrate into any project.
- NORTHCINDER AD-FREE SHOPPING AGENT
Decentralized shopping agent without ads, with deterministic ranking and signed purchase mandates. Maintains a local audit trail for full transparency.
- SUBTITLES FOR ENTIRE SEASONS IN MINUTES
Translates whole season subtitles in one pass. Supports .srt/.ass/.vtt/.lrc, 120+ languages, 27 LLM providers. Timing untouched!
- AGENT MESH: NETWORK FRAMEWORK FOR AI AGENTS
Agent Mesh implements the A2A protocol for exchanging messages between autonomous agents on Go. The framework supports Model Context Protocol, provides tools for building scalable agent networks and fast launch of inference services.
- 🤖 ASO SKILLS
AI‑agent skills for App Store (ASO) optimization and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills‑compatible AI assistant to help with keyword research and metadata optimization.
- DR-CLAW: AI‑LABORATORY OF SCIENTIFIC RESEARCH
dr-claw is an AI‑laboratory where dozens of AI assistants work like research doctors. The platform unites Claude, GPT‑4 and other models in a single IDE for automatic planning, execution and documentation of scientific tasks.
- HOLLAMA: CHAT WITH LLM IN BROWSER
hollama — a minimal LLM chat that runs entirely in the browser. It connects to local models via Ollama and stores conversations in local storage.
- CREATE YOUR OWN GOOGLE TV
couch-tv turns any screen into Google TV with a phone remote. Optionally adds Claude assistant for voice control. Setup — just hand the repo to your AI agent.
- ZEN: One‑Click Notes
Self‑hosted notes app in a single Go binary: Markdown notes inside SQLite, full‑text search, minimal resources.
- WINDOWS AUTOMATION FOR DEEPSEEK HARNESS
MCP client for Windows control via DeepSeek Harness. Bridge to CursorTouch/Windows-MCP with Computer Use toggle and dependency installer. 630 stars on GitHub.
- ClaudeBar AI Menu Bar
A macOS app that tracks AI assistant quotas (Claude, Codex, Antigravity, Gemini) directly in the menu bar. 1,196 stars on GitHub.
- MATECLAW — SECOND BRAIN ON JAVA
🤖 MateClaw — a multi-agent AI framework with memory, skills, dreams, and multi-channel support. 625 ⭐ on GitHub!
- Create Your AI Agent
A course of 8 articles and 4 videos will show how to build a coding agent in the style of Claude Code using Python from scratch.
- AI LEARNING: ROADMAPS
Complete set of roadmaps and resources for AI, ML, DL, and Data Science — from beginner to expert.
- OBOT — MCP PLATFORM ON GO
Full MCP platform: hosting, registry, gateway and chat client. 830 stars on GitHub.
- TINY VLLM: BUILD YOUR LLM
A mini version of vLLM in C++ and CUDA for fast inference of large language models. Enables building your own high-performance inference engine.
- SAGE: Multi-Agent System for Complex Tasks
Python framework for creating multi-agent systems capable of solving complex tasks together.
- KANBAN FOR HUMANS AND AGENTS
Self-hosted kanban for humans and agents. 4 MB binary starts in 2 ms with zero setup. Written in Rust, 460 stars on GitHub.
- FOUNDATION MODELS FRAMEWORK
A practical lab for building and testing applications using Apple Foundation Models.
- OPENCLUELY — AI Interview Assistant
Free open-source alternative to Cluely for technical interviews: invisible overlay, real AI support, and smart processing of question images.
- VIM WITH AI ASSISTANT
Plugin vim-ai integrates OpenAI and ChatGPT models directly into Vim/Neovim. It offers code autocompletion, snippet generation, and code explanation via chat with AI. Supports Gemini, GPT‑4, and other LLMs for productive work.
- ADK‑JS AI Agent Toolkit
ADK‑JS is an open‑source TypeScript toolkit for building, evaluating, and deploying advanced AI agents with full control and flexibility.
- Agent-Ready Knowledge Base
Rust-powered knowledge base with tree-sitter indexing and hybrid search for humans and AI agents.
- AI Code Review Bot
Scans changed lines for SAST, secrets, dependencies, lint, then runs an AI reviewer that evaluates each finding using the full diff. No extra API key required.
- Unified Visual Perception VLM
WeVisOne-VL unifies object-level and pixel-level visual perception, handling points, boxes, masks, and alpha mattes in a single vision-language model.
- RAG-CHAT ON AZURE STACK
Template for creating a ChatGPT-like chat with RAG pattern: Azure AI Search + Azure OpenAI, best practices and out-of-the-box solutions.
- AI Agent for Desktop Management
A browser-based desktop where an AI agent manages applications via natural language.
- REF-TOOLS-MCP: AGENT WITHOUT ERRORS
ref-tools-mcp helps coding agents work with any libraries without overloading the context window. It indexes code via tree-sitter, fetches up-to-date documentation and controls prompt size, preventing errors.
- AI PROJECTS ON AUTOGEN AND TUTORIALS
The repository contains a set of examples and tutorials on using AutoGen to create AI agents. Here you will find ready‑to‑run Python scripts, integrations with CrewAI, LangChain, LM Studio, and SmolAgents.
- RALEX - Autonomous Plan Execution
Extended Ralph loop for autonomous plan execution using AI. Written in Go.
- CTX: FAST HISTORY SEARCH
Local search of your AI agent's action history right on disk. Quickly find the code snippets you need without sending data over the network.
- INTELLIGENT AUDIT SYSTEM: AI AUDIT
Enterprise audit agent workspace with Agentic RAG, controlled tool usage, and human‑review workflow.
- PaperSpine: article analysis
WUBING2023/PaperSpine — a Python AI tool that helps researchers quickly identify the central argument of scientific papers and improve manuscripts.
- SEMANTICA AI-KNOWLEDGE GRAPH
Semantica — a framework for building AI‑enhanced semantic graphs, enabling semantic search, ontological inference, and explainable AI.
- claude-powerline - Beautiful Powerline for Claude
claude-powerline adds a stylish vim‑like powerline to the Claude Code interface, improving visual navigation and development productivity.
- LLM Inference Optimization Roadmap
A 10‑week plan to study the service and accelerate large language models, covering vLLM, SGLang, quantization, and speculative decoding practices.
- PYTHON SDK FOR AI AGENTS
Library for building AI agents with the full power of Google Antigravity. 1178 stars ⭐
- UNITERM: ONE TERMINAL FOR ALL
Lightweight all-in-one terminal with support for 20+ protocols and a built-in autonomous AI agent that plans and executes multi-step commands.
- AGENT SHOPPING FOR MAXIMUM BENEFIT
Filtmall-Shopping-Skill — AI agent skill for finding identical products, checking actual price and automatic purchase. It provides checkout, order placement, delivery, and after-sales support.
- DLSS 5 Feeder for Games
It adds DLSS 5 support to games without built-in DLSS by feeding synthetic depth and motion vector data through a private D3D12 device.
- Read Papers in Comfortable Chinese
Local app for reading English PDFs in fluent Chinese, with side-by-side source, AI Q&A, and paper organization.
- MCP SERVER FOR DAVINCI RESOLVE
Integration of MCP server for DaVinci Resolve Studio in Python. Automation of video editing via AI agents.
- Hand-drawn CSS annotations
The project offers a set of CSS classes for drawing hand‑drawn annotations on top of inline content without JavaScript. Appearance can be easily customized via CSS variables, making it simple to embed on any web page.
- SMALL ENGINEER ROBOT WITH AI ASSISTANT
Tiny‑Engineer — a desktop robot on ESP32 that brings an AI coding assistant to life, moving when it reads files, thinks, and writes code. After finishing a task, it demonstrates an antigravity effect, signaling readiness.
- GUFO: INFERENCE ENGINE FOR STRIX HALO
gufo — inference engine for AMD Strix Halo in C++. Qwen Flash Next Q4_K_XL delivers 59.41 tok/s (1 user) and 157.22 tok/s (8 users). Qwen27B Q4_K_XL with DFlash2 gives 70.56 tok/s. 210 stars on GitHub.
- AWS SKILLS FOR AI AGENTS
Ready-made skills for integrating AI agents with AWS services. Supports Claude Code and Codex. 1155 stars on GitHub.
- RUST RUNTIME FOR LLM INFERENCE AND EDITING
larql — Rust runtime to run, serve, and edit models. VINDEX3 format makes models executable and inspectable. 1173⭐ on GitHub.
- ENTERPRISE DEEP RESEARCH - DATA RESEARCH WITHOUT LIMITS
Salesforce Enterprise Deep Research is a tool for deep analysis of corporate data in Python using advanced AI methods.
- LUXAS - Autonomous Scientific Assistant
Luxas turns your question into a ready scientific manuscript, working autonomously while you sleep.
- LangChain on Elixir
Implementation of the LangChain framework in Elixir, enabling integration of large language models into projects.
- ROCKPACK QUICK START REACT
Zero‑config React template with built‑in SSR, automated quality gates, and AI‑ready structure. Lets you write clean code yourself or with an AI assistant instantly.
- KNOWNOTE: LOCAL AI KNOWLEDGE BASE...
KnowNote — local AI knowledge base on Electron, replacing NotebookLM... Indexes files, answers questions and builds chains of thought without sending data to the cloud.
- BOARDUI: REACT DESIGN SYSTEM FOR AI AGENTS
BoardUI offers free, ready made React components for building AI‑agent interfaces with full open source source code. The homepage features a demo chat that runs with your own model API key. Built on Next.js and fully typed TypeScript.
- AGENTS: CREATE AI AGENTS NO CODE
Create AI agents in a visual builder or via the TypeScript SDK with full two-way synchronization.
- CONNECT ATLASSIAN TO AI
The official remote Atlassian MCP server securely connects Jira, Confluence, Bitbucket and other services to AI assistants via OAuth 2.1 or tokens.
- CLOUDBASE AI: CONNECT YOUR AGENT
The CloudBase cloud platform now easily integrates with AI agents: turn prompts into working applications in just minutes.
- OKOU — AI AGENT FOR TEAMS
Okou connects to your team's tools and executes tasks across marketing, sales, engineering, and operations. Runs agents in isolated sandbox with access control. Written in TypeScript, 1.1k stars on GitHub.
- NEBULA — AI PENTEST ASSISTANT
Automates reconnaissance, note-taking, and vulnerability analysis in penetration tests.
- FAST OCR SERVER ON GPU
TurboOCR — a lightning-fast OCR server on TensorRT FP16 with PP-OCRv5 support, processing 270 images/sec on FUNSD via HTTP + gRPC API.
- From Instructions to Inference
A C reading path from one instruction to production inference, using primary sources and runnable benchmarks for each section.
- PERSONAL AI AGENT
nod — open-source AI agent with its own virtual machine. It follows invoices, prepares calls and cancels trial periods on real websites, asking for confirmation before acting.
- STRIDE GPT Threat Modeling AI
A strategic tool for automatically generating threat models using the STRIDE methodology with OpenAI's GPT.
- AI AGENT SKILLS: UNIVERSAL MANAGER
Universal skill installer for AI agents: one command, support for 12+ runtime environments via npx.
- CONNECTONION AGENT FRAMEWORK
The most advanced framework for collaborative work of AI agents in Python. Allows quickly creating and linking agents for complex tasks.
- Claude Code for Finance
Claude Code, tailored for the finance sector. Enhances efficiency of analysis, modeling, and decision‑making.
- CONCORD-MCP - AI AGENT FOR GOOGLE
Concord-mcp gives AI agents a shared workspace like Google Workspace: shared documents, spreadsheets, and calendar.
- PROXYPAL — AI in One Interface
ProxyPal unites Claude, ChatGPT, Gemini, and GitHub Copilot in a single desktop client, letting you work with any coding tool.
- Automotive Skills
Over 100 skills for Claude: functional safety ISO 26262, cybersecurity ISO/SAE 21434, SOTIF, AIAG-VDA quality, and continuous improvement tools.
- FESS: AI SEARCH FOR BUSINESS
Fess is an open source search server built on OpenSearch, indexing web, files, databases and clouds, supporting 20+ languages and semantic search with AI/RAG.
- AI MOVIE NARRATOR
Generates voiced video recaps of movies from a single text prompt. Combines an LLM for the script, FFmpeg for editing, and Python scripts for full automation. The result is a ready‑to‑publish clip with narration and subtitles.
- MOVA Scalable Video-Audio
The MOVA project generates synchronized video and audio, scaling to large datasets in Python.
- Awesome GPT Resources
Useful tools, documents, and applications for working with ChatGPT in one repository.
- LLM SANDBOX: OPEN AND RUN CODE
A lightweight and portable sandbox for executing code in Python LLM applications.
- DOCKIT – AI AGENT FOR DATABASES
Dockit – a desktop TypeScript GUI client for managing Elasticsearch, OpenSearch, DynamoDB, MongoDB and EasySearch via natural language queries. An open, privacy‑first project.
- SALES DESIGN FOR SAAS
Python library with UI‑templates based on behavioral science and CRO to boost SaaS conversion. Includes A/B‑scripts and hints from Claude and Codex for AI‑design.
- ELASTIC LABS: EXAMPLES FOR SEARCH
The repository contains notebooks and example applications for search, observability, and security based on Elasticsearch. It includes ready‑to‑use solutions for AI applications, chatbots, and log analysis.
- RAG-RETRIEVAL UNIFY SEARCH
The project unifies efficient fine-tuning of RAG search methods: embeddings, ColBERT, and reranker.
- AI Agent for Data Analysts
Smart Python agent for automating business data analysis using AI.
- AI-HANDS-ON: LEARN AI FROM SCRATCH
A collection of notebooks and files for learning AI from scratch. 1137 stars on GitHub.
- SAG: WORKBENCH FOR DOCUMENT RAG
Ready-to-use workbench for document search based on SAG. TypeScript, 1136 stars!
- RULESYNC: UTILITY FOR AI AGENTS
CLI utility for managing AI agent rules while coding. 1135 stars on GitHub!
- Obsidian Wiki Framework
Framework for AI agents that automatically creates and maintains an Obsidian wiki based on the LLM Wiki Karpathy template.
- GUIDE TO AI SYSTEMS
A practical guide to designing production-ready AI systems and evaluating their quality for engineers.
- ESP-Claw: AI for IoT
ESP-Claw is a framework for creating AI agents that write code in interactive mode on ESP32 devices. It lets you describe tasks in natural language and obtain ready C code for IoT.
- KEY AI SKILLS FOR TEAMS
Claude-Skills offers 343 AI skills, 76 expert agents, and 835 ready-to-use Python tools for engineers, PMs, marketing, and C-level.
- Clinical Evidence Benchmark
Benchmarks assistant responses by extracting the single fact underlying each answer and testing if the action follows that evidence.
- PROFESSIONAL UI DESIGN IN AGENTS
Professional UI design directly in your AI agent: Copilot Chat, Claude Code, Codex, Cursor. 270+ design skills, 150+ design systems, 160+ examples. No apps, daemons, or API keys — just files in your repo.
- SCHEMA-GUIDED REASONING AGENT
sgr-agent-core — a framework for building agent systems using Schema-Guided Reasoning in Python from the neuraldeep community.