Repository index
6792 AI, ML and Web3 projects · page 17 of 68
- ZEROSHOT - AUTONOMOUS DEVELOPER TEAM
Specify a task — get production-ready code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.
- WAKU-AGENT — PERSONAL AI AGENT
A personal AI agent in Python: local launch, memory, task loop and evaluation — everything ready in just a few minutes of reading the code.
- DAILY RADAR AI-TERMS
new-term-radar daily tracks the emergence of new AI terms: model, product and repository names spotted on X, Hugging Face, GitHub and sitemaps before they appear in keyword tools. The project is written in Python and already has 907 stars.
- TENSORFOLD: FAST LLM DECODING ON MAC.
TensorFold provides exact and fast LLM decoding on Apple Silicon via MLX, offering an OpenAI-compatible API. The Python project has already earned 526 stars and supports the model inference without the approximations.
- Agent-Native RE Audit Workbench
Agent-native, multi-platform workbench for reverse engineering and auditing CWE-602 client-side authorization flaws.
- MiroFish: Offline Multi-Agent Engine
Local offline engine for multi-agent modeling and forecasting based on Neo4j and Ollama
- Secure Key Vault
An open credential manager providing AI agents secure access to services without revealing secret keys.
- Lucebox Hub
High-speed server for running LLM locally on consumer hardware. Written in C++ for maximum performance.
- KERNEL-MEMORY: AI MEMORY
An open-source research project in C# that provides a flexible memory system for users, teams, and applications.
- VLLM-ASCEND: ASCEND PLUGIN ON GITHUB
Community plugin for vLLM on Ascend hardware from the community, written in C++. Gaining stars — already 2156!
- V-Modal AI SDK Flutter
SDK for Flutter that enables adding multimodal video search using AI content analysis.
- Compile JS to Neural Networks
Handwired transforms ordinary JavaScript functions into trainable neural network models, enabling code‑driven AI directly in TypeScript.
- AI AGENTS FOR CODE AND REVIEW
qualitylayer lets you plan, write, and review code with AI agents. Works in app, browser, terminal, and IDE. 2097 stars on GitHub.
- Claude Code Config for Trail
A set of ready-to-use configurations, documentation, and workflows for Claude Code from Trail of Bits.
- Human-in-the-Loop Phone Automation
Pinky lets AI agents operate your phone while you approve each action, keeping you in control.
- JoyAI Video Editor
The JoyAI-Video-Edit project provides real-time open video editing using autoregressive diffusion, enabling generation and modification of content via text prompts.
- ZERO-TO-SGLANG: LLM INFERENCE TRAINING
The Datawhale and SGLang course teaches LLM inference from scratch: build a mini‑SGLang, study the source code, and land your first PR. Available in English and Chinese.
- ADR: AI Agent Security in Uber
ADR provides observability, security testing, and threat detection for enterprise AI agents, already used at Uber.
- OPEN-AGENT-EMAIL: INFRASTRUCTURE FOR AI AGENTS
open-agent-email: provides the secure inboxes for the AI agents via the REST and MCP API, the SMTP, and the workflows with the human approval. the Signed webhooks, the SDK for Python and TypeScript; the deployment with Docker+PostgreSQL.
- FUSIO: INDEPENDENT API MANAGEMENT
Self-hosted platform for creating, publishing, and managing APIs in PHP. Suitable for developers who need full control over the gateway.
- LLM-Space — Prototype Agents Easily
Desktop application for developing and testing LLM agents with deep control of each step.
- UNIFIED MCP SERVER MANAGER
Unified application for managing MCP servers. Start, configure, and orchestrate everything from one place.
- AGENTSET: OPEN RAG PLATFORM
Open RAG platform with citations, support for 22+ formats, and MCP server for deep research.
- AI AGENTS EVERYWHERE ALWAYS
The AI-Anywhere project lets you run AI agents in any browser without installation. Manage tasks right from the tab.
- MCP-MEMORY SERVICE: MEMORY FOR AI
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API, knowledge graph, and autonomous consolidation.
- CURATED RE TOOLS LIST
Curated tools and resources for reverse engineering binaries, apps, firmware, formats, and protocols. 1184 GitHub stars.
- JoyAI-Image: Multimodal Model
JoyAI-Image — a unified foundation model for image understanding, text-to-image generation, and instruction-based editing.
- AI SAFETY HOT DIGEST
AI Safety HOT collects daily AI safety news, papers & incidents, jailbreaks, prompt injection, alignment and evals. On the platform — website, daily digest, RSS and MCP.
- CARBON: ERP FOR MANUFACTURING
Carbon is an open-source ERP/MES/QMS platform for complex assembly, contract and configurable manufacturing. Built with TypeScript, 2123★.
- PARALLEL CONTENT PROCESSING IN PYTHON
Lightweight library for efficient parallel content processing with GenAI. 2110 stars on GitHub!
- MCP2CLI: CLI Tool
Turn any MCP, OpenAPI, or GraphQL server into a CLI at runtime — without boilerplate code or generation.
- Local-First Data Ontology
Helix Foundry lets you build a local-first data workspace, connecting your files into a unified ontology using HelixDB and DuckDB.
- VOICE AI ON ARDUINO
Realtime Voice AI with 100+ models on ESP32. Secure WebSocket and Edge Functions for AI devices.
- MCP SERVERS CATALOG FOR AI
mcpso — catalog of 2111+ MCP servers for connecting tools to LLMs. Convenient search by categories and tags. Written in TypeScript.
- Sandboxed Agent Code Runner
SPACE offers pluggable-runtime sandboxes that safely run agent and user code in isolated environments with configurable limits.
- GHIDRA MCP — AI Reverse Engineering
Server with 200+ MCP tools for AI-powered reverse engineering. GUI plugin, Docker, and autonomous agent work with Ghidra.
- ATLAS ADAPTIVE AGENT LEARNING LLM
ATLAS implements adaptive test-time learning and autonomous specialization of AI agents for coding tasks. It runs locally on Python, uses the repository as a knowledge source and adapts to the specific codebase without external APIs.
- AI Account Auto‑Registration
The project automatically creates and manages accounts for over 15 popular AI platforms, supporting both protocol and browser modes, extensible via plugins, and delivered as a one‑click app for macOS and Windows.
- CODEXPRO: LOCAL AI FOR CODE
Run ChatGPT Developer Mode as a local agent for your repository via MCP. 223 ⭐
- DSH BLENDER AI-PLUGIN REAL-TIME
DSH‑Blender plugin links AI to Blender via TCP, sending viewport frame and angle render. Enables search, prof. render, simpl. geom. offload computations in headless mode; call starts GUI with 15 tools and blender_rt_plan (28 fam / 183 ops).
- RPA: Visual Automation with AI
Open-source RPA platform with computer vision, OCR, and LLM assistant. Import/export tests from Selenium IDE.
- UNIFIED MCP HUB
Centralized management and dynamic orchestration of multiple MCP servers/API with flexible routing strategies. TypeScript, 2106 ⭐
- SOLIDWORKS Automation with Python
A Python library for automating SolidWorks via API. Enables creating, modifying, and exporting models without manual effort.
- MEMORAX-CODE: MEMORY FOR CODING
Memorax‑code is a memory plugin for AI coding that preserves your repository experience and makes it useful for future tasks.
- MCP SERVER FOR GITLAB
MCP server for GitLab provides over 100 tools for working with projects, merge requests, issues, pipelines and wikis via REST and GraphQL API. Allows integrating AI agents such as Claude directly into your workflow.
- QUICKSC0PE: UNIVERSAL MALWARE ANALYSIS
Universal malware analysis tool. Supports APK, ELF, EXE on Linux. Uses YARA for precise threat detection.
- OPEN SCIENCE AGENTIC WORKSPACE
Open Science — a local AI workstation for researchers, an alternative to Claude Science supporting models and reproducible experiments.
- OBSIDIAN AGENT: AI IN NOTES
Connect AI agents (Claude Code, Codex, Gemini CLI) to Obsidian via the ACP protocol and control notes with voice and commands.
- Holo Card Gen for Blender+Three.js
Turns a description or reference into an editable Blender hologram card and an interactive Three.js page, preserving style, typography, and purpose.
- CLAUDE SKILL: CINEMATIC LANDING PAGES
Free Claude skill that builds premium landing pages instead of generic AI layouts. Uses 40 top prompts, a media shelf with 50+ videos, and 55+ code techniques with screenshot-based auto-verification.
- CODYNC: OPEN SOURCE GROK BOT
Codync — open-source alternative to the Grok bot, letting you chat with Claude Code, Codex, Cursor, Gemini and 40+ AI agents as local bots on iPhone, Mac, Windows, Linux or in the terminal. Free, replaces Muse and Dots, written in Rust.
- Web interface for Kubernetes
Open UI for Kubernetes: topology, event timeline, and service traffic — plus resource viewing and Helm management.
- LOU SHANG - AI CODING AGENT
A universal AI agent on Python that combines multiple LLMs and tools for automating coding.
- CLI for AI Agent Devices
CLI tool for managing iOS and Android devices via AI agents. Automate interaction with mobile devices.
- AI LEGION FOR AUTONOMOUS PENTESTING
Autonomous pentest legion with AI commander and worker swarm. Tencent IAD champion: 3rd of 634 teams, 8h unattended, 1B tokens beat 4.5B. Implements Nüwa Test: gives AIs creation, language, history.
- TWEAKCC - CUSTOMIZE CLAUDE CODE FULLY
Configure system prompts, themes, spinners, styles, and hidden features of Claude Code. Support for all platforms.
- CLAUDE VIDEO SKILL
Enables Claude Code to generate short high-quality video clips from text prompts.!! Contains 180 repositories, grouped by type with security and safety ratings!! Available in English, Chinese, with code examples and integration instructions.
- GORTEX ACCELERATES AI CODE
GorteX is a high-performance code and intelligence graph engine supporting 257 languages and multi-repository access via CLI, MCP server, and API. It reduces token usage up to 50× for AI agents.
- Claude Account Safety Toolkit
Assesses device, history, network, and payment risks to give personalized setup guidance for local, VPS, or VM environments.
- NIMBALYST VISUAL WORKSPACE
Visual workspace for Claude Code, Codex and OpenCode. Run multiple AI agents in parallel, edit output in markdown and diagrams.
- BoxLite AI — platform for AI agents
Lightweight compute platform for AI agents: runs on a laptop and scales in the cloud with unlimited resources.
- PACA: AI-SCRUM POWER
PACA is an open AI-native task tracker for Scrum teams, where people and AI agents work on the same board and in the same sprint.
- SOLID-GLASS DESIGN SYSTEM FOR AI
Solid‑glass — это TypeScript‑based дизайн‑система для создания интерфейсов AI‑агентов. Она предоставляет Material‑like компоненты, тактильную обратную связь и технические утилиты для быстрого прототипирования.
- Superglue AI Integrator
Superglue turns natural language into ready tools and integrations for long-tail and enterprise systems. Get no-code solutions.
- AI Skills for Screenwriters
A collection of professional AI agent skills for writing screenplays, teleplays, and dramatic works. Automates character development, dialogue, and plot structure.
- PROACTIVE AI AGENT TEMPLATE
OpenDuet is an open-source proactive AI agent template built on OpenBot and CopilotKit. The agent works autonomously in its own browser, prepares morning briefs, and requests confirmation before taking actions.
- Bug Hunter
Autonomous vulnerability hunting in the terminal: reconnaissance, 20 vulnerability classes, report generation, all inside Claude Code.
- OVIS — CLIENT FOR HERDR
Browser and mobile client for herdr. Chat and live terminal in every agent pane, remote SSH access, web push notifications.
- NOTTE - Framework for Web Agents
notte is a framework for web agents: create and deploy serverless automation functions in a reliable browser environment.
- INSOMNIA: MACBOOK DOES NOT SLEEP
Insomnia — menu bar for macOS that keeps MacBook awake with the lid closed. Set timer for AI‑agent session (Claude Code, Codex) to avoid sleep — system safe replacement for Amphetamine and caffeinate without kext.
- FAST LLM LAUNCH ON NPU
FastFlowLM runs LLMs on AMD Ryzen AI NPU in minutes, delivering performance comparable to Ollama but optimized for NPU.
- TELEGRAM-MCP: MANAGE CHATS EASILY!
Telegram MCP server based on Telethon lets MCP clients read chats, manage groups, and send messages, media, and contacts.
- BON - CREATE ERROR-FREE BUILDERS
bon generates type-safe builders at compile time, allowing named function arguments in Rust without boilerplate.
- AI Agents for Teams
An AI agents platform that expands team capabilities without hiring new staff.
- RUN NEURAL NETWORKS LOCALLY
A collection of the best platforms and tools for running LLM on your own hardware. 2000+ stars!
- INDEX‑TRANSLATE MULTILINGUAL AI
Index‑Translate — a multilingual family of translation models based on LLM. Implemented in Python, 345★ on GitHub, supports fine‑tuning and inference for dozens of languages.
- AWESOME LANGGRAPH: EVERYTHING UNDER MEASURE
Complete catalog of LangChain+LangGraph: QT concepts, projects, tools, and templates for LLM and multi-agent systems.
- LLAMA.VIM: LLM RIGHT IN VIM
A Vim plugin that adds code and text completion using large language models. 2000+ stars on GitHub.
- AI-Powered Code Protection
The project provides tools for threat modeling, vulnerability scanning, triage, and automated patching, as well as a configurable autonomous scanner.
- KVCACHED: ACCELERATE GPU CACHE
Virtualized elastic KV‑cache for dynamic GPU sharing, accelerating LLM inference and reducing latency.
- POWERFUL CHATGPT LIBRARY
Open source JavaScript library for working with ChatGPT. 2000+ stars on GitHub!
- DOOP: MULTI-PLAYER AI CANVAS
An open alternative to Paper.design — a collaborative canvas for people and AI agents, working in real time with built‑in MCP.
- async-openai: OpenAI in Rust
An asynchronous Rust library for integrating with OpenAI. Fast, safe, and easy to use — ideal for backend development.
- Open Alternative to Semrush and Ahrefs
Free open-source SEO tool for analysis and optimization.
- Mano-P: GUI agent for edge
Open-source GUI-VLA agent for edge devices, #1 on OSWorld (58.2%). Runs locally on Mac mini/MacBook — data never leaves the device.
- SUPERLINKED INFERENCE ENGINE
Open-source server for embedding inference, reranking, and data extraction. 2000+ stars on GitHub.
- AI-ASSISTANT PY-GPT FOR EVERYONE
Desktop AI Assistant based on multiple models: GPT-5, GPT-4, Gemini and others, with voice, vision, RAG, and image generation.
- Document: File Preview in Browser
A simple web tool for quickly viewing and editing common file formats directly in the browser.
- TAPFLOW - Streaming Simulators for Team
Self-hosted streaming of iOS and Android simulators for the whole team. Quickly test UI without real devices.
- RAGHUB: Resources and RAG Frameworks
The community gathers the best RAG frameworks, projects, and materials for AI developers. Contribute and discover new solutions.
- MCP-UNITY: Connect Unity to AI
Model Context Protocol plugin for Unity Editor. Integration with Cursor, Claude Code, Codex, and Windsurf for AI-powered game development.
- wx-cli for WeChat
CLI for working with local WeChat data in Rust with daemon architecture. Project with 2015 stars on GitHub.
- ANY-LLM: One Interface for All LLMs
Python library for unified interaction with LLM providers through a single interface.
- HANDS-FREE VIDEO SHORTS
Full pipeline: news → script → AI visuals → voiceover → subtitles → automatic YouTube Shorts upload
- LOCAL OPEN-SOURCE AI AGENT
Atomic-Chat is a private AI engine for running LLM locally without internet, fully offline on your computer. ⭐ 967 stars on GitHub.
- LLM ENGINE TURNING DOCUMENTS INTO STRUCTURED WIKI
Open-source engine that turns raw documents (PDFs, video, spreadsheets) into a structured local wiki on Markdown. Automatically builds cross-references, detects contradictions, and cites sources.
- LAWS OF ALL COUNTRIES IN GIT
Project stores legislation of all countries as a single git history. Each country is a separate submodule, each commit a law taking effect. 1.7k stars on GitHub.
- VLLM-METAL: ACCELERATING LLM ON APPLE SILICON
vllm-metal is a community‑maintained plugin that brings Metal‑based acceleration to vLLM on Apple Silicon. It uses MLX to run LLMs on macOS with low latency and high throughput, no CUDA required.
- SEO & GEO AI Skills
20 SEO and GEO skills for Claude Code, Cursor, Codex and 35+ AI agents. Keyword research, content, technical audits, and rank tracking.
- OBSIDIAN AI TEXT GENERATOR
The plugin lets you generate text in Obsidian using OpenAI, Anthropic, Google, and local models.