Repository index
6792 AI, ML and Web3 projects · page 34 of 68
- GEMINI WEB API – UNLOCK AI
gemini-web-to-api — a reversed API of the Gemini web app, compatible with OpenAI, Gemini, and Claude keys. Enables using AI as a regular API.
- Mirror and Control iPhone on Linux
Mirror iPhone screen via AirPlay and control it with mouse/keyboard over Bluetooth HID from Linux. Includes CLI for automation.
- AGENT-CI: LOCAL GITHUB ACTIONS
Run GitHub Actions locally for your agents without the cloud. Simplify CI/CD and accelerate development.
- AGENT SKILL: HUMAN-LIKE TEXT REWRITING
Agent skill that removes AI generation markers and rewrites text per ASD-STE100 Simplified Technical English. Works in two passes: removes 26 AI tells, then shortens sentences to one idea in active voice.
- AI AGENTS COMMUNICATE
hcom — a Rust tool that lets AI agents exchange messages, observe, and launch each other via terminals. Supports Claude Code, Codex, Cursor CLI, and others.
- XACTIONS: FULL KIT FOR X/TWITTER
Automate subscriptions, likes, comments and X analytics without API, using CLI and browser scripts.
- SeeSR: Super-Resolution with Semantic Understanding
Model for realistic photo super-resolution preserving semantics and textures (CVPR 2024).
- MAGI‑2‑preview Video Scaling
The project demonstrates efficient approaches to scaling video generation models, enabling training of large diffusion networks on limited hardware resources and obtaining results.
- OPENREALITY 3D SCENES FROM VIDEO
Open Reality converts phone video into AI-queryable 3D scenes. The repository includes MCP‑tools for Claude/Codex/Cursor, a self-hostable broker, and the VGGT‑SLAM library. Licensed under BSD‑2‑Clause.
- DUMPED TOKENS IN THE TRASH 🚀
Ready setup for Claude Code that cuts documentation costs by 90% in 5 minutes. Any project, one script — ⭐ 471 stars, JavaScript.
- AGENT FOR MACOS 26 AI
Agent — AI assistant for macOS 26, controlling the desktop via local and cloud LLMs. Enables task automation, writing scripts and code, interacting with applications. Supports over 18 model providers.
- MCP AGENT FOR HOME ASSISTANT
MCP server lets you control Home Assistant from Claude Code, Cursor, and VS Code. Create automations, dashboards, and edit configs in natural language.
- GPT-HOME SMART HOME ON RASPBERRY
Local chatbot based on ChatGPT, running on Raspberry Pi via LiteLLM and LangGraph. Your smart assistant without clouds.
- Real‑time Robotics Control Framework
Intrinsic Core™ offers a local, hardware‑agnostic runtime and SDK for real‑time control of industrial robots, supporting C++ development.
- NOMI — Integrated AI Video Studio
Open-source desktop application for creating AI videos: script → frame generation → timeline editing → export. Everything runs locally.
- LLMTORNADO: BUILDING AI AGENTS
.NET library with 30+ connectors for rapid AI agent creation.
- WEEKEND AI PROJECTS
A collection of ready starter code and README for quickly creating AI projects over a weekend. Requires Python, an Anthropic API key, and a terminal.
- MOTIONCLONE: VIDEO TO EDITABLE PROJECT
MotionClone rebuilds reference video into editable HyperFrames project. Compares result with original and exports to MP4. 514 stars on GitHub.
- MCP Adapter for Pi Agent
A token‑efficient Model Context Protocol adapter for a coding agent on Raspberry Pi that significantly reduces token consumption when interacting with AI.
- LLM News in Social Science
A collection of outstanding works where language models are applied in social sciences. Perfect for researchers and students.
- Bionic memory for AI
Inspired by biology, a memory system for AI agents: forgetting, strengthening upon retrieval, and consolidation. No dependencies.
- Open Source WhatsApp Business API
Open-source platform for WhatsApp Business API integration in TypeScript — 344 stars.
- Open Web Analytics
Open-source cookie-free analytics that prioritizes privacy and revenue attribution, with a TypeScript MCP server.
- THREE AI AGENTS IN GIT
parallel-code runs Claude Code, Codex, and Gemini in parallel in separate git worktrees and compares the results. 651 stars ⭐
- MIXING RECURSIONS FOR LLM
The Mixture-of-Recursions project offers dynamic recursion depth selection per token in a transformer, enabling adaptive compute allocation. This reduces KV‑cache costs and speeds up inference without losing quality.
- PLAYBOOK FOR BUILDING PROFITABLE AI APPS
Playbook for building profitable AI apps from a developer with 5 projects at $100k+ MRR. Covers path from niche selection to first profitable month with a ready tech stack.
- PROXMOXMCP-PLUS - MANAGE PROXMOX WITH AI
The project uses MCP and OpenAPI for secure management of VMs, LXCs, backups, and snapshots of Proxmox VE via LLMs and AI agents.
- CASBIN-GATEWAY - AI API PROTECTION
Casbin Gateway is an AI- and MCP-oriented security gateway for HTTP traffic with an online demo. Protect APIs in just a couple of clicks.
- HERMES OS: AGENT-LINUX DESKTOP
Herald-OS — an agent-native operating system with the Hermes Agent interface. An independent project, not affiliated with Nous Research, written in TypeScript and running on Fedora, Hyprland, and other Linux environments.
- LEMMA PLATFORM FOR AGENTS
Lemma Platform — a multiplayer harness that adapts to your workflow. Share agents, apps and workflows within your team and launch them from Slack, Telegram, WhatsApp, Teams, Email, Web or your own AI agent.
- Browser LLM Device Pool
Run large open‑source LLMs in the browser by linking multiple devices into a peer‑to‑peer compute pool, enabling chat and coding agents without any server.
- ANTIVIBE - LEARN CODE FROM AI
Claude Code skill that turns AI code into learning breakdowns. Don’t just accept it — understand how it works.
- SHOW-ME-THE-STORY: AI NOVEL
Self-hosted novel generator in Go: a single binary + web UI, compatible with the OpenAI API. It writes chapter by chapter with review, foreshadowing, and fact‑check.
- CCTEAM ONE AGENT TEAM
ccteam unites AI agents (Claude Code, Codex, Grok, DeepSeek Harness, Kimi, Pi) into one team. A session creates tasks, distributing them among providers and collecting results on any machine; control is via Telegram, Lark or a browser.
- VOICE AGENT FOR AI AGENTS
tapq is a voice agent that lets you communicate with Claude Code, Codex and other AI agents via microphone. You can respond to their prompts, give instructions and ask what they did, or just nod.
- KITION: ONE WINDOW FOR AI
Kition combines a Markdown editor, interactive table, whiteboard and AI agent in a single Electron app. Work with data, draw diagrams and get AI answers without leaving your desktop.
- MiniCode — lightweight terminal assistant
A lightweight terminal assistant for coding with a TUI architecture and tool loop, inspired by Claude Code. Implemented in TypeScript, Python, and Rust.
- PASTEGUARD - YOUR SECRETS SAFE
Open-source proxy for LLM that gives AI context, not your secrets.
- DOUBLE CLOUD CODE
headroom-desktop written in Rust lets you double the usage limits of Claude Code and Codex. More agents, fewer restrictions.
- OPEN SOURCE IDE FOR C# AND .NET
Passenger — cross-platform IDE on Avalonia with Roslyn editor, own debugger with Hot Reload, CPU/memory profiler, and MCP server for AI agents.
- OPENTABS — AUTOMATION ON STEROIDS
Browser automation without clicks: OpenTabs calls APIs for you. 644 stars on GitHub.
- Smart Screen Streaming to AI
Capture and stream screen content to AI efficiently by filtering unchanged frames and combining multiple frames into single images, minimizing token usage.
- SANDBASE-HARNESS: POWERFUL AGENT
An open runtime agent compatible with CMA, supporting MCP tools, sandboxes, auditing and session replay, as well as a local console.
- MANAGE EVERYTHING VIA AI
Hub for managing WPS, MS Office, Photoshop, and Zotero via an AI agent. 47 CLI commands, 27 academic skills, and SVG-to-PPTX.
- MCP-REDIS: AI FOR REDIS
The official MCP server for Redis provides a natural language interface, enabling agents to manage and query Redis data without code.
- PRIVATE CHAT AI
Local AI chat in the browser using WebGPU and WebLLM, with no servers or cloud data.
- PAPERFORGE — AI SCIENCE IN ONE
PaperForge automates the entire scientific paper writing process: idea generation, literature search, experiments, and LaTeX compilation.
- iOS Agents for Developers
Agent skills for iOS 26+, Swift 6.3, and SwiftUI. Accelerate development with modern Apple tools! ⭐640
- Loopy: CPU & GPU Generator
Loopy automatically generates bulk code for CPUs and GPUs in Python. 631 stars on GitHub.
- ATRIA-DAWN: LLM AGENT OF NEW GENERATION
Atria-Dawn is a framework for autonomous LLM agents with memory, planning and tool invocation. It lets you quickly assemble workflows without boilerplate code. Supports any model via a standard API.
- Claude Video Vision
A plugin for Claude Code that enables video analysis: extracting key frames and performing multimodal audio analysis.
- VIBE‑CHECK: FROM IDEA TO CODE
The project helps beginners turn a vague idea into a ready-to-build plan, teaching GitHub basics, clean code, and the check‑iterate cycle.
- CLOUD-RUN-MCP: DEPLOY TO CLOUD RUN
MCP server for deploying applications to Google Cloud Run. Automate deployments with AI agents and JavaScript.
- VENDO - AGENTS FOR BUSINESS
The vendo platform provides embeddable AI agents that automate tasks, create views, and connect client tools.
- MARMOT - Context Layer for AI
Marmot is an open context layer for AI agents that lets you catalog tables, topics, queues, and APIs and provides real‑time metadata.
- Repo for LLM Unlearning
A collection of papers, code, and resources on machine 'unlearning' in large language models. Helps researchers remove knowledge from LLMs.
- SECURE ACCESS TO MCP
tunnel-client — a client for securely connecting local MCP servers to ChatGPT, Codex, Responses API, and AgentKit without exposing them to the public internet.
- OS PLATFORM AI AGENTS
os — framework for creating AI agents: LLM support, real-time chat and voice, document training, analytics, user management, SSO and widgets. Built with React 19, Redux Toolkit, Radix UI and Tailwind CSS.
- NODETOOL: YOUR AI WORKSPACE
Open workspace for creative AI: create, edit, and share models right in the browser.
- ENVKIT: Local Development Environment
EnvKit — free local environment for Windows/macOS with nginx, multiple PHP versions, MySQL/MariaDB, PostgreSQL, Redis, MongoDB, Mailpit, Node.js and trusted .test HTTPS.
- PULSE: MONITOR OF AI ASSISTANT QUOTAS
Pulse — a floating macOS monitor showing remaining quotas of Claude Code, Codex, Antigravity, OpenCode Go and Kimi Code. Written in Swift using AppKit, it updates data in real time via each service's API.
- Open-Source AI Anime Companion
Open-source AI companion featuring Live2D avatar, real-time voice chat, long-term memory, and support for OpenRouter or local Ollama models.
- AI firewall for MCP
Open AI-agent firewall for MCP protection: outbound request control, DLP, SSRF and prompt injection defense.
- BEST LIST OF AGENT SERVICES
Awesome‑agent‑native‑services — a curated list of services for AI agents: email, browsers, memory, sandboxes, payments and MCP tools. The repository includes selection criteria and step‑by‑step guides for integrating each component.
- TRUSTLLM: EVALUATION OF LLM TRUSTWORTHINESS
TrustLLM — a toolkit for assessing LLM trustworthiness, presented at ICML 2024. It includes benchmark suites, metrics, and datasets for measuring hallucinations, bias, and answer reliability.
- 3D ENGINE DRIVEN BY AI AGENTS
Crucible — 3D engine in JavaScript driven by AI agents via code. Integrated with Blender and Claude Code for scene generation. 633 stars on GitHub.
- Pets for AI Agents
Desktop pets for programming AI agents. Connect Claude Code via MCP and watch your coding status right on the desktop.
- nWave: AI Agents for Coding
AI agents that guide you from idea to working code. You stay in control of every development step.
- OLD PHONE INTO PC CONTROL PANEL
PhoneBox turns an old Android phone into a local monitoring and control panel for Windows, Linux, and macOS. Connects via USB or Wi-Fi without cloud, displays 115 widgets: PC resources, AI sessions, media, weather, and webhooks.
- LIBRETTO: AI Browser Automation
A reliable AI toolkit for automating browser actions in TypeScript. 634 stars.
- LLM-BASED BANK AUTOMATION
AI automation of bank statements and personal financial analysis with predictions. 583 ⭐ on GitHub.
- TOUCHDESIGNER ARRIVES ON MCP
MCP server for integrating TouchDesigner with AI agents. Control visual projects directly through language models.
- DOCKER SKILLS FOR AI AGENTS
The project provides AI agents with ready‑made Docker skills for building, testing, debugging, and optimizing containers. Workflows are standardized and reusable, cutting the time to production.
- ZEPTOCLAW - LOCAL AI ON RUST
Fast personal AI assistant in a single Rust binary: tools, memory, communication channels, and autonomous sandbox mode. 633 ⭐
- OLLITERT LLM SERVER ANDROID
OlliteRT turns your Android smartphone into a local inference server compatible with the OpenAI API. It works completely offline, ensuring privacy and open-source code in Kotlin.
- COCO Superintelligent Agent
Coco — a framework with a council of 389 experts, 142 skills, and 277 teams for a full‑fledged AI department.
- Per-Project Development VMs
Creates isolated VM sandboxes per project with pre-configured toolchains for human or AI-assisted coding.
- RUSTUNNEL: Rust Tunnel
Self-hosted tunnel server in Rust. Expose local HTTP/HTTPS/TCP/UDP services to the internet via TLS‑encrypted WebSocket.
- CYRUS — DEVELOPMENT AGENT
Cyrus — a background agent based on Claude Code, integrating Linear, Slack, GitHub, and GitLab. It supports Codex, Cursor, and Gemini to accelerate development.
- OPTIMUM-INTEL - ACCELERATE INFERENCE WITH INTEL
Optimum Intel provides Intel tools to accelerate AI model inference, simplifying deployment and boosting performance.
- TINTE Agent Design System
Create, compile, install, and preview design systems from a single source of truth.
- BEST SELF-IMPROVING AGENTS LIST
A curated collection of resources on agent self-improvement based on foundation models. Ideal for AI researchers and developers.
- HERMES OFFICE: AI SUITE FOR DOCUMENTS
HermesOffice is an AI‑native office suite (Docs, Sheets, Slides, PDF) with the Hermes Agent as its brain. It preserves document bytes unchanged, works fully locally, and supports open standards.
- CREATE YOUR AI TWIN
agent-me lets you turn your knowledge, memories, and decisions into an open, inspectable AI‑agent twin. The project is written in Python and uses a knowledge graph for storing and retrieving information.
- Architect Loop
Research skill for Claude Code that unites Claude Fable 5 architect and GPT‑5.5 Codex builder via the repository as memory.
- CLOVE IN YOUR CODE
A plugin for OpenCode that connects your Claude Max/Pro subscription via Meridian. 320 stars and gaining popularity.
- NANOLANG – Language for LLM Coders
Minimal experimental language in C, created specifically for LLM code generation.
- LLM DIRECTLY IN TERMINAL
Fast stateless LLM for the shell. The qq command answers questions, qa executes commands, written in lightning‑fast Rust.
- Talos worker client
GPU worker client for the Talos network. It connects to your account, receives open‑model inference tasks via WebSocket, and reports uptime for reward calculation.
- PANE: MANAGE MULTIPLE AGENTS
Pane — open-source manager of AI agents for any CLI agent, any OS. Run locally or self‑host Remote Pane to control agents from desktop or phone via runpane CLI.
- ABIDE: FOLLOW ALL RULES
Abide makes your coding agent follow all project rules: linting, formatting and custom checks run automatically before each action. It integrates via Claude Code hooks and provides ready‑made skills for common conventions.
- Claude Code from USB
Run Claude Code from a USB drive on any PC without installation. Already over 600 stars — an open portable tool for developers.
- PI-LLM-WIKI - TURN SOURCES INTO WIKI
The project turns raw materials about the number π into a self‑sustaining Obsidian‑compatible wiki in OKF v0.2 format.
- AI agent with wallet
Franklin is an autonomous AI agent that spends USDC on its own to perform real‑world tasks. Apache-2.0, TypeScript.
- MOTIS - Multimodal Navigation
Motis provides multimodal routing, geocoding, and vector map tiles in C++.
- RKLLAMA — LOCAL AI ON ROCKCHIP
Ollama alternative for Rockchip NPU. Run AI and Deep Learning models directly on Rockchip devices with NPU optimization.
- MEMORIA — MEMORY FOR AI AGENTS
Safe memory management for AI agents on Rust. Protection of data integrity, fewer hallucinations, stable long-term context.
- SEO: 70+ Tools in CLI
Local CLI and MCP server give you access to 70+ SEO tools using your own crawler, Search Console, and GA4 data.
- INTERCEPTOR: AI AGENT IN BROWSER
Interceptor provides a single, powerful CLI and MCP‑server that enables AI agents to control a signed‑in browser, native macOS applications and a genuine iPhone. It supports automation of input, clicks and scripts without extra drivers now.
- OPEN AI CHAT WITH PLUGINS
An open collection of plugins for Open WebUI: tools, skills, filters, pipes, actions and events that extend your AI chat's capabilities.