Repository index
6792 AI, ML and Web3 projects · page 44 of 68
- LangChain Meets Google AI
🦜🔗 Library for integrating LangChain with Gemini and Vertex AI. 388 stars on GitHub.
- WRONGSTACK — AI CODE AGENT
An AI agent that reads your code, edits files, runs commands, and finds bugs in the terminal, TUI, and browser, leaving permission control with you.
- AI REDTEAM AGENTS PLATFORM
AI red‑team platform: autonomous LLM agents perform a full pentest in an isolated Kali container and generate a report. LangGraph plan/act engine, models via LiteLLM, output PDF/JSON/SARIF, interface FastAPI + React.
- OK-SKILLS: AI AGENTS FOR CODE
A collection of ready-made skills and AGENTS.md playbooks for Codex, Claude Code, Cursor and other tools compatible with SKILL.md.
- AGENT PRISM: AI AGENT TRACES
React components in TypeScript for interactive visualization of AI agent traces.
- PI-DESKTOP: AI AGENT FOR CODING
Free open‑source Electron client for working with Pi and oh‑my‑pi AI agents. Lets you chat, edit files, run a terminal, and view diffs in a single window. Supports Linux, macOS, and Windows.
- TMUX PLUGIN FOR CLAUDE CODE
tmux‑claude‑hatch launches Claude Code in separate tmux pop‑up windows for every project and displays their status via the fzf selector. The bell highlights the tmux pane that requires your attention.
- AI AGENT TEAM ON YOUR COMPUTER
tucano runs an AI agent team locally on Mac, Windows, or Linux. Agents chat in channels, write and review code, use your tools via Claude Code, Codex, or OpenCode. Any real-world actions wait for your approval.
- OUTPUT AI Agent Framework
Open TypeScript framework for building AI workflows and agents. Just describe what you need — Claude will assemble everything with best practices.
- AGENTLENS: VERIFY AGENT BEFORE HIRE
Decentralized audit protocol and marketplace for AI agents with TEE attestation, MDDRM reputation registry, and SGX/DCAP-based sandbox.
- BMALPH — AI Framework 387 stars
Unified AI Development Framework with BMAD phases and Ralph execution loop. A TypeScript project for structured AI development.
- ANDROID LUMO: SHINES
Android app that integrates with Proton Lumo, providing secure messaging and real-time encryption.
- BAGEL - Chat with Robot Data
Bagel enables dialog with drone, robot, and IoT device data in natural language, like ChatGPT for the physical world.
- MIRA: Autonomous AI Code Review
Mira is a self-hosted AI code reviewer with PR indexing, vulnerability scanning, and custom rules.
- OH-MY-CPA SELF-HOSTED AI GATEWAY
Self-hosted control plane and usage observability console for CLIProxyAPI (CPA). Connect AI providers, manage client keys, get streaming telemetry and model cost snapshots.
- XIANTU: PATH OF THE IMMORTALIST
A text-based cultivation quest powered by AI, built with Vue 3, TypeScript, and FastAPI, supporting Gemini, Claude, and OpenAI.
- PI-AGENT DESKTOP CLIENT
Desktop client for the Pi AI agent with streaming timeline, Git review with staged hunks and session tree. Native UI for Pi extensions runs on Windows, macOS and Linux, written in TypeScript, already 361★.
- DIABLO II ON IPHONE AND ANDROID
Port of Diablo II: Resurrected for iOS, macOS, and Android. Offline play, touch controls, one-tap Runewords, 100 Greater Rift levels. Metal on Apple, Vulkan on Android. Requires your own Switch game dump.
- SWE-ATLAS: CLAUDE CODE BECOMES SENIOR
SWE-ATLAS turns Claude Code into a senior AI agent: multi-project workspaces with memory, wireframe-first planning, secrets out of chat, browser QA runners, and CI/CD-aware deploys. One command: npx swe-atlas new-project
- CLAUDE CODE MODERNIZES RAILS
Claude skill for automatically upgrading Rails applications via AI. Speeds up version migration and code refactoring.
- SMART WEB SEARCH SERVER
The server provides fast web search and reliable content extraction for AI coding assistants and agents.
- ZERAIX: LOCAL AI DESKTOP
Local open-source environment for running AI models on device. Speeds up inference without cloud.
- SWYTCHCODE EXAMPLES: AGENTS IN ACTION
A collection of Swytchcode demo projects showing the work of different AI agents in TypeScript. Easy to start and adapt to your tasks.
- ALL LLMS IN ONE API
Gateway to Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen and Kimi with one key. Supports uncensored and abliterated model variants. Compatible with OpenAI and Anthropic APIs, pay per token.
- iOS MCP: AI DEVICE CONTROL
MCP tool for jailbroken iPhones — allows AI agents and developers to inspect and control devices. 404 stars ⭐
- STARTUP-SKILL: AI Agent for Startups
The platform provides AI‑agent skills for idea validation, competitive analysis, and startup planning.
- ADAPTIVE CHUNKING FOR RAG
Automatically selects the optimal chunking method for each document to improve RAG pipelines. Accepted at LREC 2026.
- PLANEXE: CREATE PLAN IN MINUTES
Turn a task description into a ready action plan in minutes with a Python AI agent.
- CURATED FINTECH LIBRARIES LIST
Collection of 370+ open source libraries for payments, banking, and financial infrastructure. Saves hours of searching for ready solutions.
- BUILDER SKILLS FOR CONVEX
Builder Skills provides ready‑made PRD, task.md, changelog and files.md templates for Convex, ready for use in Claude Code, Codex, Cursor and OpenCode.
- HUMANIZE AGENT FLOW TOKENS
Humanize — agent‑flow system for maximum token usage in LLMs. It orchestrates Claude Code and Codex calls, managing reasoning streams and cutting redundant requests via caching.
- Agent Communication over Tailscale
Enables agents to exchange messages, share data and files, and trigger wake‑ups via Tailscale network connections.
- COLLABORATION LAYER FOR AI AGENTS
Rhesis — platform for testing, simulating, and tracing AI agents. Experts annotate behavior, engineers improve agent based on found issues. Closes feedback loop between team.
- BETTER AGENT TERMINAL AI
Multi-window terminal with Claude Code AI integration for convenient work on multiple projects simultaneously.
- ZENITH — MULTI-AGENT MISSION
Zenith turns Claude Code, Codex, or Hermes into a multi-agent orchestrator for long-running tasks.
- ENTROLY - 80% SAVINGS ON AI
Entroly compresses AI context, detects hallucinations, and saves up to 80% on API costs for OpenAI, Anthropic, and Gemini.
- DESKTOP ASSISTANT FOR LINUX
Unofficial Claude Desktop packages for Linux with automatic updates. 402 stars.
- LLM Wiki Knowledge Base
Collects knowledge from your sessions with Claude Code, Codex, Copilot, and Gemini into a single base inspired by LLM Wiki by Karpathy.
- AI CONTROLS YOUR PC
MCP server giving AI full control over the computer. Cursor, files, terminal — all in the model's hands.
- CONTEXT-ENGINE CONTEXT COMPRESSION
Context-Engine MCP compresses agent prompts, boosting LLM efficiency without losing meaning. It supports Python and is ready for integration.
- OVERTIME: AGENT FOR GAME DEVELOPMENT
Project overtime lets you give a brief technical task to an AI agent, after which the agent autonomously performs work in subsequent sessions. In the demo, it built an open city in Unreal Engine without human involvement.
- MCP SERVER FOR MASSIVE.COM
MCP server provides access to Massive.com financial market data in real time. It streams price, volume, and indicator updates for crypto and traditional assets. The data can be integrated into LLM‑applications via the MCP interface.
- AI AGENTS IN LIVE OFFICE
Three.js dashboard shows every Claude Code and Codex agent activity. See what agents are doing right in the browser — like a real office.
- PRISMANTIS: 15 THEMES FOR CLAUDE CODE
Prismantis beautifies Claude Code replies: tables, code, diagrams, charts and tool rows in 15 themes with copy buttons. TypeScript mod for terminal.
- PERSONAL AGENT FOR LIFE
life-distributable — a personal agent running 24/7 on your Mac. Installs with one phrase in Claude Code. Written in Go with SwiftUI interface.
- Claude Plugin for Elixir
Claude Code for Elixir/Phoenix/LiveView: 20 agents, parallel research and auto code verification.
- DUCTOR: CONTROL AI FROM TELEGRAM
Control Claude Code, Codex CLI and Gemini CLI straight from Telegram: live stream, memory, cron‑tasks, webhooks and Docker sandbox.
- MCP SERVER FOR AZURE DEVOPS
MCP server for Azure DevOps gives AI agents access to work items, pipelines and repositories via MCP, enabling seamless instant interaction with tasks, PRs and builds!!
- SPEAKOFLOW: OFFLINE DICTATION WITH AI
Offline dictation tool for Windows, macOS and Linux — an alternative to Wispr Flow. It includes an AI assistant that, on request, reads the screen and answers questions. Everything works locally, with no data sent to the cloud.
- ImageIndexer: Auto-tagging photos via LLM
It indexes images, sends requests to a local LLM, and automatically adds tags to file metadata.
- GPTPortal: LLM Chat Web App
Lightweight Node.js application for chatting with GPT-4, Claude, Gemini, Mistral, and OpenAI Assistant via a single web interface. Supports voice, images, and files.
- WP-AUTOPLUGIN: PLUGINS WITHOUT EXTRA
Create functional WordPress plugins in minutes — just describe the needed function, with no extra code or hassle.
- WIRESHARK‑MCP: AI PACKET ANALYSIS
The project lets you upload a .pcap file and ask questions in plain language. Answers are based on tshark data, providing accurate network traffic analysis. Integration with MCP turns the AI assistant into a full‑featured packet analyzer.
- OPEN VOICE+VISION FOR AI
OpenLive — open on‑device voice+vision layer for AI agents. Supports any model or coding agent; the full speech loop (VAD, STT, TTS, barge‑in) runs locally — an open alternative to ElevenLabs, Gemini Live and OpenAI Realtime.
- Launch Sega with Debugger
A cross-platform emulator for Sega Master System, Game Gear, and SG-1000 with a debugger and built-in MCP server. Runs on macOS, Linux, Windows, and RetroArch.
- MARS: REST FRAMEWORK FOR DELPHI
MARS — REST framework for Delphi in JAX‑RS style: resources, routes, servers and clients, JWT, OpenAPI 3, database access via FireDAC/Devart and MCP servers for AI agents. Supports Windows, Linux and Docker.
- LLM THROUGHPUT BENCHMARK IN OLLAMA
Tool for measuring local LLM throughput via Ollama. Runs load tests and outputs tokens-per-second statistics.
- LIGHTWEIGHT CLI AGENT FOR CODE AND SSH
Memdoor is a lightweight coding and automation agent in a single CLI binary. Supports multi-agent workflows and runs locally or over SSH. Written in Go.
- MCP Flutter: AI Code Agent
The MCP toolkit for Flutter provides visual and semantic snapshot feedback, enabling the AI agent to guide development.
- VOICE AI ASSISTANT JARVIS
A voice assistant in Python featuring speech recognition, web search, image generation, and WhatsApp control.
- Unity Dev Agent
Open tool to assist developers in Unity.
- WORLD SIMULATION IN AI
Large-scale survey of multimodal generative models for real-world simulation. 381 stars, IEEE TPAMI 2026.
- OPENAI-TRANSLATOR - INSTANT AI TRANSLATOR
An OpenAI-based translator that instantly translates text into any language with high accuracy.
- File system for agents
File system specially developed for AI agents, featuring cutting-edge search, automatic memory profiles, and synchronization. Upload any file types and instantly find what you need.
- CLAUDE CODE FOR SCIENCE
Skills, agents, and guides for configuring Claude Code for academic research. 396 stars on GitHub.
- SUPRESEO CLAUDE SKILLS
11 Claude skills for SEO: page audits, link building, article writing, E‑E‑E‑T audit and semantic gap analysis. Methodology based on Koray Tuğberk, Kyle Roof and Lily Ray approaches, supplemented with anti‑AI‑slop rules at generation time and tested at InhouseSEO.
- KEEP CLAUDE CODE CACHE WARM
cache-tax keeps Claude Code's prompt cache warm during breaks and shows estimated cost before a cold send. Saves tokens and money when working with large contexts.
- CHATGPT BECOMES A LOCAL AGENT
openchatx-mcp turns ChatGPT into a local AI agent runtime. Control your computer, run local tools, discover MCP servers, and delegate tasks to your own models through a single MCP connection.
- CREATE BRAND WITH CLAUDE
Claude Code skill designs a brand identity as one system: logo, typography and colour palette generated from one brief. Results measured compared as identity cards and delivered as brand guidelines kit.
- ZINC - LOCAL LLM ON GPU
Zinc is an LLM inference engine in Zig that runs on AMD GPU and Apple Silicon without external dependencies.
- COTABBY AI AutoComplete Mac
Local AI autocomplete for your entire Mac — works offline everywhere you type, with open-source Swift code.
- Ktx — Context Layer
Ktx provides a universal context management layer for AI agents, allowing storing, updating, and sharing state across various modules and services.
- Local Kubernetes on Apple
The kiac project provides a local Kubernetes cluster, where each node runs in a lightweight virtual machine based on Apple's container framework. It includes metrics, storage, and load balancing.
- MARVIS RISK AGENT: AI CREDIT
Universal AI agent for credit risk: from model development to strategies.
- OPEN-WEBUI-FUNCTIONS: AI Extensions
A collection of pipelines and filters for Open WebUI that enables connecting Azure AI, N8N, Gemini and automating queries.
- CONTROL GOOGLE FLOW FROM THE COMMAND LINE
gflow-cli runs Veo videos and Imagen images from the terminal: via scripts, batches, and pipelines. The MCP server gives AI agents full programmatic control over generation. Unofficial alpha project, not affiliated with Google.
- Remote Model, Local Tools for Claude Code
Run Claude Code with the LLM hosted on a remote server while keeping file operations and tools executing locally on your machine.
- READY SKILLS FOR CLAUDE
Repository with ready-to-use skills to extend Claude capabilities. Contains scripts for task automation, code work, and data analysis. 276 stars on GitHub.
- LOCAL MCP CONTROL PLANE FOR WEB AI
Local MCP controller connecting web assistants to files, terminal, and Git. Executes tools on user machine with permission control.
- Context Management for LLM
A tool for assembling context from an entire repository, files, or Issues into structured XML with token counting for long contexts and agents.
- AI Image Extender
A TypeScript web app that uses Gemini via OpenRouter for AI image extension in any direction with seamless Poisson blending and selection of the best of three variants.
- EvoSkills: SKILLS FOR AI SCIENTISTS
🧬 Expanding EvoScientist — installable skill and knowledge packages for your AI agents.
- EDDI: AI Agents from JSON
Quarkus engine turns JSON into ready AI agents with support for 12+ LLM, RAG, and enterprise security.
- CLAUDE-AUTO-RETRY: Instant Retry
Automatically retries Claude requests when hitting limits or encountering 529/5xx errors. It waits for limit reset, uses exponential backoff, and supports tmux.
- 100 CLAUDE CODE RECIPES
A collection of 100 tested Claude Code recipes: ready-made prompts, step-by-step instructions, and six skills for instant installation.
- COMPANION FOR SYSTEM DESIGN
Free open-source repository supplementing the Grokking the System Design Interview course. Materials and examples for preparing for system design.
- Unified RSI Research Platform
A unified Python framework accelerating recommender system research with efficient training, evaluation, and deployment tools.
- Prompt Hacking Course
The most complete course on prompt engineering and LLM attacks: from basics to advanced hacking and defense techniques.
- AI Agent Skills Evaluator
An automated framework for testing and evaluating the performance of AI agents in the agentskills.io format.
- CLAUDE-CODE-USAGE-BAR LIMITS MONITOR
Shows Claude Code usage limits in the status line: hours/week, countdown, model and context window, prompt cache age — all in one line, 3 styles × 9 themes, fast daemon.
- Streaming Markdown for iOS
A fast library for rendering Markdown with streaming support. Ideal for iOS apps.
- MCP-EMAIL-SERVER - EMAIL VIA MCP
The server provides IMAP and SMTP protocols via MCP, simplifying email integration into AI agents.
- CODEXLOOM Domain Agents
Transform Codex chains into resilient agents that operate seamlessly in your domain.
- DEX YOUR AI HR CHIEF
Dex is your personal AI chief assistant, ready to work without writing code. The Python starter kit adapts to your role and tasks.
- CRIT - IMPROVE YOUR FEEDBACK LOOP
Crit is a tool for fast feedback with an AI agent, simplifying development and testing of code.
- ADMINFORTH: BUILD ADMIN PANELS FAST
Create agentic admin panels with TypeScript and Vue.js in minutes using AdminForth Framework. Quick CRUD page setup and easy extension for any task.
- AI FOR WORDPRESS: MODULAR FRAMEWORK
A set of AI modules for WordPress: test and deploy AI features without unnecessary complexity.
- AGENTIC AI ENGINEERING: PRACTICES, EXAMPLES
Practical guide to creating AI agents from scratch: LLM API, prompt engineering, tool calling, agent loop.
- COTAL: OPEN STANDARD FOR AGENTS
Cotal is an open standard for coordinating AI agents, defining a communication protocol and forming dynamic agent meshes. It enables skill discovery, composition, and management of agent workflows in TypeScript.
- CUSTOMIZATION LLM VIA LOGITSPROCESSOR
A set of LogitsProcessors for LLM behavior tuning. Solves specific tasks without changing model architecture.