16 CURATED AI REPOSITORIES • MCP SERVERS • ONE-CLICK CONFIGS

Trending GitHub AI Projects & Agentic Tools

Curated breakout open-source repositories for AI workflows. Simple explanations, why they matter, and instant copy-paste configs to connect them with Claude Desktop, Cursor, and AI agents.

Catalog of 16 Projects
MCP Servers
⭐ Trending 2026 GitHub ↗

REA (Reverse Engineer Anything)

morluto/rea

Model Context Protocol (MCP) server bridging AI coding agents (Claude Code, Cursor, Codex) with reverse-engineering engines to inspect binaries, APKs, Electron apps, and web frontends.

💡 Why it matters:

Empowers AI agents to understand proprietary binaries, trace execution paths, recover architectural graphs, and debug compiled applications without source code.

⚙️ How to connect to AI: MCP Config

Add to your Claude Desktop config (claude_desktop_config.json) or Cursor Settings → MCP.

Config JSON / Script
{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": [
        "-y",
        "rea-agents",
        "mcp"
      ]
    }
  }
}
#mcp #reverse-engineering #binary-analysis #claude-code #cursor
Agents & Automation
⭐ 118k+ GitHub ↗

Browser-Use

browser-use/browser-use

Open-source web automation library and agent enabling LLMs to natively control web browsers, fill forms, navigate pages, and extract data.

💡 Why it matters:

Translates plain English instructions into real browser actions — clicking elements, handling auth, and executing complex workflows autonomously.

⚙️ How to connect to AI: Python SDK

Install via pip and pass natural language tasks to the Agent object with your preferred LLM.

Config JSON / Script
from langchain_openai import ChatOpenAI
from browser_use import Agent
import asyncio

async def main():
    agent = Agent(
        task="Найди на GitHub трендовые репозитории по MCP и сохрани в файл",
        llm=ChatOpenAI(model="gpt-4o"),
    )
    await agent.run()

asyncio.run(main())
#agents #browser-automation #playwright #web-navigation
Scraping & RAG
⭐ 80k+ GitHub ↗

Crawl4AI

unclecode/crawl4ai

Open-source, LLM-friendly web crawler and scraper designed to feed clean, structured Markdown into RAG pipelines and AI agents.

💡 Why it matters:

Eliminates HTML boilerplate and navigation menus, delivering pristine Markdown to minimize token usage in vector databases and agent context windows.

⚙️ How to connect to AI: CLI / NPX

Run locally in Python or deploy as an MCP server to supply live web content directly to your coding assistant.

Config JSON / Script
import asyncio
from crawl4ai import AsyncWebCrawler

async def main():
    async with AsyncWebCrawler(verbose=True) as crawler:
        result = await crawler.arun(url="https://news.ycombinator.com")
        print(result.markdown[:1000])

asyncio.run(main())
#scraping #markdown #rag #crawler #llm-friendly
Local LLMs
⭐ 125k+ GitHub ↗

Ollama

ollama/ollama

Get up and running with large language models locally. Run Llama 3, DeepSeek-R1, Mistral, and custom models in one command.

💡 Why it matters:

100% private and offline inference on consumer GPUs/CPUs without telemetry or subscription fees.

⚙️ How to connect to AI: CLI / NPX

Download from ollama.com or run the CLI command to start chatting immediately.

Terminal Command
ollama run deepseek-r1:8b
#local-llm #offline-ai #deepseek #llama3 #gpu-acceleration
MCP Servers
⭐ 75k+ GitHub ↗

Official MCP Reference Servers

modelcontextprotocol/servers

Official reference implementation of Model Context Protocol servers by Anthropic: Filesystem, GitHub, Postgres, SQLite, Slack, and Fetch.

💡 Why it matters:

Equips coding assistants with standardized access to filesystems, databases, and third-party developer APIs out of the box.

⚙️ How to connect to AI: MCP Config

Paste snippet into your claude_desktop_config.json or Cursor/Windsurf MCP configuration settings.

Config JSON / Script
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "C:/Projects"
      ]
    },
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}
#mcp #anthropic #filesystem #postgres #sqlite #fetch
Developer Tools
⭐ 20k+ GitHub ↗

FastMCP

jlowin/fastmcp

The fastest, cleanest Python framework for building Model Context Protocol (MCP) servers using simple function decorators.

💡 Why it matters:

Transforms Python functions into fully documented MCP tools with automatic schema validation and type hint inference.

⚙️ How to connect to AI: Python SDK

Save as server.py and run via `fastmcp dev server.py` or inspect with the MCP inspector.

Config JSON / Script
from fastmcp import FastMCP

mcp = FastMCP("MyAssistantTools")

@mcp.tool()
def calculate_vat(amount: float, rate: float = 22.0) -> float:
    """Вычисляет сумму НДС по заданной ставке."""
    return round(amount * (rate / 100), 2)

if __name__ == "__main__":
    mcp.run()
#mcp #fastmcp #python #fastapi-style #tools
UI & Clients
⭐ 105k+ GitHub ↗

Open WebUI

open-webui/open-webui

Extensible, feature-rich, and self-hosted WebUI for LLMs supporting Ollama, OpenAI-compatible APIs, document RAG, and multi-user chat.

💡 Why it matters:

Turnkey self-hosted ChatGPT replacement with document Q&A, role-based access control, and seamless Ollama integration.

⚙️ How to connect to AI: Docker

Launch the Docker container and visit http://localhost:3000 in your browser.

Terminal Command
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
#ui #chatgpt-clone #docker #rag #ollama-webui
Memory & Context
⭐ 68k+ GitHub ↗

Mem0 (The Memory Layer for AI)

mem0ai/mem0

Universal memory layer for AI agents and assistants. Stores user preferences, session history, and semantic facts across interactions.

💡 Why it matters:

Provides persistent personalization so agents remember developer habits, stack constraints, and domain preferences across turns.

⚙️ How to connect to AI: Python SDK

Import into your agent workflow and call memory.add() / memory.search() to ground prompts.

Config JSON / Script
from mem0 import Memory

m = Memory()
# Сохранить факт о пользователе
m.add("Пользователь предпочитает Astro 5 и Tailwind CSS", user_id="rashid")

# Получить релевантный контекст перед ответом
memories = m.get_all(user_id="rashid")
print(memories)
#memory #context #personalization #vector-memory
Agents & Automation
⭐ 46k+ GitHub ↗

OpenHands (ex-OpenDevin)

All-Hands-AI/OpenHands

Autonomous AI software development agent capable of writing code, running bash commands, executing tests, and debugging in sandboxed containers.

💡 Why it matters:

Acts as an autonomous pair programmer that executes real commands inside an isolated Docker sandbox.

⚙️ How to connect to AI: Docker

Run the official Docker container and navigate to http://localhost:3000.

Terminal Command
docker run -it --rm -p 3000:3000 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/all-hands-ai/openhands:latest
#agents #software-engineer #autonomous-coding #docker-sandbox
Developer Tools
⭐ 42k+ GitHub ↗

Cline (Autonomous VS Code Agent)

cline/cline

Autonomous coding agent for VS Code with terminal execution, browser testing, and custom MCP server tool integration.

💡 Why it matters:

Enables safe, human-in-the-loop autonomous programming right inside your existing editor and workspace.

⚙️ How to connect to AI: CLI / NPX

Install the Cline extension in VS Code via the marketplace or the CLI command.

Terminal Command
code --install-extension saoudrizwan.claude-dev
#vscode-extension #autonomous-coding #mcp-support #developer-assistant
Agents & Automation
⭐ 106k+ GitHub ↗

Dify

langgenius/dify

Open-source LLM app development platform combining agentic workflows, visual orchestration, RAG pipelines, and model management.

💡 Why it matters:

Build production-grade AI agents and RAG assistants using an intuitive visual flowchart interface.

⚙️ How to connect to AI: Docker

Clone the repository and launch the full stack via Docker Compose.

Terminal Command
git clone https://github.com/langgenius/dify.git && cd dify/docker && docker compose up -d
#agents #visual-workflow #rag-pipeline #enterprise-ai
Local LLMs
⭐ 48k+ GitHub ↗

vLLM

vllm-project/vllm

High-throughput, low-latency LLM serving engine featuring PagedAttention for production model deployments.

💡 Why it matters:

Production standard for serving open-weights LLMs with massive concurrency and OpenAI API compatibility.

⚙️ How to connect to AI: Python SDK

Run the CLI command to launch a local server compatible with OpenAI endpoints.

Terminal Command
pip install vllm && python -m vllm.entrypoints.openai.api_server --model Qwen/Qwen2.5-Coder-7B-Instruct
#inference #gpu #paged-attention #openai-compatible #high-throughput
Developer Tools
⭐ 23k+ GitHub ↗

Composio

ComposioHQ/composio

Production tooling platform providing 250+ pre-built integrations (GitHub, Slack, Google, Jira) for AI agents and LLMs.

💡 Why it matters:

Manages user auth, OAuth2 flows, and permissions so AI agents can reliably act on external SaaS tools.

⚙️ How to connect to AI: Python SDK

Install the Python SDK and execute `composio add <tool>` to equip agents with integrations.

Terminal Command
pip install composio-core
#integrations #oauth2 #agent-tools #saas-connectors
Developer Tools
⭐ 25k+ GitHub ↗

Agent Skills (skills.sh)

anthropics/skills

Open catalog and specification for agent skills (`SKILL.md`) enabling plug-and-play capability extensions for coding agents.

💡 Why it matters:

Equips coding assistants with specialized domain expertise, best practices, and repeatable workflows via `npx skills add`.

⚙️ How to connect to AI: CLI / NPX

Use `npx skills add <owner/repo@skill> -y --copy` to equip agents with pre-built skills.

Terminal Command
npx skills find react
#skills #agent-skills #coding-agents #claude-code #best-practices
Scraping & RAG
⭐ 38k+ GitHub ↗

RAGFlow

infiniflow/ragflow

Next-generation open-source RAG engine based on deep document understanding of complex PDFs, tables, and multi-format docs.

💡 Why it matters:

Preserves document layout, complex tables, and visual structure to eliminate hallucinations in technical document Q&A.

⚙️ How to connect to AI: Docker

Deploy via the official docker-compose stack and upload enterprise manuals or documentation.

Terminal Command
docker compose -f docker-compose.yml up -d
#rag #pdf-parsing #document-understanding #docker #tables
Agents & Automation
⭐ 24k+ GitHub ↗

Agno (ex-Phidata)

agno-agi/agno

Lightweight, ultra-fast Python framework for building multi-modal agents with memory, knowledge, and tools.

💡 Why it matters:

Provides clean, minimal agent primitives without bloat or excessive layers of abstraction.

⚙️ How to connect to AI: Python SDK

Install via pip and build multi-modal agents with minimal lines of clean Python code.

Config JSON / Script
from agno.agent import Agent
from agno.models.openai import OpenAIChat

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    description="Вы ведущий системный инженер",
    markdown=True
)
agent.print_response("Объясни устройство протокола MCP за 3 предложения.")
#agents #lightweight #python #fast #multi-modal

Инструмент пригодился?

Сайт бесплатный и без платных функций. Небольшой донат в TON или репост помогают поддерживать его и добавлять новые инструменты.

Поделиться в Telegram