RAG Stack

RAGFlow is an open-source RAG engine combining advanced retrieval-augmented generation with agentic AI workflows.

A repository demonstrating advanced techniques for Retrieval-Augmented Generation (RAG) systems.

Framework for developing applications powered by language models

LuaN1ao (鸾鸟) is an autonomous penetration testing agent leveraging state awareness and causal reasoning.

Ollama v0.17.0 enhances model loading, tokenizer consistency, and UI integration for local LLMs like Gemma, GLM, and DeepSeek.

Hugging Face Transformers v5.2.0 adds GLM-5, Qwen3.5, Voxtral Realtime, and VibeVoice Acoustic Tokenizer with major architectural updates and breaking changes.

Awesome ChatGPT Prompts: a community-driven, open-source collection of AI prompts with over 146K stars on GitHub.

Open WebUI is a user-friendly, open-source web interface for LLMs with support for Ollama, OpenAI API, and more.

Everything Claude Code (ECC) is a battle-tested, universal AI developer toolkit supporting Claude Code, OpenCode, and Cursor with rich agents, skills, and language-specific rules.

OpenHands is an AI-driven development agent framework with CLI support, integrating models like ChatGPT, Claude AI, and now MiniMax-M2.5.

mem0ai/mem0 is a Python-based universal memory layer for AI agents, trending on GitHub with 47.8K stars and active development in the AI/chatbot space.

AI-powered trend monitoring tool aggregating multi-platform news, RSS feeds, and smart alerts with Docker support.

LocalAI is a self-hosted, local-first open-source alternative to OpenAI and Claude, running on consumer hardware without requiring a GPU.

Continue is an open-source, source-controlled AI coding agent powered by the Continue CLI, enabling enforceable AI checks in CI and deep IDE integration.

memchr offers highly optimized SIMD-accelerated routines for fast byte and substring searches across x86_64, aarch64, and wasm32.

Visualize AI/LLM workflows in your codebase.

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

"RAG-Anything: All-in-One RAG Framework"

Trending on GitHub

scrcpy is a high-star C-based Android mirroring and control tool leveraging ffmpeg/libav, actively maintained with recent fixes for device compatibility and build issues.

Supabase — the open-source Firebase alternative offering a full-stack Postgres platform for web, mobile, and AI applications.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

JeecgBoot v3.9.1 enhances its AI low-code platform with multimodal AI, intelligent agents, advanced workflow nodes, and Chat2BI chart generation.

In-depth tutorials on LLMs, RAGs, and real-world AI agent applications.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

@mcp-use/cli is a build tool for MCP servers with support for ChatGPT Apps, OAuth, observability, and more, averaging 17.8K weekly npm downloads.

An Open-Source Asynchronous Coding Agent