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

Python tool for converting files and office documents to Markdown.

No fortress, purely open ground. OpenManus is Coming.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Connect any LLM to your internal knowledge sources and chat with it in real time alongside your team. OSS alternative to NotebookLM, Perplexity, and Glean. Join our Discord: https://discord.gg/ejRN…

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped…

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Fully local web research and report writing assistant

A collection of sample agents built with Agent Development Kit (ADK)

Build effective agents using Model Context Protocol and simple workflow patterns

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…

The most accurate document search and store for building AI apps

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Python package and backend for the Elysia platform app.

An implementation of iterative deep research using the OpenAI Agents SDK

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to con…

A flexible, adaptive classification system for dynamic text classification

A lightweight Python library that allows any LLM agent to self-improve through feedback, without retraining models.

🌪️ AI research assistant that generates Wikipedia-quality articles through multi-perspective analysis. Based on Stanford's STORM methodology.

A template for using langgraph with gradio