Create LLM agents with long-term memory and custom tools 📚🦙

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 15.95% tasks in full SWE-bench

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

Drag & drop UI to build your customized LLM flow

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

A comprehensive guide to understanding and implementing large language models with hands-on examples using LangChain for GenAI applications.

Get up and running with Llama 2, Mistral, Gemma, and other large language models.

Dify is an open-source LLM app building platform. It's the core tech required to build AI-native apps, including RAG, agent capabilities, model management, observability and more, packaged into one…

LlamaIndex is a data framework for your LLM applications

AIOS: LLM Agent Operating System

Interact with your documents using the power of GPT, 100% privately, no data leaks

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

🐚 OpenDevin: Code Less, Make More

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective…

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Focus on prompting and generating

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

A framework for prompt tuning using Intent-based Prompt Calibration

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Powerful distributed job scheduling middleware that supports CRON, API, fixed frequency, fixed delay and other scheduling strategies, provides workflow to choreograph jobs to resolve dependencies, …