Awesome AI AgentsReasoning Frameworks

refly-ai/refly

⭐ 7516 TypeScript added to this list on 2025-04-19 repository created 2024-02-19

Refly is an open-source AI-native creation engine designed to empower users to transform ideas into production-ready content through an intuitive free-form canvas interface. It integrates multi-threaded dialogues, multimodal inputs including text, images, and files, and a retrieval-augmented generation (RAG) knowledge base system. The platform supports a wide range of file formats such as PDF, DOCX, RTF, TXT, MD, HTML, EPUB, and image formats like PNG, JPG, BMP, GIF, SVG, and WEBP. Refly incorporates over 13 leading AI models including DeepSeek R1, Claude 3.5 Sonnet, Google Gemini 2.0, and OpenAI O3-mini, enabling hybrid scheduling and parallel processing for enhanced AI capabilities. Key features include a multi-threaded conversation system that manages independent conversation contexts and complex workflows, a multi-model integration framework, and a powerful AI-powered skill system that supports intelligent web-wide search, vector database knowledge retrieval, and AI-assisted document generation. The platform also offers a context management system for precise knowledge base construction and multi-dimensional context correlation, alongside a knowledge base engine that supports multi-source heterogeneous data import and intelligent knowledge graph construction. Refly provides intelligent content capture from major platforms like Github, Medium, Wikipedia, and Arxiv, with automatic knowledge classification and tagging. It features a citation system for flexible multi-source referencing and a real-time AI-enhanced Markdown editor with content optimization and analysis. Additionally, Refly supports code artifact generation for HTML, SVG, Mermaid diagrams, and React applications, with real-time preview and debugging. The website visualization engine allows interactive web page rendering and preview, making it a comprehensive tool for creative and technical content production. The project supports self-hosting via Docker and offers extensive documentation, community forums, and cloud services.

https://github.com/refly-ai/refly

agentaiai-memoryai-native-creation-engineanthropicartifactartifactsblogscanvaschrome-extension-clip-&-savecitation-systemcode-artifact-generationcontent-capturecontent-creationcontextual-memorydeep-researchdeepseek-r1dockerdocumentationfree-form-canvasgeminigpt-4intelligent-searchknowledge-baseknowledge-base-integrationknowledge-graphmanusmarkdown-editormulti-model-integrationmulti-threaded-dialoguesmultimodal-inputsopenai-o1qwenragrag-retrievalreal-time-previewself-hostingvector-databasewebsite-visualization-engineworkflowwysiwyg-ai-editor

Also in Reasoning Frameworks

bytedance/deer-flow

DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.

VectifyAI/PageIndex

PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.

guidance-ai/guidance

Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.

friuns2/BlackFriday-GPTs-Prompts

A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.

mongodb-developer/GenAI-Showcase

MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.

anysphere/priompt

Priompt is a JSX-based prompting library that uses a priority system to efficiently construct token-limited prompts for language models, inspired by React's component design.

HKUDS/Auto-Deep-Research

Auto-Deep-Research is an open-source, fully automated, and cost-effective personal AI assistant that supports multiple large language models and offers a one-click launch experience as an alternative to OpenAI's Deep Research.

NirDiamant/Controllable-RAG-Agent

Controllable-RAG-Agent is an advanced Retrieval-Augmented Generation solution featuring a deterministic graph-based autonomous agent designed for complex question answering with multi-step reasoning and hallucination prevention.