ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Tag preview
58 preview projects.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Prettier is an opinionated code formatter.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
DSPy: The framework for programming—not prompting—language models
A modular graph-based Retrieval-Augmented Generation (RAG) system
LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Self-hosted LLM web UI covering Docker deployment, auth, model backends, OAI/Ollama endpoints, and reverse proxy checks.
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Bandit is a tool designed to find common security issues in Python code.
Self-hosted LLM web UI covering Docker deployment, auth, model backends, OAI/Ollama endpoints, and reverse proxy checks.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.
The Open Source Feature Store for AI/ML
Large Action Model framework to develop AI Web Agents
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
A simple, easy-to-hack GraphRAG implementation
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Build compute kernels and load them from the Hub.
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
LLM-driven browser automation with wallet extension testing. Accessibility tree + optional vision.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
An AI web browsing framework focused on simplicity and extensibility.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.