Starred repositories
🌐 WebAgent for Information Seeking bulit by Tongyi Lab: WebWalker & WebDancer & WebSailor https://arxiv.org/pdf/2507.02592
A lightweight, powerful framework for multi-agent workflows
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Tool for generating high quality Synthetic datasets
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini) and includes benchmark tools to test on your own data. Searches 10+ sources - arXiv, PubMed, GitHub, web, and your…
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
ChatMCP is an AI chat client implementing the Model Context Protocol (MCP).
Python tool for converting files and office documents to Markdown.
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
🦜🔗 Build context-aware reasoning applications
WebRAgent is a retrieval-augmented generation (RAG) web application featuring agent-based query decomposition, vector search with Qdrant, and integration with leading LLM providers for context-rich…
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案
MCP server for enabling LLM applications to perform deep research via the MCP protocol
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Research projects built on top of Transformers
Wan: Open and Advanced Large-Scale Video Generative Models
A library for efficient similarity search and clustering of dense vectors.
MAGI-1: Autoregressive Video Generation at Scale
Minimal reproduction of DeepSeek R1-Zero
A live stream development of RL tunning for LLM agents
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.