Stars
This is the official repo for the paper "LongCat-Flash-Omni Technical Report"
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.
Perforator is a cluster-wide continuous profiling tool designed for large data centers
Optimized Whisper models for streaming and on-device use
OpenChoreo is an open-source internal developer platform (IDP)
This repository collects and organises state‑of‑the‑art papers on spatial reasoning for Multimodal Vision–Language Models (MVLMs).
Universal skills loader for AI coding agents - npm i -g openskills
Open-source implementation of AlphaEvolve
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
Add long-term memory to any AI in minutes. Self-hosted, open, and framework-free.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
A blazingly fast multi-language serialization framework powered by JIT and zero-copy.
[EMNLP 2024 (Oral)] Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Realtime Multithreaded Compression library writen in C/C++
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
"RAG-Anything: All-in-One RAG Framework"