Stars
The official repository for the Scientific Paper Idea Proposer (SciPIP)
CycleResearcher: Improving Automated Research via Automated Review
基于Selkies的Linux网页版微信/QQ,支持本地中文输入法,支持AMD64和ARM64。
Available on App Store! Touch oriented, controller friendly game streaming app
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"
Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Cairo is a customizable, intuitive desktop environment for Windows.
Avrotize is a command-line tool for converting data structure definitions between different schema formats, using Apache Avro Schema as the integration schema model.
Train your AI self, amplify you, bridge the world
Chrome DevTools for coding agents
This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis fo…
Innovative open-source platform that specializes in developing next-gen compositional digital twins
一款基于 Linuxserver.io 的 KasmVNC 镜像以及百度网盘官方客户端的 Docker 镜像
An open-source & self-hostable Heroku / Netlify / Vercel alternative.
Claude Code (Sub-agent, Custom Commands) for RIPER-5
MooreThreads / vllm_musa
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
MooreThreads / ollama-musa
Forked from ollama/ollamaGet up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models on MTGPU.
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.