Stars
Backend.AI is a streamlined, container-based computing cluster platform that hosts popular computing/ML frameworks and diverse programming languages, with pluggable heterogeneous accelerator suppor…
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
A script to fix up pptx font configurations considering Latin/EastAsian/ComplexScript/Symbol typeface mappings
Repository for "K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts"
Self-hosted workspace for continuing Codex, Claude Code, and Grok work across desktop, foldable, tablet, and phone.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
pycon2026-tutorial-ai-agents
Local LLM·RAG·AI Agent·바이브 코딩을 개념부터 실습과 검증까지 다루는 학습 자료
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Repository for ACL 2026 paper “Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks”
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
The skinny framework for creating slide deck from Markdown
🔄 TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
A local-first microVM sandbox for running AI agents safely on macOS & Linux
Create beautiful slides on the web using a coding agent's frontend skills
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)