Starred repositories
MTEB: Massive Text Embedding Benchmark
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Agent S: an open agentic framework that uses computers like a human
Python
<
10000
a class="Link--muted mr-3" href="/simular-ai/Agent-S/stargazers">
5,703
598
Updated Jul 8, 2025
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / Swift / Ultralytics…
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Reference implementations of MLPerf™ inference benchmarks
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
A framework for few-shot evaluation of language models.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
SGLang is a fast serving framework for large language models and vision language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Retrieval and Retrieval-augmented LLMs
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Community maintained hardware plugin for vLLM on Ascend
📦 Get a clean, ready-to-go Linux box in seconds.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
Robust Speech Recognition via Large-Scale Weak Supervision