TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

TransMLA: Equivalently Transforms Group Query Attention into Multi-head Latent Attention.

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

PC Agent: While You Sleep, AI Works - A Cognitive Journey into Digital World

A port of Doom (1993) that runs inside a PDF file

AIlice is a fully autonomous, general-purpose AI agent.

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / Ultralytics / veRL …

s1: Simple test-time scaling

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

目前已囊括187个大模型，覆盖chatgpt、gpt-4o、o3-mini、谷歌gemini、Claude3.5、智谱GLM-Zero、文心一言、qwen-max、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及DeepSeek-R1、deepseek-v3、qwen2.5、llama3.3、phi-4、glm4、书生internLM2.5等开源大模型。不仅提供能力评…

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

The absolute most basic example of AlphaZero and Monte Carlo Tree Search I could come up with

Testing baseline LLMs performance across various models

Multi-Joint dynamics with Contact. A general purpose physics simulator.

World's First Large-scale High-quality Robotic Manipulation Benchmark

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues?

A benchmark for the next generation of data-driven global weather models.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Transforming Neural Architecture Search (NAS) into multi-objective optimization problems. A benchmark suite for testing evolutionary algorithms in deep learning.

An open-sourced end-to-end VLM-based GUI Agent

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Mamba SSM architecture