AI Model Training

Count Count

A collaborative notebook and visualization platform for modern data teams

Gradio Gradio

Use a few lines of Python to build an interactive web interface for machine learning models and share it as an open source library

DeepEval Confident AI

Open source evaluation framework for LLM application RAG and Agent, using Pytest style to incorporate evaluation into the R&D process

HELM HELM

The large model overall evaluation system launched by Stanford University emphasizes transparent evaluation of multiple scenarios and indicators.

Ollama Ollama

One line of commands to run mainstream open source large models such as Llama, DeepSeek, and Qwen locally, 173K+ GitHub Star

ACE-Ego ACE-Ego

One brain, multiple types of embodied operation VLA model research project

OpenCompass OpenCompass

Open source large model evaluation system launched by Shanghai Artificial Intelligence Laboratory

Agenta Agenta

The open source LLMOps platform covers prompt word experiments, evaluation, online and observation, and supports 50+ models and Agent orchestration.

DeepSeek API 深度求索

DeepSeek open API platform provides V3/R1/V4 series model inference capabilities at a very low price

HoneyHive HoneyHive

Observation, evaluation, monitoring and continuous improvement platform for production-level AI Agents

Jan Jan

Open source, local large model desktop client that can be run offline, compatible with cloud models and comes with OpenAI style API

Aim Stack Aim

Open source ML experiment tracking and visualization platform for teams focused on data sovereignty