slime is an LLM post-training framework for RL Scaling.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

Tongyi Deep Research, the Leading Open-source Deep Research Agent

An open-source AI agent that brings the power of Gemini directly into your terminal.

Bookmarklet to export the content from chatbots to a PDF or text with a single click. Supports Claude, ChatGPT, Grok and Gemini.

🦜🔗 The platform for reliable agents.

Fully local web research and report writing assistant

A library for mechanistic interpretability of GPT-style language models

Simulation code for paper "Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality"

A library for advanced large language model reasoning

【升级版-Electron】Check how many CEFs are on your computer. 检测你电脑上有几个CEF.