AI dev and agent tools, decision-grade.

Fully automatic censorship removal for language models

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

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Democratizing Reinforcement Learning for LLMs

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"