ART alternatives

The 12 products closest to ART in what they do and who they're for, best match first.

rLLM — Enables reinforcement learning training for AI agents with minimal code changes. (Code, Free)
Agent Lightning — Train existing artificial intelligence agents with reinforcement learning and zero code changes. (Code, Free)
OpenRLHF — High-performance distributed architecture and unified agent-based execution (Code, Free)
AReaL — Bridges foundation model training with modern agent-based applications. (Code, Free)
RLinf — Scalable open-source framework supporting real-world robots and simulators. (Code, Free)
NeMo Molt — It scales fully-async agentic RL to frontier MoE scale with a small PyTorch stack. (Code, Free)
ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture. (Code, Free)
OpenCode — Works with 75+ model providers, local models, and existing subscriptions (Code, Free)
XTuner — High-efficiency training for 200B+ scale MoE models without expert parallelism. (Code, Free)
RAGEN — Diagnoses agent failures and stabilizes reasoning training. (Code, Free)
pstack — Improves AI coding agent outcomes with rigorous workflows. (Code, Free)
Stagewise — Maintain full sovereignty over AI models while running agents in parallel. (Code, Free)