Run This Ai
EN DE

RLLM

Agentic RL on any harness, with any backend, on any benchmark

★ 5,797 GitHub Apache-2.0 reinforcement-learningllm-trainingagent-frameworkverlgrpo LLM & Chat

Overview

rLLM is an open-source framework for training language agents with reinforcement learning. Bring any harness, run it in any sandbox, and switch training backends with one flag — the same agent code drives both eval and training. Includes 60+ integrated benchmarks, multiple RL methods such as GRPO, REINFORCE and RLOO, and battle-tested results like DeepScaleR-1.5B and DeepCoder-14B.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  rllm:
    image: https://github.com/rllm-org/rllm/blob/main/Dockerfile
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/rllm:/data

Best VPS for RLLM →

Related tools

Guides & articles