Skip to content
AgentRadar
Rllm

Rllm

Train your AI agents with RL

Agentes de Programación
8.0 /10
Código abierto

Última actualización

2026-06-15

GitHub Stars

5,618

Acerca de Rllm

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

Nuestro veredicto

A coding agent that is open-source and self-hostable backed by 5.6k GitHub stars. Train your AI agents with RL. Any framework. Minimal code changes..

Características

Any harness
Any sandbox
Multiple training backends, one API
Multiple training methods
Battle-tested
Workflow Engine

Calificaciones detalladas

Facilidad de uso
7.7
Relación calidad-precio
8.2
Características
8.0
Soporte
7.4
Rendimiento
8.1
Calificación general
8.0 /10

Pros y Contras

Pros

  • Open-source — fully self-hostable and auditable
  • Active community with 5.6k GitHub stars
  • Any harness
  • Any sandbox

Contras

  • Requires technical setup; less hand-holding than managed alternatives
  • Limited third-party reviews and benchmarks

Casos de uso

Code generationCode reviewDebuggingRefactoring

¿Para quién es?

Teams and individuals looking for software development automation who value open-source flexibility and control.

#agent-framework#agentic-workflow#coding-agent#distributed-training#llm-reasoning#rllm

Preguntas frecuentes

What is Rllm?

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

How much does Rllm cost?

Rllm is open-source and free to self-host. See https://github.com/rllm-org/rllm for installation instructions.

Is Rllm open source?

Yes — Rllm is open source with 5.6k stars. The source code is on GitHub at https://github.com/rllm-org/rllm.

Who should use Rllm?

Teams and individuals looking for software development automation who value open-source flexibility and control.

Agentes relacionados

Enlaces y recursos