AgileRL

Library for LLM post-training (SFT, DPO, GRPO and agentic RL) and classic RL, with evolutionary hyperparameter optimization.

Harness by AgileRL

IndexedApache-2.0★ 959

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install agilerl

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

AgileRL covers LLM post-training from supervised fine-tuning and preference tuning through multi-turn agentic RL, with LoRA, FSDP2 multi-GPU training and vLLM rollouts. It also includes classic single-agent, multi-agent, offline and bandit RL, with evolutionary hyperparameter optimization. The README describes Arena, a managed service for training and deploying runs at scale, and a YAML-manifest CLI that coding agents can drive.

Use cases: model-inference

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: agilerl (pypi)README
Multi-agent: YesREADME
Deploys to: managed cloudREADME
Maturity: Stablegithub.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 959
Forks: 84
Open issues: 3
Weekly downloads: 697
Last commit: Oct 24, 2026 (4 days ago)
Last release: Oct 21, 2026 (7 days ago)
Last package publish: Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi agilerl
License: Apache-2.0
Repository: github.com/AgileRL/AgileRL
Website: agilerl.com
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Cite this page

AgileRL. Agent Mart. https://agentmart.dev/harnesses/agilerl (last updated 2026-10-24)