rLLM
rLLM is an Apache-2.0 framework for training language agents with reinforcement learning. You bring any harness, including 10+ CLI agents such as Claude Code, Codex, mini-swe-agent and OpenCode, or wrap your own LangGraph or OpenAI Agents SDK agent with @rllm.rollout, run it in Docker, Daytona, Modal or local sandboxes, and switch training backends with one flag. The same agent code drives both evaluation and training.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, coding in the terminal, building AI agents, evaluating agents, running code safely, training and fine-tuning agents
Use cases
About rLLM
rLLM is listed in our frameworks category and is aimed at builders. rLLM is an Apache-2.0 framework for training language agents with reinforcement learning. You bring any harness, including 10+ CLI agents such as Claude Code, Codex, mini-swe-agent and OpenCode, or wrap your own LangGraph or OpenAI Agents SDK agent with @rllm.rollout, run it in Docker, Daytona, Modal or local sandboxes, and switch training backends with one flag. The same agent code drives both evaluation and training. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-11-06.
rLLM at a glance
- Category: Frameworks
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: rllm-org/rllm · 5,925 stars (as of Nov 18, 2026)
- Official site: docs.rllm-project.com
- Listed on AgentScout: Nov 6, 2026
rLLM FAQ
What is rLLM?
rLLM is an Apache-2.0 framework for training language agents with reinforcement learning. You bring any harness, including 10+ CLI agents such as Claude Code, Codex, mini-swe-agent and OpenCode, or wrap your own LangGraph or OpenAI Agents SDK agent with @rllm.rollout, run it in Docker, Daytona, Modal or local sandboxes, and switch training backends with one flag. The same agent code drives both evaluation and training.
How much does rLLM cost?
rLLM's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find rLLM's source code?
On GitHub at rllm-org/rllm, which had 5,925 stars as of Nov 6, 2026.
What are alternatives to rLLM?
Similar tools include smolagents, Omnigent, ECC, Orca Agent Engine, Court Skill and Council Of High Intelligence.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
rLLM ratings and reviews
Be the first to rate rLLM: tap 1 to 5 stars below. A written review is optional.
rLLM alternatives
Other frameworks tools in our directory. See all frameworks tools →
smolagents
smolagents is Hugging Face's Apache-2.0 Python library for agents that think in code: its CodeAgent writes each action as a Python snippet rather than a JSON tool call, and the core agent logic fits in about 1,000 lines. Generated code can run in sandboxes such as E2B, Modal, Blaxel or Docker, tools and agents can be shared to and pulled from the Hugging Face Hub, and it works with any model, from local transformers or Ollama to OpenAI, Anthropic and other providers via LiteLLM.
Omnigent
Open-source agent framework and meta-harness that orchestrates Claude Code, Codex, Cursor and other agents together.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond
Orca Agent Engine
Open Apache-2.0 runtime to build, run, and govern managed agents with choice of harness (Claude Agent SDK, Codex, Pi) and model; open-sourced Oct 6, 2026 (Developer Preview).
Court Skill
Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.
Council Of High Intelligence
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.