Harness Toolbox/Agent SDKs & frameworks/rllm-org/rllm

rllm-org/rllm

Democratizing Reinforcement Learning for LLMs

View on GitHub →

PythonApache-2.0agent-frameworkagentic-workflowdistributed-trainingllm-trainingmachine-learning

Stars

5.7k

Δ 7d

+16

Δ 30d

+80

Age

1 yr

Last push

7h ago

90-day star history

#28 of 65 in Agent SDKs & frameworks

Most-wanted open issues

Ranked by 👍 reactions. 77 open issues total, checked 2026-07-17.

Issue	👍	Comments	Opened
Evaluation Results Are Zero Due to Format Inconsistency in DeepSeek-R1-Distill-Qwen-1.5B	10	6	1 yr
Is RL Better than SFT?	3	1	1 yr
Reproduce evaluation results on AIME (41% vs 43.1%)	1	9	1 yr
Techniques for Optimizing hyperparameters in the verl Framework for Improved Training Efficiency	1	1	1 yr
is 4*24GB not enough for batch 4?	1	2	1 yr

Alternatives in Agent SDKs & frameworks

langchain-ai/langchain

The agent engineering platform.

⭐142.0k

Python

3 yrs

zhayujie/CowAgent

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory a…

⭐46.0k

Python

3 yrs

Build, run, and manage agent platforms.

⭐41.2k

Python

4 yrs

wshobson/agents

Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gem…

⭐38.0k

+2257d

Python

11 mo

CopilotKit/CopilotKit

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI P…

⭐36.1k

+1947d

TypeScript

3 yrs

ComposioHQ/composio

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to…

⭐29.3k

+1107d

TypeScript

2 yrs