An easy-to-use, fast toolkit to scale up RL post-training on a single node.

7 stars 0 forks 7 watchers Python Apache License 2.0
agent agentic-ai grpo llm local-ai local-llm machine-learning post-training reinforcement-learning rl self-hosted sft
11 Open Issues Need Help Last updated: Jul 3, 2026

Open Issues Need Help

View All on GitHub
good first issue kind/documentation priority/important-soon area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/testing area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/cleanup area/api area/testing area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/cleanup area/api area/testing area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/api area/engine priority/important-soon

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/api area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation kind/cleanup area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/cli area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/bug area/algorithms area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/serving area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft
good first issue kind/documentation area/api area/dx

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Python
#agent#agentic-ai#grpo#llm#local-ai#local-llm#machine-learning#post-training#reinforcement-learning#rl#self-hosted#sft