NVIDIA-NeMo / labs-molt
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
Why this job: matched by what the repo talks about: framework, agentic, research, first
What it does
PyTorch. That is the whole stack: ~9.2K lines of RL code that scale to 1T-class MoE on vLLM with TP / EP / CP — think DeepSeek-V3 at --fsdp.ep_size 256, Adam CPU offload for the largest actors. One agent API, one trainable actor, clean enough to read end-to-end.
Get started
git clone https://github.com/NVIDIA-NeMo/labs-molt.git
cd labs-molt - Maintenance
- Active
- Last commit today
- Stars
- 1,281
- +63 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.2
- Released 6 days ago
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- 11
- Last 90 days
- Issues
- 47% closed
- 9 still open
- Pull requests
- 195 merged
- 12 waiting
- Releases
- 16
- 16 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
More: languages, topics and project record
Languages
- Python 97%
- Dockerfile 2%
- Shell 1%
Topics
- agentic-rl
- expert-parallelism
- fsdp
- llm
- rl-framework
- rlhf
- rlvr
- tensor-parallelism
- huggingface
- context-parallelism
Project record
- JobAgent frameworks
- StatusListed
- Commits337
- Forks126
- Watching5
- Stars in 28 days+90
- CreatedJun 23, 2026
- First seen by usNov 7, 2026
- CheckedNov 12, 2026