slime is an LLM post-training framework for RL scaling. It provides tools for fine-tuning and scaling reinforcement learning models. It connects to PyTorch and Hugging Face Transformers. Developers use it to optimize LLM training and deployment.
slime is an LLM post-training framework for RL scaling. It provides tools for fine-tuning and scaling reinforcement learning models. It connects to PyTorch and Hugging Face Transformers. Developers use it to optimize LLM training and deployment.
pip install slimeAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"thudm-slime-github": {
"command": "uvx",
"args": [
"pip install slime"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from slime?"
No configuration required. This server works out of the box.
"What resources are available in slime?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in slime"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in slime with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.