Workflows
2 recipes, filter by use case, license, or difficulty.
Local InferenceFreeMachine-verified
Serve MiniMax M3 yourself for agentic coding (vLLM)
Stand up MiniMax M3 on an 8x H200 node as an OpenAI-compatible endpoint and point any coding agent at it, validated serve flags + endpoint config.
MiniMax M3vLLM· advanced
ResearchFreeVerified on a mock
Hermes + NotebookLM "Second Brain"
Pair Hermes with NotebookLM to build a self-researching, self-teaching knowledge system.
Replaces Perplexity Pro
ObsidianNotebookLMHermes Agent· advanced