Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Roboflow Rf detr Roboflow Deployment
- Workflow:OpenHands OpenHands Organization Onboarding
- Workflow:Trailofbits Fickling Pickle Decompilation and Tracing
- Workflow:ARISE Initiative Robomimic Training Policy From Demonstrations
- Workflow:Interpretml Interpret EBM Model Export
- Workflow:OWASP Www project top 10 for large language model applications Agentic Security Assessment
- Workflow:Googleapis Python genai Context Caching
- Workflow:Princeton nlp Tree of thought llm Adding new task
- Workflow:Treeverse LakeFS Write Audit Publish With Hooks
- Workflow:Ucbepic Docetl Playground Interactive Development
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui File And Path Utility Functions
- Principle:Google deepmind Dm control Manipulation Episode Loop
- Principle:Huggingface Datatrove Media Reading Framework
- Principle:Ollama Ollama Model Loading And GPU Scheduling
- Principle:Google deepmind Mujoco Model Text Dump
- Principle:Microsoft Semantic kernel Multi Agent Orchestration
- Principle:Ollama Ollama CGoBridge
- Principle:HKUDS AI Trader MCP Service Orchestration
- Principle:Openai Openai agents python Execution Resumption
- Principle:Openai Evals Chain of Thought Prompting
Implementations
- Implementation:Apache Flink RecordsWithSplitIds
- Implementation:Facebookresearch Audiocraft DiffusionSolver
- Implementation:Alibaba MNN Llmexport Script
- Implementation:Apache Beam StreamingEngineComputationConfigFetcher
- Implementation:Microsoft DeepSpeedExamples NvidiaBert DatasetProvider
- Implementation:ARISE Initiative Robosuite OperationalSpaceController
- Implementation:Teamcapybara Capybara Spec Shared Matchers
- Implementation:Lance format Lance EncodingFormat
- Implementation:Hiyouga LLaMA Factory V1 Base Sampler
- Implementation:InternLM Lmdeploy GuidedDecoding
Heuristics
- Heuristic:Mlfoundations Open flamingo Gradient Clipping Max Norm
- Heuristic:Alibaba MNN Warning Deprecated Winograd Codegen
- Heuristic:OpenHands OpenHands Streamable HTTP Over SSE
- Heuristic:Astronomer Astronomer cosmos Memory Optimised Imports
- Heuristic:Danijar Dreamerv3 Symlog TwoHot Prediction
- Heuristic:LLMBook zh LLMBook zh github io Reward Model LM Regularization
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:SqueezeAILab ETS Thread Parallelism Suppression
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
Environments
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:Apache Spark Python Environment
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Confident ai Deepeval Python 3 9 Runtime
- Environment:Huggingface Transformers PEFT Adapter Env
- Environment:Scikit learn contrib Imbalanced learn Keras TensorFlow
- Environment:Huggingface Optimum Accelerated Inference Environment
- Environment:Liu00222 Open Prompt Injection Python Dependencies
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment