Main Page
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:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:Fede1024 Rust rdkafka Transactional Produce Consume
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Explodinggradients Ragas RAG Evaluation
- Workflow:MaterializeInc Materialize dbt Integration
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:HKUDS AI Trader End to End US Stock Trading
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:Langgenius Dify Visual Workflow Builder
Principles
- Principle:Dagster io Dagster Custom Resource Pattern
- Principle:Puppeteer Puppeteer Web Worker Interaction
- Principle:Mlc ai Mlc llm Native Application Building
- Principle:Deepspeedai DeepSpeed Pipeline Module Construction
- Principle:Huggingface Diffusers Dual LoRA Configuration
- Principle:NVIDIA NeMo Curator CLIP Embedding
- Principle:SeleniumHQ Selenium Pull Request Submission
- Principle:Sktime Pytorch forecasting TFT Model Instantiation
- Principle:Axolotl ai cloud Axolotl Distributed Environment Setup
- Principle:Apache Druid Query Composition
Implementations
- Implementation:Run llama Llama index BaseQueryEngine
- Implementation:NVIDIA DALI ScratchCopyImpl
- Implementation:Evidentlyai Evidently Legacy Text Part Feature
- Implementation:Elevenlabs Elevenlabs python HistoryClient
- Implementation:Datajuicer Data juicer Quality Classifier Eval
- Implementation:NVIDIA NeMo Curator XennaStageAdapter
- Implementation:Sgl project Sglang CPU Activation
- Implementation:Microsoft DeepSpeedExamples Test Function CIFAR
- Implementation:Openai Evals Eval Base Class
- Implementation:Sgl project Sglang Engine Generate Multimodal
Heuristics
- Heuristic:Cohere ai Cohere python ToolCallV2 Auto UUID Override
- Heuristic:Princeton nlp Tree of thought llm Global State Token Counting
- Heuristic:Iterative Dvc Shell Execution Pitfalls
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:TobikoData Sqlmesh Execution Time Caching
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
- Heuristic:Apache Airflow DAG Top Level Code Avoidance
- Heuristic:Neuml Txtai LLM Context Window Fallback
- Heuristic:Triton inference server Server Concurrency Throughput Rule
Environments
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Farama Foundation Gymnasium Video Recording Dependencies
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:FlowiseAI Flowise Docker Environment
- Environment:Sdv dev SDV GPU CUDA Support
- Environment:Lucidrains X transformers PyTorch CUDA
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Apache Spark JDK Build Environment