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:Microsoft BIPIA White Box Defense Finetuning
- Workflow:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:Explodinggradients Ragas Test Data Generation
- Workflow:Huggingface Datatrove Minhash Deduplication
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
- Workflow:Cleanlab Cleanlab CleanLearning Robust Training
- Workflow:Pola rs Polars DataFrame Aggregation and Grouping
- Workflow:Volcengine Verl Data Preprocessing For RL
- Workflow:Microsoft Autogen Studio Team Deployment
Principles
- Principle:Fastai Fastbook Model Ensembling
- Principle:SeleniumHQ Selenium WebDriver Session Creation
- Principle:DistrictDataLabs Yellowbrick Parallel Coordinates Visualization
- Principle:Iamhankai Forest of Thought CGDM Answer Selection
- Principle:OpenBMB UltraFeedback Principle Sampling
- Principle:Allenai Open instruct Streaming Generation Configuration
- Principle:Farama Foundation Gymnasium Environment Validation
- Principle:Openclaw Openclaw Binding Configuration
- Principle:DevExpress Testcafe Selector Filtering And Traversal
- Principle:Huggingface Trl PEFT LoRA Configuration Reward
Implementations
- Implementation:Mlflow Mlflow Pyproject Generator
- Implementation:Arize ai Phoenix Traces Resource
- Implementation:Interpretml Interpret Feature Bin Metadata
- Implementation:Farama Foundation Gymnasium ReacherEnv V5
- Implementation:LMCache LMCache Redis Connector
- Implementation:Obss Sahi Coco2yolo
- Implementation:Elevenlabs Elevenlabs python TurnConfigWorkflowOverride
- Implementation:Astronomer Astronomer cosmos Get Dataset Alias Name
- Implementation:Langfuse Langfuse Traces UI Table Service
- Implementation:NVIDIA NeMo Aligner Compute Topk Logits
Heuristics
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:Huggingface Datasets Batch Size Optimization
- Heuristic:Bentoml BentoML Adaptive Batching Tuning
- Heuristic:Huggingface Trl Disable Dropout For RL Training
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
Environments
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:Huggingface Trl vLLM Generation Environment
- Environment:Nautechsystems Nautilus trader Asyncio Uvloop Event Loop
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:Mbzuai oryx Awesome LLM Post training Python Requests
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment
- Environment:SeleniumHQ Selenium Selenium Manager Runtime
- Environment:Mlfoundations Open flamingo WebDataset Training Dependencies
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Volcengine Verl Ray Distributed Environment