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:EvolvingLMMs Lab Lmms eval Custom Task Creation
- Workflow:Apache Druid SQL Query Execution
- Workflow:Helicone Helicone Cost Calculation Pipeline
- Workflow:Volcengine Verl Multi Turn Tool Use Training
- Workflow:Webdriverio Webdriverio Cloud Service Integration
- Workflow:Avhz RustQuant Stochastic Process Simulation
- Workflow:Kubeflow Kubeflow Platform Deployment
- Workflow:Online ml River Streaming Anomaly Detection
- Workflow:OpenGVLab InternVL Preference Optimization
- Workflow:Explodinggradients Ragas LLM Benchmarking
Principles
- Principle:Ray project Ray Actor Runtime Initialization
- Principle:MarketSquare Robotframework browser API Test Context Setup
- Principle:FlowiseAI Flowise Prompt Management
- Principle:Confident ai Deepeval Golden Generation from Contexts
- Principle:Openclaw Openclaw Multi Agent Architecture
- Principle:OpenBMB UltraFeedback Principle Sampling
- Principle:Facebookresearch Audiocraft Audio Watermark Training
- Principle:CrewAIInc CrewAI Tool Execution And Monitoring
- Principle:Vespa engine Vespa Subscriber Shutdown
- Principle:Open compass VLMEvalKit Dataset Registration
Implementations
- Implementation:MarketSquare Robotframework browser Coverage Keywords
- Implementation:Vespa engine Vespa Application ABI Spec
- Implementation:TobikoData Sqlmesh Model SqlmeshModel
- Implementation:Microsoft Onnxruntime CPU FakeQuant
- Implementation:Elevenlabs Elevenlabs python SpeechToTextClient Convert
- Implementation:Speechbrain Speechbrain SpeakerBrain Compute Forward
- Implementation:Webdriverio Webdriverio Monad
- Implementation:Run llama Llama index IndexStructType
- Implementation:HKUDS AI Trader Jina Search Tool
- Implementation:Langfuse Langfuse TraceUpsertQueue
Heuristics
- Heuristic:SeleniumHQ Selenium Explicit Over Implicit Waits
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:Openclaw Openclaw Config Cascade Resolution
- Heuristic:Vespa engine Vespa KStemmer Dictionary Loading
- Heuristic:Googleapis Python genai LRO Polling Backoff
- Heuristic:NVIDIA DALI Memory Pool Tuning
- Heuristic:Microsoft BIPIA Torch Compile Platform Guard
- Heuristic:Huggingface Peft LoRA Default Configuration
- Heuristic:Gretelai Gretel synthetics Mixed Precision Training Tradeoff
- Heuristic:Duckdb Duckdb Sanitizer Configuration
Environments
- Environment:Huggingface Datasets PyTorch Integration
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Recommenders team Recommenders Spark Environment
- Environment:Datajuicer Data juicer Python Runtime Environment
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Pytorch Serve Python PyTorch Runtime
- Environment:Langgenius Dify Node Frontend Environment
- Environment:NVIDIA NeMo Aligner NeMo Framework GPU Environment