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:Arize ai Phoenix Span Annotation Pipeline
- Workflow:Langchain ai Langchain Tool Calling Structured Output
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:Datahub project Datahub Metadata Actions Pipeline
- Workflow:BerriAI Litellm Observability Integration
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:Googleapis Python genai Multi Turn Chat
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Predibase Lorax OpenAI Chat Completion
- Workflow:Danijar Dreamerv3 Evaluation Only
Principles
- Principle:Haosulab ManiSkill Trajectory Replay Conversion
- Principle:Openclaw Openclaw Reply Delivery
- Principle:Eventual Inc Daft Descriptive Statistics
- Principle:Triton inference server Server Classification Postprocessing
- Principle:Apache Druid Supervisor Operational Management
- Principle:Apache Hudi CI Parallel Test Orchestration
- Principle:Alibaba ROLL MCoreAdapter Model Factory
- Principle:Obss Sahi COCO Dataset Export
- Principle:Langgenius Dify Embedding Indexing Configuration
- Principle:Datajuicer Data juicer Operator Testing
Implementations
- Implementation:Huggingface Datasets Sharding Utils
- Implementation:Duckdb Duckdb Add Library Unity
- Implementation:Rapidsai Cuml Spectral Embedding
- Implementation:Helicone Helicone SignIn Page
- Implementation:Explodinggradients Ragas Experiment Comparison Pattern
- Implementation:Langgenius Dify CreateApp
- Implementation:Open compass VLMEvalKit MMHelix Skyscrapers Eval
- Implementation:ContextualAI HALOs Alignment Trainers
- Implementation:NVIDIA NeMo Aligner Image Text RMS
- Implementation:Wandb Weave Git Push Release
Heuristics
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:Testtimescaling Testtimescaling github io Dual JSON Sync
- Heuristic:Huggingface Peft Warning Deprecated Bone
- Heuristic:Onnx Onnx External Data Path Security
- Heuristic:Protectai Modelscan Nested Zip Not Supported
- Heuristic:Apache Kafka Coordinator Loading Commit Interval
- Heuristic:Allenai Open instruct Pre Init Torch Distributed
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
Environments
- Environment:TobikoData Sqlmesh GitHub CICD Runner
- Environment:Openai Openai node WebSocket Dependency
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Huggingface Trl DeepSpeed Environment
- Environment:Nightwatchjs Nightwatch Android Mobile Testing
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Promptfoo Promptfoo Python Runtime
- Environment:Bitsandbytes foundation Bitsandbytes CUDA GPU Runtime
- Environment:Langfuse Langfuse Node 24 Runtime