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:Dagster io Dagster RAG Pipeline
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:Vllm project Vllm Structured Output Generation
- Workflow:Farama Foundation Gymnasium Policy Gradient Training
- Workflow:Tencent Ncnn Object Detection Inference
- Workflow:CrewAIInc CrewAI Flow Based Orchestration
- Workflow:Deepset ai Haystack Document Indexing Pipeline
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:OWASP Www project top 10 for large language model applications Agentic Security Assessment
- Workflow:LaurentMazare Tch rs LLM Text Generation
Principles
- Principle:Confident ai Deepeval LLM Span Enrichment
- Principle:Google research Deduplicate text datasets Byte Range Removal
- Principle:PacktPublishing LLM Engineers Handbook SageMaker Training Orchestration
- Principle:HKUDS AI Trader Trading Outcome Recording
- Principle:Neuml Txtai Benchmark Evaluation
- Principle:Google deepmind Mujoco Plugin System
- Principle:Volcengine Verl RLHF Data Preparation
- Principle:BerriAI Litellm Retry And Fallback
- Principle:Online ml River Anomaly Detection Base Interface
- Principle:Truera Trulens Feedback Function Definition
Implementations
- Implementation:Teamcapybara Capybara Node Actions Attach File
- Implementation:Mage ai Mage ai Commercetools Orders Schema
- Implementation:Helicone Helicone UseFeatureTrial
- Implementation:Langgenius Dify Security Middleware
- Implementation:Tensorflow Tfjs Python Inference
- Implementation:Avhz RustQuant Longstaff Schwartz
- Implementation:Anthropics Anthropic sdk python Stream Parsed Snapshot
- Implementation:Evidentlyai Evidently Legacy Report
- Implementation:Heibaiying BigData Notes DataFrame Transformation API
- Implementation:TobikoData Sqlmesh FileExplorer Directory
Heuristics
- Heuristic:Microsoft Playwright Timeout Configuration Tips
- Heuristic:Kornia Kornia Gradient Detach Stability
- Heuristic:Run llama Llama index Batch Eval Retry Strategy
- Heuristic:Cohere ai Cohere python Warning Deprecated Legacy Generate API
- Heuristic:MarketSquare Robotframework browser Docker Chrome Security
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:Intel Ipex llm Llama Padding Token Workaround
- Heuristic:Togethercomputer Together python Repetition Penalty Conflict
- Heuristic:Recommenders team Recommenders SAR Cold Start Items
- Heuristic:Protectai Modelscan Exit Code Conventions
Environments
- Environment:Tensorflow Serving Kubernetes Deployment Environment
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:Mit han lab Llm awq Flash Attention Environment
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment
- Environment:Huggingface Peft GPU Hardware Detection
- Environment:Vllm project Vllm Distributed
- Environment:Google deepmind Dm control EGL Headless Rendering
- Environment:Sgl project Sglang CPU Runtime
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Datajuicer Data juicer GPU CUDA Environment