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:Unstructured IO Unstructured Performance Profiling
- Workflow:OpenHands OpenHands SaaS Server Assembly
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:Openai Openai node Structured Output Parsing
- Workflow:Protectai Llm guard LLM Input Output Scanning
- Workflow:Huggingface Datatrove Summary Statistics
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:Openai Openai python Audio Processing
- Workflow:Bigscience workshop Petals Distributed Text Generation
Principles
- Principle:Huggingface Trl Reward Argument Configuration
- Principle:Mistralai Client python Embedding Generation
- Principle:TA Lib Ta lib python Abstract Function Instantiation
- Principle:ChenghaoMou Text dedup Pipeline Configuration
- Principle:Duckdb Duckdb Adaptive Sorting
- Principle:Pyro ppl Pyro Discrete Marginal ELBO
- Principle:Interpretml Interpret Rule Based Classification
- Principle:LaurentMazare Tch rs Trainable JIT Loading
- Principle:Openai Openai node Text To Speech
- Principle:Apache Spark YARN Web Proxy Security
Implementations
- Implementation:Eventual Inc Daft Read Hudi
- Implementation:ArroyoSystems Arroyo Connection Tester
- Implementation:InternLM Lmdeploy Gemm Desc
- Implementation:EvolvingLMMs Lab Lmms eval Register Metric
- Implementation:Neuml Txtai Topic Modeling
- Implementation:Farama Foundation Gymnasium VectorEnv Step Reset
- Implementation:Sktime Pytorch forecasting mLSTMCell
- Implementation:TobikoData Sqlmesh EnvironmentDetails
- Implementation:Online ml River Evaluate Progressive Val Score Drift
- Implementation:TobikoData Sqlmesh API Commands
Heuristics
- Heuristic:Protectai Llm guard PyTorch Compile Warmup
- Heuristic:Mlfoundations Open flamingo Loss Masking Strategy
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Risingwavelabs Risingwave LSM Compaction Tuning
- Heuristic:Trailofbits Fickling Force Flag Bypass
- Heuristic:PeterL1n BackgroundMattingV2 Backbone Scale Selection
- Heuristic:Astronomer Astronomer cosmos Watcher Queue Sizing
- Heuristic:Apache Hudi Compaction Scheduling Safety
- Heuristic:Openai Openai node Stream Usage Interruption
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
Environments
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:Openai Whisper FFmpeg
- Environment:Datahub project Datahub Python 3 10 Ingestion Environment
- Environment:Apache Airflow Development Contributor Environment
- Environment:Datahub project Datahub Frontend Build
- Environment:Huggingface Datasets JAX Integration
- Environment:VainF Torch Pruning PyTorch Python Core
- Environment:Microsoft Playwright Node Runtime Environment
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:DevExpress Testcafe Firefox Marionette