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:OpenBMB UltraFeedback Completion Generation
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:Lm sys FastChat ShareGPT Data Pipeline
- Workflow:Microsoft Playwright Network mocking and interception
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Zai org CogVideo Video Editing DDIM Inversion
- Workflow:CARLA simulator Carla Autonomous Navigation
- Workflow:Diagram of thought Diagram of thought DoT Iterative Reasoning
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:Princeton nlp Tree of thought llm Baseline comparison
Principles
- Principle:Tensorflow Serving HTTP Compression
- Principle:Apache Spark Source Compilation
- Principle:Apache Beam Pipeline Configuration Twister2
- Principle:Nightwatchjs Nightwatch Page Commands
- Principle:DistrictDataLabs Yellowbrick Grid Search Visualization
- Principle:Googleapis Python genai Tool Definition
- Principle:Huggingface Datasets Archive Extraction
- Principle:Farama Foundation Gymnasium MuJoCo Locomotion
- Principle:Microsoft BIPIA Few Shot Example Construction
- Principle:Webdriverio Webdriverio AI Self Healing
Implementations
- Implementation:Webdriverio Webdriverio MSPO Aggregator
- Implementation:Neuml Txtai HFPipeline
- Implementation:Haosulab ManiSkill Merge Trajectories Func
- Implementation:BerriAI Litellm Exception Mapping
- Implementation:MarketSquare Robotframework browser Strict Mode Keywords
- Implementation:BerriAI Litellm MCP Registry
- Implementation:Huggingface Datasets Dataset Sort
- Implementation:Infiniflow Ragflow FileManagerService
- Implementation:Diagram of thought Diagram of thought Format Compliance Validator
- Implementation:Explodinggradients Ragas Experiment Comparison Pattern
Heuristics
- Heuristic:Apache Airflow Database Lock Handling
- Heuristic:Speechbrain Speechbrain Gradient Clipping Strategy
- Heuristic:Mit han lab Llm awq Skip QK Projection Clipping
- Heuristic:Avhz RustQuant Interpolation Method Selection
- Heuristic:Mlc ai Web llm Penalty Parameter Defaults
- Heuristic:Huggingface Transformers FSDP Activation Checkpointing Tip
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:Apache Kafka Container JMX RMI Port Tip
- Heuristic:Pola rs Polars Streaming For Large Datasets
- Heuristic:Google research Deduplicate text datasets Ulimit File Descriptors For Merge
Environments
- Environment:Neuml Txtai Python Core Dependencies
- Environment:Webdriverio Webdriverio Browser Driver Environment
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment
- Environment:Kornia Kornia CUDA GPU Environment
- Environment:Apache Druid Druid Cluster Api
- Environment:Vespa engine Vespa Cosign Sigstore Signing
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Helicone Helicone Wrangler CLI
- Environment:Cypress io Cypress Linux Display Server