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:Langchain ai Langgraph ReAct Agent Creation
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:Haifengl Smile Matrix Decomposition Pipeline
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:Kornia Kornia Image Stitching Panorama
- Workflow:Trailofbits Fickling Safe ML Model Loading
- Workflow:Open compass VLMEvalKit Adding Custom VLM
- Workflow:ClickHouse ClickHouse Building From Source
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:FMInference FlexLLMGen Data Wrangling Batch Inference
Principles
- Principle:Triton inference server Server Automated Profiling
- Principle:Apache Flink Hybrid Source Initialization
- Principle:Marker Inc Korea AutoRAG Pipeline Runner Initialization
- Principle:Microsoft Playwright Launch Codegen
- Principle:AUTOMATIC1111 Stable diffusion webui SD3 Text Conditioning Pipeline
- Principle:Google deepmind Mujoco Rendering Resource Cleanup
- Principle:Lance format Lance Full Text Query Execution
- Principle:OpenRLHF OpenRLHF Direct Preference Optimization
- Principle:Microsoft Agent framework Custom Aggregation Pattern
- Principle:SeldonIO Seldon core Production Traffic Monitoring
Implementations
- Implementation:Langgenius Dify Debug Models
- Implementation:Cohere ai Cohere python ChatMessageV2 Union
- Implementation:Haosulab ManiSkill BaseEnv Step Reset
- Implementation:FlowiseAI Flowise EvaluationResultSideDrawer
- Implementation:Scikit learn Scikit learn MetadataRequests
- Implementation:AUTOMATIC1111 Stable diffusion webui Train embedding
- Implementation:CARLA simulator Carla AckermannControllerSettings
- Implementation:Neuml Txtai Pooling Base
- Implementation:Langfuse Langfuse API Dataset Items Schema
- Implementation:Obss Sahi Slice Coco
Heuristics
- Heuristic:Dotnet Machinelearning Sparsity Threshold Optimization
- Heuristic:Microsoft Semantic kernel Function Choice Behavior Selection
- Heuristic:SeleniumHQ Selenium FindElements For Absence Check
- Heuristic:Unslothai Unsloth Merge Memory Management
- Heuristic:Ggml org Llama cpp Context Size Alignment
- Heuristic:Langfuse Langfuse BullMQ Retry Strategy Patterns
- Heuristic:Fede1024 Rust rdkafka Librdkafka Debug Logging
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Huggingface Trl Disable Dropout For RL Training
- Heuristic:Haosulab ManiSkill Initial Pose Performance
Environments
- Environment:Alibaba MNN ARM Mobile Environment
- Environment:SeleniumHQ Selenium Grid Deployment Environment
- Environment:Lm sys FastChat GPU CUDA Inference
- Environment:Allenai Open instruct Python 3 12 Runtime
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Mlc ai Mlc llm OpenCL Android Environment
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Norrrrrrr lyn WAInjectBench External Repos Dependencies
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Vespa engine Vespa Docker OCI Container Runtime