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:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Fastai Fastbook NLP Text Classification
- Workflow:FlagOpen FlagEmbedding Embedder Inference
- Workflow:Bentoml BentoML Multi Model Composition
- Workflow:Hiyouga LLaMA Factory LoRA SFT Finetuning
- Workflow:Dagster io Dagster LLM Fine Tuning
- Workflow:SeleniumHQ Selenium Browser Session Setup
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Facebookresearch Audiocraft EnCodec Compression Training
Principles
- Principle:Microsoft DeepSpeedExamples LoRA Fusion And Export
- Principle:FMInference FlexLLMGen HELM Dependency Installation
- Principle:Puppeteer Puppeteer Device Emulation
- Principle:Haifengl Smile SQL to ML Bridge
- Principle:TA Lib Ta lib python C Library Installation
- Principle:Interpretml Interpret Debug And Logging
- Principle:Langfuse Langfuse ChatML Normalization
- Principle:AUTOMATIC1111 Stable diffusion webui Hypernetwork training configuration
- Principle:AUTOMATIC1111 Stable diffusion webui Embedding creation
- Principle:DevExpress Testcafe Runner Fluent Configuration
Implementations
- Implementation:Infiniflow Ragflow ForceGraph Component
- Implementation:Ggml org Llama cpp Jinja String
- Implementation:SeleniumHQ Selenium Bazel Test With Filters
- Implementation:Apache Flink AsyncSinkBaseBuilder Build
- Implementation:Isaac sim IsaacGymEnvs Task Design Specification
- Implementation:Cohere ai Cohere python ModelsClient
- Implementation:Facebookresearch Habitat lab SingleAgentAccessMgr
- Implementation:Interpretml Interpret TreeNode
- Implementation:PrefectHQ Prefect Client Delete Flow Run
- Implementation:Mlflow Mlflow Pyproject Configuration
Heuristics
- Heuristic:CARLA simulator Carla Behavior Agent Profiles
- Heuristic:AnswerDotAI RAGatouille Index Rebuild Vs Update Decision
- Heuristic:Dotnet Machinelearning LDA Thread Reservation
- Heuristic:OpenBMB UltraFeedback Principle Distribution Tuning
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:TA Lib Ta lib python Compatibility Mode Switching
- Heuristic:Bentoml BentoML Warning Deprecated Runner Class
- Heuristic:Princeton nlp Tree of thought llm Ad Hoc Value Map Scoring
- Heuristic:Microsoft Autogen Warning Deprecated JSON Env Files
- Heuristic:Nightwatchjs Nightwatch Node 17 DNS IPv4 Workaround
Environments
- Environment:Promptfoo Promptfoo Node Runtime
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:OpenHands OpenHands Frontend Build Environment
- Environment:Sdv dev SDV Python Runtime
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:Unstructured IO Unstructured Ingest CLI
- Environment:Kubeflow Pipelines KFP Backend Deployment