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:Mistralai Client python Streaming Chat Completion
- Workflow:Vllm project Vllm Speculative Decoding
- Workflow:Openai Evals Running a single eval
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Openai Whisper Audio Transcription
- Workflow:Huggingface Trl GRPO Training
- Workflow:Hiyouga LLaMA Factory LoRA SFT Finetuning
- Workflow:Iterative Dvc Experiment Tracking
- Workflow:Zai org CogVideo Video Captioning
- Workflow:ArroyoSystems Arroyo UDF Development
Principles
- Principle:Langchain ai Langchain Package Configuration
- Principle:Anthropics Anthropic sdk python API Request Execution
- Principle:Trailofbits Fickling Pickle Scanner Benchmarking
- Principle:Liu00222 Open Prompt Injection Combined Attack Injection
- Principle:Volcengine Verl FSDP Distributed Training
- Principle:Duckdb Duckdb Performance Regression Detection
- Principle:Langchain ai Langgraph Release Automation
- Principle:Princeton nlp Tree of thought llm Naive Baseline Sampling
- Principle:Openai Openai agents python Agent Definition
- Principle:OpenGVLab InternVL Vision Language Projection
Implementations
- Implementation:Cypress io Cypress Component Config Options
- Implementation:Microsoft Playwright DefaultFontFamilies
- Implementation:MarketSquare Robotframework browser WebApp State Keywords
- Implementation:Elevenlabs Elevenlabs python VoicesClient Search
- Implementation:Microsoft Playwright CssParser
- Implementation:Farama Foundation Gymnasium CliffWalkingEnv
- Implementation:Haotian liu LLaVA DeepSpeed ZeRO Configuration
- Implementation:Apache Druid HistoryDialog
- Implementation:Openai Openai node ChatCompletionStream Class
- Implementation:CARLA simulator Carla World Apply Settings For Sync
Heuristics
- Heuristic:Apache Dolphinscheduler Gzip Compression Threshold
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Marker Inc Korea AutoRAG Data Format Requirements
- Heuristic:Mlfoundations Open flamingo Gradient Clipping Max Norm
- Heuristic:Astronomer Astronomer cosmos Deprecation Migration Paths
- Heuristic:Huggingface Peft Warning Deprecated Bone
- Heuristic:LMCache LMCache Health Monitor Thresholds
- Heuristic:Promptfoo Promptfoo Warning Deprecated Cache Migration
- Heuristic:Confident ai Deepeval Dotenv Loading Order
- Heuristic:BerriAI Litellm SSL Cipher Optimization
Environments
- Environment:Astronomer Astronomer cosmos Cloud Provider Dependencies
- Environment:Huggingface Peft BitsAndBytes Quantization
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:Norrrrrrr lyn WAInjectBench External Repos Dependencies
- Environment:Guardrails ai Guardrails OpenTelemetry Tracing