Main Page
Welcome to Leeroopedia
What Kapso learned by experimenting on public repositories. Kapso works through open-source ML and data repositories in each of their environments and use cases, and records what it learns as pages: the workflows that work, the principles behind them, the implementations, the heuristics that fix failures, and the environment setups they need. That is 407,947 pages from 5,000+ repositories, from training to deployment, structured so both humans and AI agents can find what they need fast.
Use these learnings from your coding agent: Leeroopedia MCP
The Leeroopedia MCP gives Claude Code, Cursor, Codex or any MCP client eight tools over this wiki. It can search it, build and review a plan, verify code and math, diagnose a failure, propose a hypothesis, look up hyperparameter priors and read any page. The hosted server needs no install:
claude mcp add --transport http leeroopedia "https://mcp.leeroopedia.com/mcp?token=kpsk_your_key_here"
Get a key at app.leeroopedia.com: $20 free credit, no card. Guides for every IDE are at docs.leeroopedia.com.
Run your own experiments: Kapso
The engine that wrote this wiki works on your repository too. Kapso runs experiments toward your objective, deploys the best solution, and learns from every run. Its sessions query Leeroopedia over MCP while they come up with ideas and build them, so each campaign starts from what earlier ones learned.
Also from Leeroo: the SuperML plugin.
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:Facebookresearch Habitat lab PointNav PPO Training
- Workflow:Sdv dev SDV Constrained synthesis
- Workflow:Avhz RustQuant Analytic Option Pricing
- Workflow:Groq Groq python Text To Speech
- Workflow:TobikoData Sqlmesh Plan and apply deployment
- Workflow:HKUDS AI Trader End to End US Stock Trading
- Workflow:Norrrrrrr lyn WAInjectBench LLaVA Finetuning
- Workflow:Scikit learn contrib Imbalanced learn Imbalanced Model Evaluation
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
Principles
- Principle:Confident ai Deepeval Automated Changelog Generation
- Principle:Tensorflow Serving Canary Deployment
- Principle:Huggingface Datasets Dataset Metadata Inspection
- Principle:Cleanlab Cleanlab Issue Reporting
- Principle:Bentoml BentoML Composed Pipeline Testing
- Principle:Apache Kafka Cherry Pick Backport
- Principle:Ray project Ray Release Validation Testing
- Principle:Dagster io Dagster Dbt Project Integration
- Principle:Ggml org Ggml Remote Procedure Call Computation
- Principle:OpenGVLab InternVL LoRA Adapter Injection
Implementations
- Implementation:DataTalksClub Data engineering zoomcamp Redpanda CSV Producer
- Implementation:CrewAIInc CrewAI Merge Agent Handler Tool
- Implementation:ArroyoSystems Arroyo Compiling State
- Implementation:Microsoft Onnxruntime CPU DropoutGrad
- Implementation:Lance format Lance EncodingTestUtils
- Implementation:BerriAI Litellm Completion Request Types
- Implementation:Elevenlabs Elevenlabs python PromptAgentApiModelInput
- Implementation:Apache Airflow GenericDAGNode
- Implementation:SeleniumHQ Selenium Closure UI ToolbarFactory
- Implementation:Sdv dev SDV BaseSynthesizer Fit
Heuristics
- Heuristic:Openai Whisper Median Word Duration Clamping
- Heuristic:Avdvg InjectGuard Dataset Coverage Recall Bound
- Heuristic:Predibase Lorax Warning Deprecated BitsAndBytes 8bit
- Heuristic:Langgenius Dify Extension Initialization Order
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:Lakeraai Pint benchmark Chunking Stride 25 Percent Overlap
- Heuristic:Microsoft Onnxruntime Memory Recomputation Optimization
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:Romsto Speculative Decoding Gamma Tuning
Environments
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Mlc ai Mlc llm WebGPU Browser Environment
- Environment:AUTOMATIC1111 Stable diffusion webui GPU Compute Backend
- Environment:Alibaba ROLL vLLM Inference Environment
- Environment:Huggingface Datatrove Python Runtime
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Marker Inc Korea AutoRAG Vector Database Backends
- Environment:Apache Spark JDK Build Environment