DS DevShelfHub Projects · AI tools
Quick reference · 96 cheatsheets

Cheatsheets

Dense, scannable one-pagers for the tools you already know — the commands, classes, and patterns worth keeping under Ctrl + F. Not tutorials, not deep dives. Just the parts you forget.

96
sheets
4
topics
5m
avg read
LA AI frameworks

LangChain

75 items

LangChain is a Python/JS framework for composing LLM-powered applications: it provides a unified interface across model providers, a composable LCEL pipe syntax, and pre-built chains for RAG, agents, and memory. This cheatsheet covers the core imports, Chat and Embedding model wrappers, LCEL runnables, prompt templates, retrievers, agents, tools, LangGraph state, and full minimal RAG and agent examples.

Chains LCEL LangGraph RAG
7 min 2026-05-17
Open sheet
CR AI frameworks

CrewAI

102 items

Agents, Tasks, Crews, Processes, Flows — the everyday API surface plus the YAML config that drives a crew.

Agents Tasks Flows
6 min 2026-05-17
Open sheet
MO AI frameworks

Model Context Protocol

78 items

JSON-RPC primitives, tools, resources, prompts, sampling, lifecycle — the spec compressed into a one-page reference.

JSON-RPC Tools Resources
6 min 2026-05-17
Open sheet
PR Prompting

Prompt Engineering

64 items

Zero-shot, few-shot, chain-of-thought, role prompting, structured output, tool use — patterns and gotchas in one place.

Patterns CoT Structure
5 min 2026-05-17
Open sheet
GI Dev tooling

Git

97 items

Branching, rebasing, fixing mistakes, recovering lost commits, interactive rebase, worktrees — the commands you reach for under pressure.

Branches Rebase Recovery
7 min 2026-05-17
Open sheet
DO Dev tooling

Docker

97 items

Images, containers, volumes, networks, Compose, multi-stage builds, and BuildKit — the day-to-day Docker commands and Compose snippets for Docker Engine 25+ and Compose v2. Covers the full workflow from Dockerfile authoring through registry push and production cleanup.

Build Run Compose
6 min 2026-05-17
Open sheet
RE Dev tooling

Regex

65 items

Character classes, anchors, quantifiers, groups, lookarounds — with examples that actually parse the things you need.

Patterns Groups Lookarounds
5 min 2026-05-17
Open sheet
PY Languages

Python

105 items

Comprehensions, dataclasses, typing, async, pathlib, itertools — the standard-library surface a Python dev actually uses.

Stdlib Typing Async
7 min 2026-05-17
Open sheet
LL AI frameworks

LlamaIndex

97 items

LlamaIndex is a Python data framework for building LLM applications over custom documents: it handles ingestion (SimpleDirectoryReader, PDF, web), chunking, embedding, vector storage, and retrieval in a single opinionated pipeline. This cheatsheet covers Documents, Nodes, VectorStoreIndex, retrievers, query engines, the chat engine pattern, agents, tools, and production configuration.

Indices Retrievers QueryEngines
7 min 2026-05-17
Open sheet
HA AI frameworks

Haystack

79 items

Components, pipelines, document stores, retrievers, generators, agents — the deepset framework as a one-page reference.

Pipelines Components Stores
6 min 2026-05-17
Open sheet
AU AI frameworks

AutoGen

65 items

AgentChat, Core, Extensions — agents, teams, termination, tools, and the modern v0.4+ async API. Covers AssistantAgent, RoundRobinGroupChat, SelectorGroupChat, and the autogen_ext model clients for OpenAI, Anthropic, and Ollama.

Agents Teams Termination
6 min 2026-05-17
Open sheet
LA AI frameworks

LangSmith

63 items

LangSmith is LangChain's observability and evaluation platform: every chain and agent run is traced automatically, letting you inspect each step's inputs, outputs, latency, and token usage. This cheatsheet covers tracing setup, the Client API, dataset creation, evaluators, feedback logging, the Prompt Hub, and automated testing patterns for LLM applications in production.

Tracing Datasets Evals
6 min 2026-05-17
Open sheet