What's Actually
Used in AI Dev

Detects AI coding tools by config files: CLAUDE.md, .cursorrules, AGENTS.md, .windsurfrules, .github/copilot-instructions.md, .aider.conf.yml, .clinerules. Tracks 7 tools: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Windsurf, Aider, Cline.

1. 1 Claude Code 599
2. 2 AGENTS.md (Codex等) 371
3. 3 Cursor 40
4. 4 GitHub Copilot 30
5. 5 Windsurf 4

Primary language breakdown for AI-relevant repos (AI score ≥ 40). Aggregates GitHub's detected `primary_language` to show which languages dominate AI development.

1. 1 Python 97
2. 2 TypeScript 56
3. 3 JavaScript 18
4. 4 HTML 7
5. 5 Jupyter Notebook 3

GitHub topic tags self-applied by repo owners. llm/agent/rag/chatbot — what developers tag their AI projects with.

1. 1 claude 10
2. 2 llm 8
3. 3 mcp 7
4. 4 anthropic 6
5. 5 rag 6

Which LLM provider companies/SDKs are mentioned across observed repos. Counts mentions of OpenAI, Anthropic, Google Gemini, AWS Bedrock, etc.

1. 1 OpenAI 31
2. 2 Anthropic 27
3. 3 Gemini 22
4. 4 Ollama 13
5. 5 Groq 12

AI-specific frameworks: LangChain, LlamaIndex, AutoGen, CrewAI, etc. (Web/UI frameworks are in a separate category.)

1. 1 LangGraph 15
2. 2 LangChain 14
3. 3 LlamaIndex 3
4. 4 Vercel AI SDK 2
5. 5 CrewAI 1

General-purpose frameworks for AI app frontends/APIs: Next.js, FastAPI, Streamlit, Gradio, Django, React, Flask, etc.

1. 1 FastAPI 29
2. 2 Streamlit 25
3. 3 Next.js 21
4. 4 React 18
5. 5 Express 5

Where AI apps/models are deployed: AWS, GCP, Azure, Vercel, Cloudflare, Modal, Replicate, RunPod, Hugging Face Spaces, etc.

1. 1 Vercel 15
2. 2 AWS 3
3. 3 Railway 2
4. 4 Fly.io 1
5. 5 Azure 1

Authentication layer for AI SaaS: Auth0, Clerk, Supabase Auth, NextAuth, Firebase Auth, WorkOS, etc.

Bootstrapping

Vector databases for AI/RAG embeddings storage: Pinecone, Chroma, Qdrant, pgvector, FAISS, etc.

1. 1 Chroma 17
2. 2 pgvector 4
3. 3 Pinecone 1

General-purpose databases beyond vector storage: PostgreSQL, MySQL, MongoDB, Redis, Oracle, SQL Server, Supabase, Neon, etc.

1. 1 SQLite 10
2. 2 Redis 5
3. 3 Supabase 4
4. 4 PostgreSQL 4
5. 5 MySQL 4

Which specific LLM models get mentioned: GPT-4o, Claude 3.7, Gemini 2, Llama 3.x, DeepSeek-V3, etc.

1. 1 Claude 49
2. 2 Llama 24
3. 3 Gemini 22
4. 4 DeepSeek 8
5. 5 GPT-4 7

Embedding model adoption: text-embedding-3, nomic-embed, bge, jina, etc.

1. 1 sentence-transformers 2
2. 2 bge 2
3. 3 text-embedding-ada 1

AI agent construction frameworks: LangGraph, CrewAI, AutoGen, smolagents, MCP, etc.

1. 1 MCP 22