Instrument with the Wizard
Add Neatlogs to your project in minutes with one command.
The fastest way to add Neatlogs to an existing project is the wizard. Run one command, give it your API key, and it instruments your code for you.
npx @neatlogs/wizardRun it from your project root.
Get your project API key from the Neatlogs dashboard before you start. The wizard prompts for it interactively.
What it does
The wizard reads your project to detect your language, LLM providers, agent frameworks, and vector databases, then installs the latest Neatlogs SDK and instruments your code the right way for your stack. You don't pick an SDK version, an endpoint, or which files to edit.
When it finishes, run your app as usual — your first traces appear in the dashboard. The wizard also leaves behind a project-specific skill so your coding agent can keep instrumenting new code as your project grows, and offers to connect the MCP server so your agent can query your traces. Both are optional.
Requirements
- Node.js ≥ 20 (the wizard runs via
npx, whether your project is Python or TypeScript) - A Neatlogs account and API key
Supported stacks
The wizard detects and instruments a wide range of libraries across both languages:
| Supported | |
|---|---|
| LLM providers | OpenAI, Anthropic, Google GenAI, AWS Bedrock, Cohere, Groq, Mistral, Together, Ollama, Replicate, OpenRouter, Portkey, LiteLLM (plus Vertex AI when used through LangChain) |
| Agent frameworks | LangChain, LangGraph, CrewAI, LlamaIndex, OpenAI Agents, Pydantic AI, DSPy, Agno, Google ADK, Strands, AutoGen, Haystack, Smolagents (Python); LangChain, LangGraph, Mastra, Vercel AI SDK, OpenAI Agents (TypeScript) |
| Vector databases | Chroma, Pinecone, Qdrant, Weaviate, Milvus, Elasticsearch |
If your project mixes frameworks (say, the Vercel AI SDK plus LangChain in one app), the wizard instruments each one the right way.
Using Azure OpenAI? The SDK fully supports it via
neatlogs.wrap(AzureOpenAI(...))/wrapAzureOpenAI(...)— the wizard just doesn't auto-detect it yet, so wire it up with the one-line wrap from the Azure OpenAI integration.
Prefer to do it by hand?
The wizard is the recommended path, but everything it does you can do yourself. Follow the Python SDK or TypeScript SDK section for the manual setup.