██████  ██████  ███████ ███    ██ ███████ ███    ███ ██ ████████ ██   ██ 
██    ██ ██   ██ ██      ████   ██ ██      ████  ████ ██    ██    ██   ██ 
██    ██ ██████  █████   ██ ██  ██ ███████ ██ ████ ██ ██    ██    ███████ 
██    ██ ██      ██      ██  ██ ██      ██ ██  ██  ██ ██    ██    ██   ██ 
 ██████  ██      ███████ ██   ████ ███████ ██      ██ ██    ██    ██   ██ 

opensmith

The open-source, local-first alternative to LangSmith.

opensmith is to LangSmith what Ollama is to OpenAI — the local-first, privacy-first alternative.

Why opensmith?

Why opensmith

LangSmith is powerful, but it is built around cloud-hosted tracing and is most natural inside the LangChain ecosystem. opensmith is a local-first alternative: install it with pip, use it with any Python LLM pipeline, and inspect traces on your machine without accounts, hosted services, Docker, or configuration. No trace data leaves your machine.

Install

pip install opensmith

Quickstart

Example 1: @trace decorator

from opensmith import trace


@trace
def call_llm(prompt: str):
    return openai.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
    )


@trace
def my_pipeline(question: str):
    # search_docs is your own retrieval function
    docs = search_docs(question)
    return call_llm(docs + question)

Async functions are supported:

from opensmith import trace


@trace(tags=["production", "rag"])
async def call_llm(prompt: str):
    return await openai.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
    )

Example 2: context manager

from opensmith import trace


with trace("my_pipeline", tags=["debug"]) as t:
    t.log("query", query)
    response = openai.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": query}],
    )
    t.log("response", response)

Example 3: autopatch() zero code changes

from opensmith import autopatch


autopatch()

Patch only selected backends:

from opensmith import autopatch


autopatch(only=["openai"])

Patch everything except selected backends:

from opensmith import autopatch


autopatch(exclude=["chromadb"])

Console mode

Print trace results to the terminal as they complete:

from opensmith import set_console_mode, trace


set_console_mode(True)


@trace
def my_func():
    return "ok"

Configuration

opensmith reads opensmith.json from the current working directory on import:

{
  "db_path": "./my_traces.db",
  "console_mode": false,
  "autopatch": ["openai", "qdrant"]
}

Dashboard

opensmith ui

Open http://localhost:7823.

CLI reference

Supported backends

Storage

Traces are stored locally at ~/.opensmith/traces.db unless overridden with opensmith.json or set_default_db_path().

Star History

License

MIT