Show HN: OpenSmith – Trace LLM pipelines locally with trace, no cloud

OpenSmith, an open-source, local-first alternative to LangSmith for tracing LLM pipelines, launched with 100% local data storage via SQLite and no cloud requirement. The tool, installable via pip, supports any Python LLM pipeline and offers a local dashboard at localhost:7823, with optional integrations for OpenTelemetry and Postgres.

The open-source, local-first alternative to LangSmith. opensmith is to LangSmith what Ollama is to OpenAI — the local-first, privacy-first alternative. | LangSmith | opensmith | | |---|---|---| | Setup | Cloud account required | pip install opensmith | | Data privacy | Sends traces to cloud | 100% local, SQLite only | | Framework | Best with LangChain | Works with any Python code | | Cost | Free tier then paid | Free forever, open source | | Offline | No | Yes | | Docker | No | No | | Dashboard | Hosted | localhost:7823 | 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. pip install opensmith Optional integrations: pip install "opensmith otel " pip install "opensmith postgres " pip install "opensmith all " Use opensmith all to install both OpenTelemetry and Postgres support. python 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: python 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} , Warn when a trace exceeds a token budget: python from opensmith import trace @trace token budget=1000 def my pipeline : return call llm "summarize this document" python 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 python from opensmith import autopatch autopatch Patch only selected backends: python from opensmith import autopatch autopatch only= "openai" Patch everything except selected backends: python from opensmith import autopatch autopatch exclude= "chromadb" Print trace results to the terminal as they complete: python from opensmith import set console mode, trace set console mode True @trace def my func : return "ok" opensmith reads opensmith.json from the current working directory on import: Create a starter config: opensmith init { "db path": "./my traces.db", "console mode": false, "autopatch": "openai", "qdrant" } opensmith ui Open http://localhost:7823 . If the port is already in use, opensmith automatically tries the next available port. Use --no-auto-port to disable this behavior. | Command | Description | |---|---| opensmith init | Create a starter opensmith.json config. | opensmith ui | Start the local dashboard with automatic port selection. | opensmith traces --q rag --status err --tags production | List and filter traces in the terminal. | opensmith stats | Show aggregate trace, step, token, and cost statistics. | opensmith export | Export traces to JSON or CSV. | opensmith clear | Delete all locally stored traces after confirmation. | | Backend | Package | Status | |---|---|---| | openai | openai | ✅ | | anthropic | anthropic | ✅ | | litellm | litellm | ✅ | | qdrant | qdrant-client | ✅ | | chromadb | chromadb | ✅ | | pinecone | pinecone-client | ✅ | Traces are stored locally at ~/.opensmith/traces.db unless overridden with opensmith.json or set default db path . Use Postgres instead by installing opensmith postgres and setting OPENSMITH DB URL : export OPENSMITH DB URL="postgresql://user:pass@localhost:5432/opensmith" Install both Postgres and OpenTelemetry support with pip install "opensmith all " . Export traces with nested steps as JSON: opensmith export --format json --output traces.json Export a flat trace list as CSV: opensmith export --format csv --output traces.csv OpenTelemetry export is disabled by default. Install the optional dependencies and set OPENSMITH OTEL ENDPOINT to enable OTLP HTTP export: pip install "opensmith otel " export OPENSMITH OTEL ENDPOINT="http://localhost:4318" opensmith sends traces to /v1/traces and metrics to /v1/metrics under that endpoint. MIT