langsmith-fetch
LangSmith Fetch - Minimal CLI for fetching LangSmith threads and traces
Decision gist · record as of 2026-08-14
Yes, if you actively use LangSmith and need a quick way to export traces and threads for testing or debugging. The low install friction and straightforward CLI make it easy to adopt. However, the aging maintenance status (no updates in 245 days) and unclear license warrant verification before use in production or proprietary contexts. No known security vulnerabilities.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10 and valid LangSmith API credentials (LANGSMITH_API_KEY and LANGSMITH_PROJECT environment variables).
- Low install friction with six common runtime dependencies.
- Maintenance status is aging—the package has not been updated since its initial release 245 days ago, which may indicate limited ongoing support or that it has reached a stable endpoint.
License · maintenance · safety
(unclear) — License treatment is unclear; no SPDX identifier or raw license text is available in the metadata. Verify the actual license before use in proprietary or restricted contexts.
last release 2025-12-12 (245 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 83,667 downloads/mo, #14,057 on PyPI
Alternatives
Verify before relying
pip install langsmith-fetch
export LANGSMITH_API_KEY=lsv2_...
export LANGSMITH_PROJECT=your-project-name
langsmith-fetch traces ./my-traces --limit 10- Whether the package is actively maintained or has reached a stable, feature-complete state despite no updates in 245 days.
- Actual license terms, since license_treatment is marked unclear and no SPDX or raw license text is provided.
- Whether the 71 tests mentioned in the description are actually present and passing in the current release.
What it is and what it does
LangSmith Fetch is a command-line tool for exporting traces and threads from LangSmith projects. It wraps the LangSmith API to let you bulk-download recent execution data or retrieve specific items by ID, saving them as JSON files or printing them to stdout. The tool is built on click, requests, and rich for a polished CLI experience, and integrates with python-dotenv for environment-based configuration.
You use it primarily for testing and debugging—pulling real LangSmith data locally to inspect, validate, or feed into other tools. It supports filtering by time range, customizable output formats (pretty, JSON, raw), and concurrent fetching. Configuration is minimal: set your API key and project name as environment variables, and the tool handles the rest, including automatic project UUID lookup and caching.
Use it for
- Export recent traces from a LangSmith project to a local directory for offline inspection and debugging.
- Fetch a specific trace or thread by ID and pretty-print it to stdout for quick inspection during development.
- Bulk-download traces with metadata and feedback for integration into test suites or validation pipelines.
- Use as a programmatic data source for code agents that need to retrieve LangSmith execution history.
- Filter and export traces from the last N minutes or since a specific timestamp for incident analysis.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you actively use LangSmith and need a quick way to export traces and threads for testing or debugging.
The low install friction and straightforward CLI make it easy to adopt. However, the aging maintenance status (no updates in 245 days) and unclear license warrant verification before use in production or proprietary contexts. No known security vulnerabilities.
Install
langsmith-fetch on PyPI
Before you install
Low install friction with six common runtime dependencies. Maintenance status is aging—the package has not been updated since its initial release 245 days ago, which may indicate limited ongoing support or that it has reached a stable endpoint.
Requires Python >=3.10 and valid LangSmith API credentials (LANGSMITH_API_KEY and LANGSMITH_PROJECT environment variables).
License in practice
License treatment is unclear; no SPDX identifier or raw license text is available in the metadata. Verify the actual license before use in proprietary or restricted contexts.
Quickstart
pip install langsmith-fetch
export LANGSMITH_API_KEY=lsv2_...
export LANGSMITH_PROJECT=your-project-name
langsmith-fetch traces ./my-traces --limit 10Verify before relying
- Whether the package is actively maintained or has reached a stable, feature-complete state despite no updates in 245 days.
- Actual license terms, since license_treatment is marked unclear and no SPDX or raw license text is provided.
- Whether the 71 tests mentioned in the description are actually present and passing in the current release.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packagesclicklangsmithpython-dotenvpyyamlrequestsrich |
| Maintenance | Aging 245 days since the last release |
| First released | |
| Downloads | 83,667 / month, #14,057 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: langsmith_fetch-0.3.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “langsmith data export cli”
- langsmith-fetchA CLI tool for fetching traces and threads from LangSmith projects,…
- langsmith-mcp-serverExposes LangSmith observability data (conversation history, prompts,…
- langsmithLangSmith is a Python client SDK for the LangSmith observability and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Testing packages
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
virtualenv creates isolated Python environments where packages can be installed independently without affecting the system Python or other projects.
Coverage.py measures which lines of Python code are executed during test runs, reporting coverage percentages and identifying untested code paths.
Install it if you want to measure test completeness or enforce coverage thresholds in your project.
pytest-asyncio is a pytest plugin that enables writing and running async test functions using the asyncio library, allowing developers to await code directly within test cases.
Install it if you write tests for any asyncio-based code.
A pytest plugin that generates test reports in Common Test Report Format (CTRF) as JSON, compatible with pytest-xdist and pytest-playwright for distributed and browser-based testing.
Install it if you need CTRF-formatted test output for CI/CD integration or cross-tool reporting.
See also langsmith-mcp-server · langsmith · langchainplus-sdk · langgraph-sdk · langgraph-checkpoint · langgraph-checkpoint-sqlite · langwatch · langchain-cli · langgraph-checkpoint-postgres · langgraph