langchain-ai

langchain-ai / langsmith-cli

Public

A coding agent-first CLI for interacting with LangSmith.

17
2
100% credibility
Found Mar 05, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

A command-line interface for listing, querying, exporting, and managing LangSmith resources like traces, runs, datasets, evaluators, experiments, and threads.

How It Works

1
🔍 Discover LangSmith CLI

You learn about a simple tool that lets you peek into your AI app's activity logs straight from your command line.

2
📥 Get it set up

Copy and paste one easy command to download and place the tool on your computer.

3
🔗 Link your account

Share your LangSmith login info once so the tool knows your projects.

4
📋 See your projects

Ask to list all your AI projects and spot the active ones at a glance.

5
🔬 Explore traces and runs

Pull up full details of recent app sessions, check speeds, errors, and costs to understand what happened.

6
📊 Manage tests and scores

List datasets, experiments, or scoring rules to review and tweak your AI evaluations.

✅ Gain quick insights

Now you effortlessly review, export, and improve your AI app's performance every day.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is langsmith-cli?

Langsmith-cli is a Go-based CLI for querying and managing LangSmith resources like traces, runs, datasets, evaluators, experiments, and threads. It delivers agent-first coding access with JSON output by default for scripting and langsmith client integration, plus pretty tables and trees for quick human review. Developers get fast, scriptable LangSmith interaction without Python or JS SDK overhead—ideal for pulling traces or uploading eval datasets via simple commands like `langsmith trace list --project my-app` or `langsmith dataset upload data.json`.

Why is it gaining traction?

It stands out as a lightweight langsmith client alternative to verbose SDKs, with built-in filters for errors, latency, tokens, and tags, plus export to JSONL for analysis. The agent-first design shines for github coding agents like Cursor or Claude Code, enabling automated trace pulls or eval runs without custom wrappers. Pretty hierarchies and full CRUD for datasets/experiments make debugging LLM apps feel instant.

Who should use this?

LLM engineers tracing production agent runs in LangSmith who need CLI speed over web UI. Eval teams bulk-uploading datasets or managing evaluators for experiments. Github coding agent builders integrating langsmith client.trace for real-time feedback loops.

Verdict

Grab it if LangSmith is your observability stack—installs easily via script, covers 90% of query needs. Alpha status means expect changes, but strong docs and tests offset the 1.0% credibility score from just 17 stars.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.