langchain-ai

langchain-ai / langsmith-claude-code-plugins

Public

LangSmith plugins for Claude Code

18
4
100% credibility
Found Apr 04, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A plugin for Claude Code that automatically traces conversations, tool calls, subagents, and context compaction to LangSmith for visualization and debugging.

How It Works

1
🔍 Discover session tracking

You hear about a handy add-on that records your AI coding chats for easy review.

2
📥 Add the add-on

Inside your AI coding tool, you grab the add-on from its marketplace with a simple command.

3
🔗 Link your dashboard

You sign up for a free tracing dashboard, grab a private passcode, and connect it so your sessions get saved there.

4
💬 Chat and build as usual

You keep using your AI helper for coding questions, file edits, and tasks like normal.

5
📊 Traces appear automatically

Behind the scenes, every conversation turn, tool use, and helper action gets captured without interrupting your flow.

6
👀 Review in your dashboard

Open your online dashboard to see colorful diagrams of what happened in each session.

✅ Master your AI sessions

You now spot patterns, debug tricky moments, and improve your coding workflow effortlessly.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 18 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-claude-code-plugins?

This TypeScript plugin brings LangSmith tracing to Claude Code, Anthropic's AI coding agent, capturing full conversations, tool calls, subagent runs, and context compaction in LangSmith traces. Developers install it directly in Claude Code via the plugin marketplace with commands like `/plugin install langsmith-tracing@langsmith-claude-code-plugins`, set a LangSmith API key via env vars like `CC_LANGSMITH_API_KEY`, and get detailed traces of inputs, outputs, token usage, and metadata without changing their workflow. It solves the black-box problem of local AI coding sessions by piping everything to LangSmith for debugging and analysis.

Why is it gaining traction?

Unlike generic logging, it nests Claude Code traces under existing LangSmith runs from LangSmith SDK or LangSmith Python GitHub workflows, making it a smooth LangSmith GitHub integration for agentic apps. Features like automatic interruption marking and subagent support (with completion-only tracing) stand out for teams using LangSmith agent builder GitHub tools or LangSmith Studio GitHub dashboards. The zero-config plugin install and env var toggles like `TRACE_TO_LANGSMITH=true` hook devs who want observability without SDK wrappers.

Who should use this?

AI engineers prototyping with Claude Code in local terminals, LangChain devs invoking it programmatically via subprocesses, or teams monitoring GitHub Actions with LangSmith GitHub repo traces. Ideal for backend devs debugging tool-heavy coding agents or full-stack teams correlating Claude Code sessions with LangSmith Helm deployments.

Verdict

Grab it if you're deep in Claude Code and LangSmith—solid for observability, with clear docs and TypeScript reliability. At 18 stars and 1.0% credibility score, it's early but functional; test in a side project before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.