Braintrustdata Braintrust Claude Plugin
- 19 repo stars
- Updated July 23, 2026
- braintrustdata/braintrust-claude-plugin
braintrustdata-braintrust-claude-plugin is a Claude Code plugin bundle that connects Braintrust evaluation, conversation logging, and LLM observability to your local Claude Code sessions.
About
braintrustdata-braintrust-claude-plugin is a two-plugin Claude Code bundle from Braintrust that connects your local agent workflow to evaluation, structured logging, and observability. developers shipping AI features—chat assistants, coding agents, or API-backed LLM products—install it when they need more than printf debugging: they want traces of what Claude said, which tools fired, and how new prompts compare to baselines. The marketplace listing emphasizes automatic capture of conversations and usage, plus evaluation-oriented helpers so you can judge whether changes actually improve outcomes. It is not a replacement for your application’s unit tests; it is the layer that makes LLM-specific quality measurable. Use it during Ship when you are hardening agent behavior, and keep it on during Operate when you need ongoing visibility into real coding sessions and regressions.
- Bundle of 2 Claude Code plugins aimed at Braintrust eval, logging, and observability
- Automatically captures Claude Code conversations, messages, tool calls, and usage for traceability
- Helper scripts and examples for evaluation workflows against agent responses
- Enables observability across working sessions—not a one-off test script
- Fits agents and assistant-heavy builds that need logged, correctable LLM behavior
Braintrustdata Braintrust Claude Plugin by the numbers
- Data as of Jul 24, 2026 (Skillselion catalog sync)
/plugin install braintrustdata-braintrust-claude-plugin@braintrustdata/braintrust-claude-pluginAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 19 |
|---|---|
| Last updated | July 23, 2026 |
| Repository | braintrustdata/braintrust-claude-plugin ↗ |
What it does
Wire Claude Code agent runs into Braintrust for eval datasets, trace logging, and production-style LLM observability without leaving the editor.
Who is it for?
Best when you're running Claude Code daily on agent or LLM-backed products and already use or plan to use Braintrust for experiments and traces.
Skip if: Skip if you only need generic application error monitoring with no LLM-specific evals or conversation-level logging.
What you get
After you register the bundle, agent conversations and calls can be logged and evaluated in Braintrust so you can compare versions and monitor behavior over time.
- Structured logs and traces of Claude Code assistant activity
- Evaluation workflows tied to agent messages and tool usage
- Ongoing observability signal for prompt and tool change regressions
Recommended Plugins
Abix5 Memory HindsightHindsight memory bank integration for Claude Code
Agentic Dev Io Mcp Code ExecutionToken-efficient MCP server interaction through code execution.1
Agneym Agneym Claude MarketplaceClaude Code plugin marketplace for Agney's plugins
Akkomar Mozdata Claude Plugin1 plugin
Amitpatole Claude Genkit PluginFirebase Genkit Plugin for Claude Code12
Aserper RtfdSpoonfeed your AI coding assistant with up to date documentation efficiently and without using a cloud service with the RTFD mcp server that runs on YOUR machine without any API key requirements!14How it compares
LLM eval and observability plugin bundle, not a generic code-review or security audit skill.
FAQ
Who is Braintrustdata Braintrust Claude Plugin for?
and small-team developers using Claude Code on agent workflows who want Braintrust-backed evaluation, logging, and trace visibility for assistant behavior.
When should I use Braintrustdata Braintrust Claude Plugin?
Use it while shipping and iterating on LLM features—when you need to score responses, capture sessions, and watch regressions after prompt or tool changes.
How do I add Braintrustdata Braintrust Claude Plugin to my agent?
Install the plugin marketplace entry from the braintrustdata/braintrust-claude-plugin repository into Claude Code, complete Braintrust account setup, then enable the bundled plugins so hooks and helpers can record and evaluate runs.