AI News HubLIVE
In-site rewrite2 min read

Raindrop Workshop: The First Local Debugger for AI Agents

Raindrop Workshop is a free, open-source local debugger for AI agents that streams agent traces token-by-token in real time and integrates with Claude Code via MCP for self-healing agent loops.

SourceProduct Hunt AIAuthor: Alexis Gauba

Raindrop | Monitoring for AI agents | Product Hunt

Monitoring for AI agents

5.0•1 review•

296 followers

Monitoring for AI agents

5.0•1 review•

296 followers

Visit website

Observability tools

Raindrop helps AI engineers discover issues in production agents, and build “self-healing” agents that propose and validate fixes automatically.

Overview

Launches2

Reviews1

Alternatives

Customers

Built with

Team

More

This is the 2nd launch from Raindrop. View more

Raindrop Workshop

Launching today

Open source, free, local debugger for AI agents.

Raindrop Workshop is the first local debugger for agents.

It's free, local, and open source.

Your local agent traces stream, token-by-token, instantly. Another Agent like Claude Code can read them over MCP. Then Claude can write evals, replay traces, fix bugs... and do it all over again.

This is the Self-Healing Agent loop. And it’s only possible on Raindrop.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Subscribe

SocialLinkedInX

Previous Raindrop Launches

RaindropSentry for AI Products

Launched on April 29th, 2025

5.0

Based on 1 review

Review Raindrop?

Reviews

Most Informative

Knowledge infrastructure for AI agents

Promoted

Maker

📌

Hey PH! This is Alexis, Co-Founder of Raindrop.

Your agent fails at 1am, traces are in some SaaS dashboard, harness is on your machine, eval suite is in a third place, and Claude sees none of it.

We've been stuck in this loop. So we built our way out of it. Workshop is the first sane way to debug your agent locally.

It has two parts: a local UI and an MCP.

Every span streams live to a local browser UI and you can replay any agent run with edited prompts, models, and tools.

The MCP lets you create self-healing eval loops. Claude Code reads your traces, writes evals, and fixes what's broken.

It's free, open source, and works with all the agent SDKs you already use.

One command to install: curl -fsSL https://raindrop.sh/install | bash

Excited to hear what you think!

Report

2h ago

Welcome to the self-improving agentic world. Very solid team, great launch. Congrats Alexis!

Report

1h ago

Maker

@alexmasmej It's a crazy world! Thanks so much Alex

Report

1h ago

used Raindrop to build Letterbook

•15 reviews

The best AI monitoring and logging tool!

Alternatives Considered

Report

36 views2mo ago