Raindrop AI Launches Open-Source Tool for Local AI Agent Debugging

AI Launches Open-Source Tool for Local AI Agent Debugging">

Raindrop AI, an observability startup, has launched a new open-source tool called Workshop, which provides developers with a local debugger and evaluation tool specifically designed for AI agents. This tool has been a long-awaited solution for developers working with agentic AI, which has gained significant traction over the past year. Workshop allows developers to see all the traces of what their agent has been doing in a single, lightweight Structured Query Language (SQL) database file (.db).

Workshop functions as a local daemon and UI that streams every token, tool call, and decision to a local dashboard, typically hosted at localhost:5899. This provides developers with real-time telemetry, eliminating the latency of traditional polling and addressing growing concerns regarding the privacy of sending local traces to external servers. According to Ben Hylak, Raindrop's co-founder and CTO, the .db file takes up relatively little memory.

The tool is available for macOS, Linux, and Windows, and can be installed through a one-line shell command that automates binary placement and PATH configuration for bash, zsh, and fish shells. For developers who prefer to build from source, the repository is hosted on GitHub and utilizes the Bun runtime. One of the standout features of Workshop is the "self-healing eval loop," which allows coding agents like Claude Code to read traces, write evals against the codebase, and fix broken code autonomously.

Workshop is compatible with a broad range of programming languages, including TypeScript, Python, Rust, and Go, and integrates with popular SDKs and frameworks such as the Vercel AI SDK, OpenAI, Anthropic, LangChain, LlamaIndex, and CrewAI. It is also designed to work seamlessly with various coding agents, including Claude Code, Cursor, Devin, and OpenCode. The tool has been released under the MIT License, ensuring it remains free and open-source for all users.

The launch of Workshop marks a significant milestone for Raindrop AI, and the company is celebrating by offering limited-edition physical merchandise to users who install the tool and execute a specific "drip" command. According to Hylak, the tool was built to provide a "sane" way to debug agents locally, changing how their team and early customers build autonomous systems.