Observability Startup Raindrop AI’s New Open Source, MIT Licensed "workshop" The tool, launched today, gives developers something they’ve probably subconsciously wanted since last year ushered in the agentic AI era: a native debugger and assessment tool designed specifically for AI agents, allowing developers to view all of their agent’s traces in a single, lightweight Structured Query Language (SQL) database file (.db).
It acts as a local daemon and UI that streams every token, tool call, and decision to a local dashboard – usually hosted at localhost:5899-The moment it happens. By visiting their localhost, developers can see everything their agent was doing – including mistakes or errors – and identify what went wrong, when, and ideally, understand why. All of this is stored in a single .db file, which takes up relatively little memory, according to an
This real-time telemetry eliminates the latency of traditional polling and addresses the growing developer concern regarding privacy of sending local traces to external servers.
This tool is available for macOS, Linux, and Windows. It can be installed via a one-line shell command that automates binary placement and PATH configuration for the bash, zsh, and fish shells. For developers who prefer to build from source, the repository is hosted on GitHub and uses the bun runtime.
Product: Installation of Self-Healing Eval Loop
The standout feature of the platform is "self-healing eval loop," Which allows coding agents like Cloud Code to read traces, write evaluations against the codebase, and fix broken code autonomously.
In practical application, if a veterinary support agent fails to ask the necessary follow-up questions, the workshop captures the full trajectory. Cloud Code then reads this trace, writes a specific eval, identifies the logic error in the prompt or code, and re-runs the agent until all assertions pass.
Compatibility and ecosystem integration
Workshop is compatible with a wide range of programming languages, including TypeScript, Python, Rust, and Go.
It integrates with popular SDKs and frameworks like Vercel AI SDK, OpenAI, Anthropic, Langchain, Laminedex, and CrewAI. It is also designed to work seamlessly with various coding agents, including Cloudflare, Cursor, Devin, and OpenCode.
Licensing and community implications
Workshop is released under the MIT License, ensuring that it remains free and open source for all users. The purpose of this permissive licensing is to foster community contributions and allow enterprise users to maintain data sovereignty.
Hillac notes on the X that the device was created to provide a "SANE" Changing the way agents debug locally, the way their teams and early customers build autonomous systems.
To celebrate the launch, Raindrop offered limited-edition physical merchandise to users who installed the tool and implemented a specific "Drip" Permission.
<a href