All activity
Joshua Knauberleft a comment
Hey everyone! AI agents are surprisingly easy to build. Understanding what they're doing is another story. I recently had a complex coding agent where subagents silently stopped passing responses to each other. An error somewhere in the chain, but instead of failing loudly, the agents just worked around it. Output looked almost right. I only found it by accident after hours of debugging. With...
BreadcrumbOpen-source LLM tracing for agent visibility
Breadcrumb is the Plausible of LLM tracing. Self-hosted, open source, and built for developers who just want to understand what their agents are actually doing without the enterprise bloat of LangFuse or LangSmith.
Three lines to get your app traced. An LLM watches every trace and automatically flags issues: wrong tool calls, looping agents, oversized models and cost spikes, all before you even know something's wrong. Ask questions about your traces in plain English and get charts back.
BreadcrumbOpen-source LLM tracing for agent visibility
Designers love Claude Code for prototyping, but tweaking designs is still hard. Flare fixes this.
Works with any web app: Add a script tag or Vite plugin. Edit CSS visually in the browser, copy as a prompt, paste into Claude Code to update your source.
Flare DesignVisual CSS editor that ships code changes through Claude AI
Joshua Knauberleft a comment
Hey everyone! I've been talking to designers experimenting with Claude Code and noticed a pattern: removing the coding step was a wow moment, but going back to tweak CSS still required technical knowledge. What's next for Flare: Text content editing Expanded CSS compatibility Component library integration MCP server for direct file injection (no copy-paste) This is v1. Would love to hear what...
Flare DesignVisual CSS editor that ships code changes through Claude AI