Ross ROSS = Recommend OSS · open-source software intelligence for agents

raindrop-ai/workshop

Give your coding agent the power to write and run agent evals. observed · 2026-08-28

github.com/raindrop-ai/workshop · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

81/100

  • Activity 99
  • Release rhythm 99
  • Longevity 8

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 125
  • days_rel: 11
  • days_push: 11
  • n_releases_24m: 22

Full methodology

Adoption not part of the score

1058 stars · 63 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Raindrop Workshop is an open-source local debugger for AI agents that streams live traces of tokens, tool calls, and decisions into a browser UI. It integrates with coding agents like Claude Code to read traces, write and run evals against your codebase, and replay production traces locally.

Use cases

  • debug my AI agent locally with live traces
  • watch every token and tool call my LLM agent makes
  • have Claude Code write and run agent evals
  • replay a production agent trace against local code
  • instrument my Vercel AI SDK or LangChain app for tracing
  • turn agent failures into tests automatically

When to choose

  • you're building LLM/agent apps and need local, real-time trace debugging
  • you want your coding agent to autonomously write evals and fix agent failures
  • you use supported SDKs (Vercel AI SDK, OpenAI/Anthropic SDKs, LangChain, CrewAI, Pydantic AI, Mastra) and want zero-config tracing
  • you prefer a free, local, open-source tool over hosted-only observability

When to avoid

  • you need production-scale observability and team dashboards - that's Raindrop Cloud, not Workshop
  • your agent framework or SDK has no Raindrop integration
  • you need a fully self-contained workflow with no cloud connection at all
  • you're not working with LLM-powered agents or AI features

Facets

cli-tool · maturity active

tracing monitoring testing developer-tools mcp large-language-models developer-tools windows cli python go rust agent-debugging llm-observability agent-evals trace-replay coding-agent-integration local-debugger ai-agents debugging macos linux typescript

10 sources

Member repositories

RepositoryRoleHealth v2
raindrop-ai/workshopmain81

For agents

markdown · JSON · MCP: product_card(name="raindrop-ai/workshop")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem