[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-76074":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},76074,"workshop","raindrop-ai\u002Fworkshop","raindrop-ai","Give your coding agent the power to write and run agent evals.","https:\u002F\u002Fwww.raindrop.ai\u002Fworkshop\u002F",null,"TypeScript",875,45,594,1,0,13,32,236,39,94.99,"MIT License",false,"main",true,[27,28,29],"llm","raindrop","tracing","2026-06-12 04:01:20","\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fdocs\u002Fassets\u002Fworkshop-hero.png\" alt=\"Workshop: the local debugger your agent is missing.\" width=\"100%\">\n\u003C\u002Fp>\n\n# Raindrop Workshop\n\n**The local debugger your agent is missing.** Watch your agent think locally,\nthe moment it happens: every token, every tool call, every decision.\n\nGive Claude Code the power to read your traces, write evals against your\ncodebase, and fix what's broken.\n\n## Install\n\n```bash\ncurl -fsSL https:\u002F\u002Fraindrop.sh\u002Finstall | bash\n```\n\n## Build from source\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fraindrop-ai\u002Fworkshop.git\ncd workshop\nbun install\nbun run dev\n```\n\n`bun run dev` starts the local Workshop daemon and Vite UI. Open\n`http:\u002F\u002Flocalhost:5899` after it starts.\n\n## Instrument your agent\n\nOpen your coding agent of choice in your repository and run:\n\n```text\n\u002Finstrument-agent\n```\n\nThis will instrument your agent with Raindrop tracing and open Workshop in your browser.\n\nThat's it. Traces stream into the UI the moment your agent runs.\n\n## What it does\n\n- **Live streamed traces.** Every token, tool call, and span streams into\n  Workshop as it happens. No polling, no refreshing.\n- **Coding-agent integration.** Claude Code reads your traces, writes evals\n  against your codebase, and fixes what's broken.\n- **Self-healing eval loop.** Claude writes the eval, runs your agent, sees the\n  failure, fixes the code, and re-runs — until every assertion passes.\n- **Local replay.** `\u002Fsetup-agent-replay` scaffolds an HTTP endpoint that replays a\n  production trace against your real agent code.\n\n## Compatible with everything\n\n- **Languages:** TypeScript, Python, Go, Rust\n- **SDKs:** Vercel AI SDK, OpenAI Agents SDK, Anthropic SDK, Claude Agent SDK,\n  LangChain, LangGraph, CrewAI, Mastra, Pydantic AI, DSPy, Google ADK, Strands,\n  Agno, Deep Agents\n- **Providers:** AWS Bedrock, Azure OpenAI, Vertex AI\n- **Coding agents:** Claude Code, Codex, Devin, Cursor, OpenCode\n\n## Configuration\n\n| Env var | Purpose | Default |\n| --- | --- | --- |\n| `RAINDROP_WORKSHOP_PORT` | HTTP + WS port | `5899` |\n| `RAINDROP_WORKSHOP_DB_PATH` | SQLite database file | `~\u002F.raindrop\u002Fraindrop_workshop.db` |\n| `RAINDROP_LOCAL_DEBUGGER` | SDK-side: where to mirror traces | unset |\n\n## CLI\n\n```bash\nraindrop workshop          # start and open UI\nraindrop workshop setup    # write .env, then start and open\nraindrop workshop status   # check health\nraindrop workshop reset    # delete local DB after confirmation\nraindrop update            # update the binary\n```\n\n## License\n\nMIT.\n","Raindrop Workshop 是一个本地调试工具，旨在为编码代理提供实时追踪和评估功能。它支持实时流式传输代理的每个令牌、工具调用及决策过程，无需手动刷新页面即可查看最新状态。此外，该工具集成了多种编程语言（如TypeScript, Python等）和SDK，能够与Claude Code等编码代理无缝协作，自动修复代码中的错误，并通过自愈评估循环确保所有断言均能通过。适用于需要对AI驱动的编码代理进行深入分析和调试的场景，帮助开发者更高效地定位并解决问题。",2,"2026-06-11 03:54:23","CREATED_QUERY"]