{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigsxf6so6ja3ug2ebod3k7kwmmedew7plyy3gboajuwejca7fmfge",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mjvxkuas5z62"
  },
  "path": "/t/we-built-traceai-an-open-source-tool-for-tracing-llm-calls-in-production/175403#post_1",
  "publishedAt": "2026-04-20T05:47:15.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "GitHub - future-agi/traceAI: Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks · GitHub"
  ],
  "textContent": "Hey everyone\n\nWe have been building traceAI, an open-source observability tool\nfor LLM apps in production. It captures every call, inputs, outputs,\nlatency, costs, and errors with minimal setup.\n\nWorks with any LLM backend.\n\nRepo: GitHub - future-agi/traceAI: Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks · GitHub\n\nWould love feedback from folks here. What does your current\nmonitoring setup look like for production LLM apps?",
  "title": "We built traceAI, an open-source tool for tracing LLM calls in production"
}