10 Open-Source Tools for Building Trustworthy AI Apps, from Langfuse to TruLens
Shruti_0810 · x · 2026-11-09
A curated list of 10 open-source GitHub repos for building production-ready LLM applications, focused on observability and evaluation:
- Langfuse: tracing, prompt management, and cost tracking for LLM apps
- Arize Phoenix: debugging AI workflows and investigating retrieval/response-quality issues
- Promptfoo: automated prompt and model comparison testing before deployment
- DeepEval: measuring response quality, hallucinations, and RAG performance
- TruLens: evaluation and tracking for LLM experiments and AI agents (4k GitHub stars)
The core argument: demos look impressive, but the real test comes when real users arrive, costs grow, and unexpected errors appear — that's where these tools matter.
More from coding & agent
- Vercel's agent-browser hits 48k stars: a Rust CLI that reads pages as accessibility trees for AI agents — sven_ai · 2026-11-09
- Same AI, different game: getting answers vs directing engineering work — burhop · 2026-11-09
- Dev builds full-screen voice face for Mac that drives Codex coding agents hands-free — Ok-Suspect-9855 · 2026-11-09
- DeepSeek agent harness wired to a Grok x_search plugin pulls live X posts, demo shows — teortaxesTex · 2026-11-09
- Agent passed its own tests while wrong: lessons from a 2-bit local model building a Unity game — Stunning-Sherbet1853 · 2026-11-09
- 12 GitHub repos poisoned with CLAUDE.md prompt injection tricking AI coding agents into running malware — cyb3rops · 2026-11-09