10 Open-Source Projects for Observability, Eval and Cost Control in AI Apps
Shruti_0810 · x · 2026-11-02
A curated list of 10 GitHub projects for keeping AI applications accurate, fast and cost-efficient after launch:
- Langfuse: visibility into LLM calls, prompts, token usage and costs
- Arize Phoenix: trace investigation, output evaluation, RAG pipeline debugging
- Promptfoo: test prompts and models to catch failures before users do
- DeepEval: automated tests for quality, hallucinations and RAG
- TruLens: measure how retrieval and generation steps work together
- The attached image also highlights LiteLLM (62k stars AI Gateway, Rust core + Python SDK, calls 100+ LLM APIs in OpenAI format)
A practical engineering index for AI app quality assurance.
More from coding & agent
- Software fundamentals are key to getting good results from AI coding agents — bendee983 · 2026-11-02
- PR adds patient retry logic for model capacity errors in OpenAI Codex — bytebot · 2026-11-02
- Perplexity open-sources WANDR: 500 research tasks, 170,495 evidence points, URL-rechecking grader — thisguyknowsai · 2026-11-02
- 4 AIs, 96 questions, 2,671 citations: 74% are blog posts, 99% on companies' own sites — tibo_maker · 2026-11-02
- Agent audit said 0 blocks while hooks logged 7: Claude Code transcript drift broke a blind detector — Ok-Motor-9812 · 2026-11-02
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02