Build an LLM eval dashboard with Langfuse, or a private local assistant with Ollama
goyalshaliniuk · x · 2026-09-13
Two hands-on project ideas for AI developers:
- AI evaluation & monitoring dashboard: Python + Langfuse + PostgreSQL to track response quality, latency, cost, and hallucinations while learning LLM evaluation, observability, tracing, and optimization. Langfuse is an open-source agent evals & observability platform with 34.5k stars.
- Local LLM assistant: Ollama + Python + Streamlit to run a fully private assistant on your laptop, covering local inference, quantization, prompt design, and privacy.
More from coding & agent
- Codex feels so productive it may be hiding your real progress, dev warns — alexmacgregor__ · 2026-09-13
- Building a company AI desktop stack: hunting a Claude Cowork alternative for non-technical staff — Feeling_Dog9493 · 2026-09-13
- Auto-manage your credit card rewards via Muse + CardStack's MCP connector — armand_ruiz · 2026-09-13
- Function calling explained: the 4-step loop behind every coding agent — Al_Grigor · 2026-09-13
- Fully offline camera app runs YOLOv8n + fine-tuned 0.8B VLM on-device, open-sourced — divinetribe1 · 2026-09-13
- Building a sleeping interactive character on Waveshare ESP32 with Copilot CLI — DanWahlin · 2026-09-13