Why you should always build your own LLM proxy: auth, caching, cost visibility
viksit · x · 2026-11-19
viksit argues you should 'always build your own LLM proxy', citing easier auth and RBAC, logging and telemetry, caching, data loss prevention, simpler internal app integration, and per-container network access rules. He also recommends Cloudflare outbound workers.
Quoted builder samsaffron adds that a proxy is a game changer for agent/harness development: digging into payloads makes it easy to debug low cache-efficiency cases and tell whether the fault is yours or the API's, gives full cost visibility — and his original motivation was simply to stop giving agents inside Docker containers real credentials.
More from coding & agent
- Human Principal launches private beta: cryptographic proof a human is behind your AI agent — yenkel · 2026-11-19
- GPT-6.2 builds code-only 3D fairy town and a deep-sea civilization in 10–20 minutes — OpenAIDevs · 2026-11-19
- Designers are being asked to do interior design while ignoring the architecture — round · 2026-11-19
- Dev builds a playable FPS in under 5 hours with GPT-6.2 and Unreal Engine 5.9 MCP — OpenAIDevs · 2026-11-19
- Stop vibe coding: a 7-step AI coding workflow from AGENTS.md to hooks — _jaydeepkarale · 2026-11-19
- You're using 10% of Postgres RLS: FORCE RLS, security_invoker and more — _jaydeepkarale · 2026-11-19