Developer Builds Single-Key AI Gateway Routing 18 Models With Auto-Failover

·1 views

A developer has built an OpenAI-compatible API gateway that consolidates access to 18+ large language models under a single endpoint and API key, eliminating the need for separate provider accounts. The gateway uses rule-based request profiling to route simple tasks to free or low-cost models and complex reasoning requests to flagship models, reducing overall API spend. An automatic failover system detects provider errors such as rate limits or timeouts and silently retries on backup providers, with production logs showing eight consecutive successful switches without user impact. The gateway also tracks upstream peak and off-peak pricing windows and adjusts its own markup accordingly, passing cost savings to users during off-peak hours. A free tier offering 100 API calls is available, and the project is shared on DEV Community for developers seeking to reduce vendor lock-in and infrastructure complexity.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Framework Proposes Four-Layer System to Build a Personalized AI Agent Modeled on You

A new practical framework published on DEV Community expands on AI researcher Andrej Karpathy's concept of a 'second self' — an AI trained to replicate a person's thinking, decisions, and voice. While Karpathy experimented with a personal wiki to capture declared knowledge and values, the framework argues that tacit knowledge — instincts, judgment calls, and unspoken expertise — remains largely unencoded. To address this gap, the proposed system organizes personal AI training into four layers: identity, reasoning, skills, and intuition, each sourced from different data types. Techniques such as think-aloud recordings, behavioral logging, and chain-of-thought distillation are combined into a structured week-by-week build plan. The goal is an AI agent capable of representing a person's reasoning and defaults even in their absence.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Malaysian Agency Hand-Wrote 154 Local SEO Pages and Tracked What Worked

Penang-based web design agency Seed Light, founded by Gregory Yeoh, manually wrote 154 local landing pages across 19 services and 8 Malaysian cities instead of using templated programmatic SEO. The approach was driven by Google's March 2024 scaled-content policies, which increasingly penalise pages that are near-identical except for swapped city names. Each page was tailored to genuine local market realities — for example, Johor Bahru pages addressed cross-border Singapore customers, while Kuala Lumpur pages focused on committee-based procurement. Even the hand-written pages initially contained 79 duplicate strings, highlighting that human writers can inadvertently template their own work at scale. The agency concluded that honest local detail, structured answer passages, and clean internal linking consistently outperformed volume-based content strategies.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to Build a Typed Content Moderation Layer in Node.js Using JSON Schema

A software architecture guide outlines a content moderation pattern for Node.js applications where uploaded content stays in a pending state until a chat-completions-compatible adapter returns a locally validated JSON Schema result. The design separates responsibilities clearly: Node.js handles authentication, rate limits, and file inspection, while a moderation component receives only an item ID, normalized text, and an approved image reference. Text and image are evaluated together in a single decision envelope, since captions and visuals can alter each other's meaning. The system enforces a strict three-way outcome — allow, block, or review — where 'review' explicitly captures uncertainty, policy mismatches, or malformed responses rather than defaulting to approval. A runnable Python example is provided to illustrate the contract, though the pattern can be implemented in any language as long as the versioned decision object is preserved.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

What a Compromised Password Manager Master Password Actually Means for Your Data

A password manager secures all stored credentials behind a single master password, making that password a high-value target — its compromise can expose an entire vault rather than just one account. However, encryption still plays a critical role because well-designed password managers never store the master password directly; instead, they use it to derive a cryptographic key that unlocks the encrypted vault. Algorithms like AES are commonly used to ensure that stolen vault data remains unreadable without the correct key. The overall security depends on multiple factors, including how the key is generated and protected, and how the master password itself is processed. Weak master passwords remain a significant vulnerability, as attackers can undermine even strong encryption through efficient guessing if key derivation parameters are inadequate.

0 comments Read more at DEV Community