GoKawiilExperiential launches open-source LLM gateway that learns from traffic to build custom routers
A new open-source project called Experiential offers an OpenAI-compatible gateway and router for agent workflows, letting teams route requests across hosted, bring-your-own-key, and local models through a single API. It includes controls over which users and agents can access specific models, spending limits, and a wizard that sets up a local gateway with a one-time API key in minutes. A hosted version is also available, supporting both OpenAI and Anthropic Messages API formats and integration with coding agents like Claude Code, Cursor, and Codex.
GoKawiil's interpretation of the reporting above, not reported fact.
As companies juggle multiple LLM providers and rising inference costs, tools that centralize access control, budgeting, and observability across models are becoming critical infrastructure for AI teams. By turning production usage data into an optimized custom router, Experiential offers a path to automatically balance cost, speed, and quality without manual tuning—an approach that could reduce vendor lock-in and give smaller teams enterprise-grade routing capabilities.
- Experiential is an open-source, OpenAI-compatible gateway for routing agent traffic across hosted, BYOK, and local LLMs.
- It supports granular controls over model access, spending budgets, and use-case restrictions per user or agent.
- A hosted version integrates directly with coding agents and converts real usage telemetry into a custom-optimized router or model.
Source: github.com, 2026-08-27
Published there as: “Show HN: We built open OpenRouter that distills usage into a better model”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.