Board Archive Editions Search Newsletter

01BoardToday on GitHub
02ArchiveEvery day we kept
03EditionsThe Weekly Star
04SearchThe whole record
05NewsletterEvery Monday

How we pick PrivacyCaptured daily

A field guide to open source.
Follow the work. Keep the record.

How we pick Privacy

A project by Patrick Xin

Board Archive Editions Search Newsletter

01BoardToday on GitHub
02ArchiveEvery day we kept
03EditionsThe Weekly Star
04SearchThe whole record
05NewsletterEvery Monday

How we pick PrivacyCaptured daily

cheaper-inference/OmniRoute — Starlogs

cheaper-inference /

OmniRoute

An LLM gateway that routes OpenAI-compatible requests across many providers, using free tiers by default with zero-config auto routing.

developer-tools
self-hosted
ai-gateway
coding-agent

Stars: 64,489
Sightings: 21
Best rank: No. 1
First seen: Aug 13
Language: TypeScript

Open on GitHub ↗

Each star is a day on a trending board. The higher it ranked that day, the larger and higher the star.

First seen Aug 13, No. 1, its highest
Last seen Sep 11, No. 11 · 21 days on the boards

What it's for.

Route LLM calls across providers via one endpoint
Use free-tier LLM providers with zero config
Connect coding CLIs like Claude Code and Codex

How you start.

Install OmniRoute; it works immediately with no keys or configuration
Send OpenAI-compatible chat requests to the local endpoint using the auto model
Use the CLI configure and run commands to set up and launch supported coding CLIs

Before you begin.

Free-tier availability is not guaranteed: providers can change quotas, eligibility, models, or regions at any time.

Stars+17,295 since first seen

counted on a capture dayjoined straight between counts

Sightings21 days on the boards

no boards keptnot on a boardfewer starsmore

Nearby

Close by description, tags or language

decolua
9router
A local proxy service that routes AI coding tools to 40+ providers with token compression and subscription-to-free model fallback.

tashfeenahmed

freellmapi

Self-hosted service that pools free-tier LLM providers behind one OpenAI-compatible API with routing, failover, and per-key rate tracking.

Alishahryar1

free-claude-code

Local proxy server that lets coding agents like Claude Code and Codex use models from many providers, including free tiers.