OmniRoute vs router
Free MIT AI gateway for coding CLIs: one endpoint over 352 providers (150+ free tiers) and 1,200+ models with quota-aware auto-fallback, RTK+Caveman token compression, MCP/A2A and a desktop app. — versus — Weave's Go model router: drop-in proxy speaking Anthropic, OpenAI and Gemini APIs that scores each request with an on-box ONNX embedder (Avengers-Pro clusters) and routes to the cheapest fit model.
Both put a local endpoint in front of coding CLIs; omniroute maximises provider/free-tier coverage, weave router optimises which model handles each request.
| OmniRoute | router | |
|---|---|---|
| Stars | 64k | 4.2k |
| Forks | 8.9k | 116 |
| Language | TypeScript | Go |
| License | MIT | NOASSERTION |
| Last activity | yesterday | yesterday |
| Topics | gateway, coding | gateway |
| Curated connections | 7 | 5 |
OmniRoute — the curator's take
The maximalist gateway for people who refuse to pay per token: it catalogues 444 free-tier entries, computes an honest monthly budget (~1.47B tokens, re-audited fortnightly, regional-ID quotas shown separately), and schedules Claude Code, Codex, Cursor, OpenCode, Cline or Copilot traffic across them with quota-aware fallback so a limit never stops you. 61k stars and 550 contributors are real. NOT for a production application: 352 providers means 352 terms of service and 352 latency profiles, and the value is breadth, not guarantees. For a small, predictable stack use a purpose-built gateway; use OmniRoute to keep coding when your subscription runs dry.
router — the curator's take
Choose it when the goal is *smart* routing, not just multi-provider fan-out: an in-process embedder classifies each action and picks a model per request in under 50ms, with a `/v1/route` endpoint to inspect the decision and OTLP traces out of the box. `npx @weave-os/router` wires Claude Code, Codex, opencode or pi in one step; self-hosting needs Postgres (and Pub/Sub for multi-replica). Don't reach for it if you want a plain gateway (litellm), free-tier pooling (omniroute), or to route through subscription CLIs (cliproxyapi) — and note the Elastic License v2, which is not OSI open source, and that the frictionless quickstart is the hosted service.