# weave-os/router

> A model router proxy for agentic systems that picks the right model per request across Anthropic, OpenAI, Gemini and OpenRouter, cutting costs 40-70% with just an endpoint change. It acts as a drop-in API replacement and works with Claude Code, Codex, Cursor and custom apps.

- Magnitude: 0.9 out of 10 — Steady
- Stars: 5,591 total · +0 stars measured 2026-10-14, 00:02–11:12 UTC, ≈ 1 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: Apache-2.0 · Created: 2026-04-27 · Last push: 2026-10-14
- GitHub: https://github.com/weave-os/router · Homepage: https://weaveos.com/products/router · Page: https://gitnova.dev/en/r/weave-os/router

## Useful for

- Point Claude Code or Codex at localhost:8080 to auto-select a model per request
- Cut LLM costs while keeping provider keys on your own box via BYOK
- Inspect the routing decision via /v1/route without proxying the request

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 00:02–11:12: 5592 → 5591 stars (-1). This is the change over that interval.
- Recent forks include notable developers: @dorucioclea (314 followers).

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 2 watchers for 5,591 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 156
- Issues and pull requests: 1,705
- Watchers: 2
- Average over the last week: 4 per day
- Usual pace: 48 per day
- Latest release: hmm-model-v1 (2026-07-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: 10, 10, 7, 7, 1, 8, 5, 3, 3, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-01 1.7, 10-02 2.2, 10-03 1.9, 10-04 1.5, 10-05 1.4, 10-06 1.4, 10-07 1.4, 10-08 1.3, 10-09 1.3, 10-10 1.0, 10-11 1.3, 10-12 1.2, 10-13 1.2, 10-14 1.0

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-14 11:15 UTC, updated every 30 minutes.