#3030th of 53 in Gateways and observability

router

Proxy that picks a model per request across Anthropic, OpenAI and Gemini APIs

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 5.6k
License: Apache-2.0
Last commit: Nov 2026
Language: Go

Stars, last 28 weeks+5,618

2 on 28 Apr 20265,620 on 10 Nov 2026

From GitHub's daily star counts.

Checked 12 Nov 2026 on GitHub.

Overview

Weave Router is a Go proxy that chooses a model for each request using an embedding and cluster scorer based on Avengers-Pro. It accepts Anthropic Messages, OpenAI Chat Completions and Gemini requests, and forwards to Anthropic, OpenAI, Gemini, OpenRouter or any OpenAI-compatible endpoint. A hosted router is offered, or it can be self-hosted with Postgres and a dashboard.

Who it is for: Engineers routing coding-tool or app traffic across several LLM providers

Strengths

Accepts Anthropic, OpenAI and Gemini request formats, with streaming, tool calls and vision
Installer configures Claude Code, Codex, Copilot, opencode and pi, with on/off switching
POST /v1/route shows a routing decision without calling a model
Self-hosted mode includes a dashboard, rk_ keys and OpenTelemetry tracing

Weaknesses

README recommends the Weave-managed router over self-hosting
Self-hosted HMM policy is frozen, without training, online learning or registry
Cursor cannot reach a localhost router; needs a public URL and a paid seat
Multi-replica deployments additionally need Pub/Sub for cache invalidation

What it needs

no GPU
Docker + Compose
Needs Docker, Postgres, Go 1.26+, Node 18+ (installer), Provider API key, Pub/Sub (multi-replica)
Models: Anthropic, OpenAI, Gemini, OpenRouter, OpenAI-compatible endpoints
port 8080

Also in Gateways and observability

See all 53

Also in Gateways and observability
Rank	Project	Score
1	OmniRouteLLM gateway routing one OpenAI-compatible endpoint across 372 providers86.8k stars+11,398 (+15%) in 30 daysMIT	96 out of 100
2	headroomCompresses tool outputs, logs and history before they reach the LLM79.5k stars+4,550 (+6.1%) in 30 daysApache-2.0	92 out of 100
3	new-apiGateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs51.8k starsAGPL-3.0known advisory in latest version	91 out of 100
#4	MLflowTracing, evaluation and prompt registry for LLM apps, plus ML tracking Live demo ↗ (opens in a new tab)28.8k starsApache-2.0	91 out of 100
#5	LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers63.2k starscustom license	88 out of 100

How to choose

List the providers you call today; check the gateway's native support rather than generic passthrough.
Key management, per-team budgets and audit logs separate gateways from simple proxies.
Check latency overhead and whether streaming is passed through unchanged.

Health

Releases: No GitHub releases
Top contributor: 54% of commits982 of 1,826 in the last 12 months
Security advisories: 1 published ↗ (opens in a new tab)On GitHub, in the last 12 months; 1 critical or high
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 11 Nov 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

Apache-2.0 Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

Set it up

Needs before it works: Docker, Postgres, Go 1.26+, Node 18+ (installer), Provider API key, Pub/Sub (multi-replica).

Bring in an engineer who knows router. By the hour for upkeep and fixes, or a fixed price for a build. Our own engineering service; it never changes a rank.

Where to run it

RackNerd ↗ (opens in a new tab)Budget KVM VPS from $26.99 a year to run Docker apps yourself.
RepoCloud ↗ (opens in a new tab)One-click hosting for about 890 open-source apps, each on its own VPS.

Referral links: if you sign up through one, we get a commission. They never change a rank.

Ask your AI assistant

The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.

Setup for other apps

Claude Codeclaude mcp add archestack -- npx -y @archestack/mcp

Connector URLhttps://mcp.archestack.com/mcp

Then ask: Compare router with its top alternatives on Archestack

#30 of 53 in Gateways and observability on Archestack, as of 12 Nov 2026.

Show it in your README or on your site

The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.

Show code

README (Markdown)

[![Archestack](https://archestack.com/badge/weave-os/router.svg)](https://archestack.com/best-of-ai/projects/router/)

Site or blog (HTML)

<iframe src="https://archestack.com/embed/best-of-ai/router/" title="router on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

How badges work Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with router filled in.

Chat and assistants

Agents and MCP

RAG, search and memory

Voice

Image and video

Workflows

Coding with AI

Apps and SaaS

Models and ML

Security

Learning

By field