weave-os /router

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

★ 5,622⑂ 168👁 2⑃ 2,132● 74▤ 1
GoApache-2.0Created 2026-04-27weaveos.com/products/router
Download: HMM frozen model v1hmm-model-v1 ↓12026-07-13
+0
Daily
5,622
stars
168
forks
2
watchers
2,132
prs
74
issues
1
releases

README

!Built with Weave Router


 Weave Router

Weave Router is a proxy that selects a model for each API request. It works with
Anthropic, OpenAI, and Gemini APIs, so you can use it with coding tools or your
own application. You can use the hosted router or run it yourself with your own
provider keys. For the best experience, use the managed router hosted by Weave.

The router uses an HMM classifier policy to choose from enabled models.
It supports streaming, tool calls, and vision.

 Get started

For the hosted router, run the installer and follow the setup prompts:

bash
npx @weave-os/router


You'll need Node 18 or later. The hosted setup page can help you get a router
key; you can also create one in the Weave dashboard
under Settings → API keys. To choose a tool directly, use one of these commands:

bash
npx @weave-os/router --claude
npx @weave-os/router --codex
npx @weave-os/router --copilot
npx @weave-os/router --opencode
npx @weave-os/router --pi


The installer configures your selected tool to use Weave. For Copilot, it adds
Weave Router to the model picker; you can also start it with
copilot --model weave/auto.

For example, to switch Codex back to its previous provider, run
npx @weave-os/router off --codex. Use on --codex to switch back to Weave,
or --uninstall --codex to remove the configuration. See the installation guide for
what changes for each tool, project-level setup, and all available options.

For client-specific setup, connection checks, switching back, and uninstall, see the
Router quickstart, Claude Code guide,
and Codex CLI guide.

 Run it yourself

You'll need Docker, Go 1.26 or later, a provider API key, and a local checkout.
For example, with an OpenRouter key:

bash
git clone https://github.com/weave-os/router.git
cd router
echo 'OPENROUTER_API_KEY=sk-or-v1-...'  .env.local
echo 'ROUTER_ADMIN_PASSWORD=replace-with-a-strong-password'  .env.local
make full-setup


This starts the router and Postgres, creates a router key, and offers to set up
Claude Code. The router listens at  and the dashboard is
at . The router key (rk_...) is printed during
setup; use it to authenticate clients. Your provider key is separate and stays in
.env.local. Without an admin password, inference still works but dashboard
administration is disabled.

To connect another supported tool to the local router, add --local to its
installer command, for example:

bash
npx @weave-os/router --codex --local


Cursor routes its Agent and Ask chats through the router. Cursor calls the base
URL from its own servers, not from your machine, so a localhost router is
unreachable: use the hosted router or a publicly reachable self-hosted URL. In
Cursor, open Settings → Models, turn on OpenAI API Key with your rk_...
router key, set Override OpenAI Base URL to /v1, and add a custom
model named weave-auto (the router rejects other weave- names). Tab
completion and Apply stay on Cursor's own models, and BYOK needs a paid Cursor
seat.

The self-hosted router sends prompts

Top issues

Latest release

HMM frozen model v1 hmm-model-v1 Pre-release 2026-07-13
Portable frozen HMM router artifact for the companion policy sidecar.

- Model: hmm-router-frozen-v1
- Embedding contract: google/gemini-embedding-2, 3072 dimensions
- SHA-256: b326bda644aac86831bae47d0b69de008046f62324a4b93a1eba702581c174df
- Runtime data only: no Python pickle, training rows, prompts, training provenance, or WorkWeave registry dependency

This prerelease is intended for the self-hostable HMM sidecar PR. The router remains on cluster routing unless HMM is explicitly configured.

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON