Agent Switchboard

Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Router 2.0 adds subscription-aware routing for Claude Code, Codex, and opencode.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your coding agent:

  • Sub-50ms Routing

    Use Workweave Router to route each prompt to the best model: ‹what you need›

Install the CLI

Install it as its own instructions say.

Its page: github.com/weave-os/router

Call the API

Auth An API key from Weave

Its page: github.com/weave-os/router

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
CLIAPI
Auth
API Key
Skills
3

Skills

  • Sub-50ms Routing

    Routes each prompt to the best model in under 50ms using an on-box embedder, no extra network hop.

  • Drop-In Proxy

    Acts as an Anthropic- and OpenAI-compatible proxy for Claude Code, Codex, and opencode.

  • Cost Reduction

    Cuts model spend 40-70% by sending simple prompts to cheaper models and hard ones to frontier models.

Infrastructure & Opsmodel-routingproxycost-optimizationclaude-codecodexopen-sourcellm-gateway
Visit Agent
workweave-router
Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Router 2.0 adds subscription-aware routing for Claude Code, Codex, and opencode.
try this first
Ask your coding agent:
Use Workweave Router to route each prompt to the best model: ‹what you need›sub-50ms-routing
use it now
An API key from Weaveapi.auth
fields
nameWorkweave Router
providerWeave
urlhttps://github.com/weave-os/router
categoriesinfrastructure
accesscli · api
authapiKey
streamingfalse
pushfalse
verifiedtrue
officialfalse
sponsoredfalse
tagsmodel-routing, proxy, cost-optimization, claude-code, codex, open-source, llm-gateway
skills
sub-50ms-routingSub-50ms RoutingRoutes each prompt to the best model in under 50ms usin…
drop-in-proxyDrop-In ProxyActs as an Anthropic- and OpenAI-compatible proxy for C…
cost-reductionCost ReductionCuts model spend 40-70% by sending simple prompts to ch…
alternatives
/agents/workweave-router/alternatives8 listedopenrouter, vercel-ai-gateway, litellm
compare
/compare?a=workweave-router&b=openrouter&c=vercel-ai-gatewaywith openrouter, vercel-ai-gateway