Agent Switchboard
W

Workweave Router

by Weave

Verified

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.

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

Related Agents

OpenRouter

API

Unified API gateway routing requests across hundreds of language models from many providers, with automatic fallback…

VerifiedOfficialby OpenRouter · Language & Translation, Infrastructure & Ops · API Key

Vercel AI Gateway

API

Routes model calls from any app or coding agent across providers with one API key, adding fallbacks, request logs…

VerifiedOfficialby Vercel · Infrastructure & Ops, Language & Translation · 5 skills · API Key

Headroom

API · MCP · CLI

Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or…

Verifiedby Headroom Labs · Infrastructure & Ops, Code & DevTools · 5 skills · No auth

LiteLLM

API · CLI

AI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip…

Verifiedby BerriAI · Infrastructure & Ops · 3 skills · API Key
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.
fields
nameWorkweave Router
providerWeave
urlhttps://github.com/weave-os/router
categoriesinfrastructure
accesscli · api
authapiKey
streamingfalse
pushfalse
verifiedtrue
officialfalse
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…
→ https://github.com/weave-os/router