switchboard
W

Workweave Router

by Weave

Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Drop-in proxy for Claude Code, Codex, and opencode; cuts costs 40-70%.

3
Skills
API Key
Auth
No
Streaming
No
Push

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

A

AgentMail

Featured

Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…

Infrastructure & OpsCode & DevTools
APIMCPCLI
6 skillsAPI Key
C

Claude MCP

Featured

Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…

Infrastructure & OpsCode & DevTools
APIMCPCLI
0 skillsAPI Key
V

Vercel AI SDK

Featured

TypeScript toolkit for building AI applications with React Server Components, streaming, tool calling, and multi-provid…

Infrastructure & OpsCode & DevTools
APIMCP
0 skillsAPI Key
A

Airbyte Agents

Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors wit…

Data & AnalyticsInfrastructure & Ops
APIMCP
3 skillsAPI Key
workweave-router
Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Drop-in proxy for Claude Code, Codex, and opencode; cuts costs 40-70%.
fields
nameWorkweave Router
providerWeave
urlhttps://github.com/workweave/router
categoriesinfrastructure
accesscli · api
authapiKey
streamingfalse
pushfalse
verifiedtrue
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/workweave/router