@agentrouterai

One OpenAI-compatible API for every model, one router for every MCP tool. Formerly Envoy AI Gateway.

theagentrouter.ai
Joined October 2026
  • Tweets20
  • Following3
  • Followers50
7Media
$ROUTER is now live on Pons. Integrate once. Switch models without rewriting. Providers, credentials, limits and failover move out of your agent and into one router. Models. Tools. Agents. One router. CA: 0x83890309681e005506ef32887406e9c8cd9dc5f3
52
1
62
959
What is Agent Router, and why does your agent need one? A thread on the problem, how it works, and what it does for you 🧵
23
27
310
How it works: you describe providers, credentials, tools and limits once. Agent Router turns that into Envoy configuration. Agent Router configures. Envoy handles the traffic, the same proxy that already carries much of the world's production traffic.
1
19
Agent Router moves all of that out of your agent and into configuration. Your agent gets one OpenAI-compatible API for every model and one router for every MCP tool. Platform teams handle providers, credentials, limits and failover.
1
2
25
The problem: every agent ends up carrying its own provider APIs, credentials, failover logic, tool wiring and token limits. That's a lot of infrastructure living inside code that should be about the agent itself.
12
15
196
Agent Router is built in the open: an Agentic AI Foundation project with maintainers from four companies and weekly meetings on Mondays. 1.2 is the first release under the new name. Bring the production problem you're actually running into.
9
12
223
Your agent never counts a token.
3
136
Agent Router configures: providers, credentials, routing, tools and limits. Envoy handles the traffic, as it has in production for a decade.
2
156
Agent Router is open source. Read the code, run it on your laptop, ship the same config to Kubernetes. github.com/theagentrouter/ag…

GitHub - theagentrouter/agent-router: Manages Unified Access to Generative AI Services built on...

Manages Unified Access to Generative AI Services built on Envoy Gateway - theagentrouter/agent-router

github.com
4
2
194
From laptop to production, only the packaging changes. OPENAI_API_KEY=sk-... aigw run export OPENAI_BASE_URL=http://localhost:1975/v1 The same config ships to a gateway or a Kubernetes cluster. Or skip the install and use a hosted service.
1
113
$ROUTER supply burned. 🔥 Burned for good. Back to building. robin.etherscan.io/tx/0x8131…
12
9
154
One integration point for your agent. Six things that move out of your agent code and into configuration: 1/7
6
134
7/7 · Observability. Which model answered, how many tokens, time to first token, where a fallback kicked in. No instrumentation in your agent, OpenTelemetry GenAI conventions.
4
6/7 · Inference-aware routing. Route to self-managed models with Kubernetes InferencePool support and inference-aware endpoint picking.
4
5/7 · One router for every MCP tool. One tool catalog from many MCP servers, filtered by who is asking, so context stays small and wrong-tool calls stay rare.
6
4/7 · Credentials stay out of your code. Your agent authenticates to the router and nothing else. Provider keys and AWS, GCP and Azure credentials are rotated in one place.
5
3/7 · Traffic management. Provider fallback, model name virtualization, and token limits per team, app, or model. Your agent never counts a token.
6
2/7 · One API, every provider. Route OpenAI-compatible requests to Anthropic, Bedrock, Vertex, Azure, or self-hosted vLLM. Switching models is changing the model name.
113
Formerly Envoy AI Gateway. Same code, same maintainers.
103
Integrate once. Switch models without rewriting. Agent Router gives your agent one OpenAI-compatible API for every model and one router for every MCP tool. Platform teams set up providers, credentials, limits and failover. Envoy handles the traffic.
1
97
Load more