Agent Router (formerly Envoy AI Gateway)
Open-source, Envoy-powered control plane giving agents one OpenAI-compatible API for every model and one router for MCP tools, with provider credentials, failover and token limits. It was formerly Envoy AI Gateway and is now an Agentic AI Foundation project.
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 18 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Tier
- T3
- Section
- Inference platforms & gateways
- Created
- 2024-10-21 repo fix
- Latest release
- last commit 2026-10-28 repo fix
- License
- Apache-2.0 vendor fix
- Pricing
- searched not found fix
- Funding
- searched not found fix
- Freshness
- 2026-10-29 fix
- Layer
- model-infra repo fix
- Licensing
- open-source vendor fix
- Protocols
- mcp-client, mcp-server, openai-compatible, opentelemetry vendor fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
Your Docusaurus site did not load properly.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- searched not found
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- yes
Similar systems
Other inference platforms & gateways in the catalog, ranked by inbound references.
- LiteLLM T1
BerriAI's open-source LLM gateway — unified OpenAI-format API for 100+ providers; LiteLLM Proxy adds budgets, fallbacks, observability, rate-limiting.
- OpenRouter T1
Unified API + marketplace for 300+ models — pay-as-you-go credits, automatic fallback, model arena. Used as default LLM router by many JS/TS agents.
- Together AI T1
Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated endpoints, fine-tuning API, training cluster.
- Fireworks AI T1
Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-LoRA serving. Targets latency-sensitive production use cases.
- vLLM T1
Open-source LLM inference engine with PagedAttention — high-throughput batching, paged KV-cache. UC Berkeley origin; de-facto OSS inference stack.
- Portkey AI T2
AI gateway + observability — load balancing across 200+ LLMs, retries, caching, eval, prompts. Open-source Gateway + commercial Portkey Cloud. Acquired by Palo Alto Networks (closed about 2026-06); now sold as Prisma AIRS AI Gateway (GA 2026-07-16).
Sources (17 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Framework vendor
- What it does & what's distinct Open-source, Envoy-powered control plane giving agents one OpenAI-compatible API for eve… vendor
- Claims / benefits Your Docusaurus site did not load properly. vendor
- Created 2024-10-21 repo
- Latest release last commit 2026-10-28 repo
- License Apache-2.0 vendor
- GitHub https://github.com/theagentrouter/agent-router (2314★) repo
- Mindshare 2314 GitHub stars repo
- OTel yes vendor
- Project & sources https://theagentrouter.ai/ ; https://github.com/theagentrouter/agent-router vendor
- obs-opentelemetry yes vendor
- cost-observability-cost-attribution yes vendor
- licensing-bucket open-source vendor
- taxonomy-three-layer-rollup model-infra repo
- sdk-languages go,rest repo
- protocol-support mcp-client,mcp-server,openai-compatible,opentelemetry vendor
- maturity ga vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-30 Added to the catalog #347
Related systems
References (11)
- Agent2Agent Protocol (A2A) integrates with — Agent Router docs have an Agent2Agent (A2A) traffic capability page. (verified 2026-10-29)
- Anthropic Claude (foundation models) integrates with — Agent Router supported-providers page lists Anthropic (native and on GCP Vertex AI / AWS Bedrock). (verified 2026-10-29)
- Cohere Command R+ / Command A integrates with — Agent Router supported-providers page lists Cohere (compatibility API). (verified 2026-10-29)
- DeepSeek R1 / V3 family integrates with — Agent Router supported-providers page lists DeepSeek. (verified 2026-10-29)
- Google Gemini 3 family integrates with — Agent Router supported-providers page lists Google Gemini on AI Studio. (verified 2026-10-29)
- Mistral Large 2 / Mixtral family integrates with — Agent Router supported-providers page lists Mistral. (verified 2026-10-29)
- Model Context Protocol (MCP spec) integrates with — Agent Router docs have an MCP gateway capability page. (verified 2026-10-29)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — Open-source, Envoy-powered control plane giving agents one OpenAI-compatible API for every model and one router for MCP tools, with provider credentials, failover and token limits.
- Together AI integrates with — Agent Router supported-providers page lists Together AI. (verified 2026-10-29)
- vLLM integrates with — Agent Router supported-providers page lists self-hosted vLLM. (verified 2026-10-29)
- xAI Grok 4 integrates with — Agent Router supported-providers page lists xAI Grok. (verified 2026-10-29)