// Switch models, control cost
envoyv1.39.3
Cloud-native high-performance edge/middle/service proxy
Open source Maintained For agents
IN ONE PARAGRAPH
envoy is cloud-native high-performance edge/middle/service proxy.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to switch models, control cost.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it from the official package registry:
brew install envoy - 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → litellm The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] ★ 62k new-api A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. ★ 50k kong 🦍 The API and AI Gateway ★ 44k claude-code-router One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control. ★ 38k apisix The Cloud-Native API Gateway and AI Gateway ★ 17k
03Related
- ›Ollama 文档 · OllamaEnglish
- ›handy-ollama 动手学 Ollama · DatawhaleChinese
- ›vLLM 文档 · vLLMEnglish
- ›SGLang 文档 · SGLangEnglish
- ›llama.cpp · ggml-orgEnglish
- All tutorials →