[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:respan-gateway":3},"\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.respan.ai\" rel=\"nofollow ugc noopener\">\n    \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fassets\u002Fwordmark-dark.png\">\u003C\u002Fsource>\n      \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frespanai\u002Frespan-gateway\u002FHEAD\u002Fdocs\u002Fassets\u002Fwordmark.png\" alt=\"Respan Gateway\" width=\"420\" \u002F>\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n  \u003Ch1>Respan Gateway: open-source LLM gateway\u003C\u002Fh1>\n  \u003Cp>\u003Cb>The universal adapter for AI.\u003C\u002Fb>\u003C\u002Fp>\n  \u003Cdiv>\n    \u003Ca href=\"#license\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT%20OR%20Apache--2.0-brightgreen.svg?style=flat\" alt=\"License: MIT OR Apache-2.0\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frespanai\u002Frespan-gateway\u002Factions\u002Fworkflows\u002Fci.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Frespanai\u002Frespan-gateway\u002Fci.yml?branch=main&amp;style=flat&amp;label=CI\" alt=\"CI\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frespanai\u002Frespan-gateway\u002Freleases\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Frespanai\u002Frespan-gateway?style=flat&amp;label=Latest%20Release&amp;color=6D28D9\" alt=\"Latest release\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fcrates.io\u002Fcrates\u002Frespan-gateway\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fcrates\u002Fv\u002Frespan-gateway?style=flat&amp;logo=rust&amp;label=crates.io&amp;color=6D28D9\" alt=\"crates.io\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frespan-gateway\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Frespan-gateway?style=flat&amp;logo=python&amp;logoColor=white&amp;label=PyPI&amp;color=6D28D9\" alt=\"PyPI\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002FKEanfAafQQ\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?style=flat&amp;logo=discord&amp;logoColor=white\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fdiv>\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\u003Cp>\u003Cstrong>Respan Gateway\u003C\u002Fstrong> is an open-source LLM gateway: a single Rust binary that sits between your code and\nevery AI API. Point the SDK you already use at it, and it connects you to\neverything: chat models, images, video and voice from every major provider;\ntools for any model, from web search and memory to code sandboxes and any MCP\nserver; and traffic control (format translation, fallback, retries and hedged\nrequests), with a live log of every call. \u003Cstrong>\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=pVv2ibXiTXM\" rel=\"nofollow ugc noopener\">▶ Watch the demo\u003C\u002Fa>\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cbr \u002F>\n\u003Cdiv align=\"center\">\n  \u003Cimg alt=\"Your app plugs into Respan Gateway, which connects it to models, voice, image and video, tools, embeddings and self-hosted models, with fallback, hedging, translation, tool loop, PII redaction and tracing built in\" src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frespanai\u002Frespan-gateway\u002FHEAD\u002Fdocs\u002Fassets\u002Fgateway-hero.png\" width=\"900\" \u002F>\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\u003Cblockquote>\n\u003Cp>[!TIP]\nStarring the repo helps more developers find Respan Gateway.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2>LLM gateway features\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cp>\u003Cstrong>Any client, any model\u003C\u002Fstrong>\u003Cbr \u002F>\nOpenAI Chat Completions, OpenAI Responses, Anthropic Messages and Gemini API\nclients can all call any model, with streaming, tools,\nimages and reasoning translated.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Multimodal\u003C\u002Fstrong>\u003Cbr \u002F>\nRealtime voice across vendors (an OpenAI Realtime client talks to Gemini\nLive, and back), plus images, speech, transcription, embeddings and video\nthrough OpenAI's or Gemini's APIs, to any vendor that has them.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>MCP gateway and tools for every model\u003C\u002Fstrong>\u003Cbr \u002F>\nPut MCP servers or built-in tool vendors behind the gateway, from web search\nto code sandboxes. It runs their tools inside chat requests, so a plain chat\ncall can use them, whatever the client or model.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Traffic control\u003C\u002Fstrong>\u003Cbr \u002F>\nNamed routes, globs and \u003Ccode>provider\u002Fmodel\u003C\u002Fcode>; fallback, retries, cheapest or\nfastest; and hedged requests that race a slow call against a second\nprovider.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Observability\u003C\u002Fstrong>\u003Cbr \u002F>\nA live request log with cost, latency and tokens for every call, and traces\nin \u003Ca href=\"https:\u002F\u002Frespan.ai\" rel=\"nofollow ugc noopener\">Respan\u003C\u002Fa>, where span-02 analyzes how your agents\nbehave.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Best-in-class performance\u003C\u002Fstrong>\u003Cbr \u002F>\n0.07 ms of added latency, 56,000 requests per second and 31 MB of memory in\nour benchmarks: about 3× the throughput of the next\nfastest gateway we tested.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Write your own plugin in minutes\u003C\u002Fstrong>\u003Cbr \u002F>\nEvery feature above is a plugin, built on the same public Rust API you can\nuse: one trait with four hooks. Start from the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frespanai\u002Frespan-gateway\u002Fblob\u002FHEAD\u002Fdocs\u002Fplugins.md\" rel=\"nofollow ugc noopener\">plugin guide\u003C\u002Fa>\nor an \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frespanai\u002Frespan-gateway\u002Fblob\u002FHEAD\u002Fexamples\u002FREADME.md\" rel=\"nofollow ugc noopener\">example\u003C\u002Fa> such as guardrails, PII masking o\u003C\u002Fp>\n\u003C\u002Fli>\n\u003C\u002Ful>\n",1795123405833]