<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>llm-router</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3521/feed"/>
    <updated>2026-11-13T00:29:50+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3521/feed</id>
            <entry>
            <id>https://links.biapy.com/links/14352</id>
            <title type="text"><![CDATA[Otari]]></title>
            <link rel="alternate" href="https://otari.ai/?ref=blog.mozilla.ai" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14352"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[open-source AI gateway for any model.

Any model in your coding agent
in 5 minutes

Put open-weight and frontier models behind one API key. See what drives spend, cap it before it runs over, and send each request to the right model.

Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

- [Otari @ GitHub](https://github.com/mozilla-ai/otari).

Related contents:

- [Otari by Mozilla AI: your operating system for AI governance @ Mozilla.ai](https://blog.mozilla.ai/otari-by-mozilla-ai-your-operating-system-for-ai-governance/).]]>
            </summary>
            <updated>2026-11-06T07:03:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/14186</id>
            <title type="text"><![CDATA[Bifrost]]></title>
            <link rel="alternate" href="https://www.getmaxim.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14186"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Enterprise AI Gateway Built for Scale.

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

- [Bifrost @ GitHub](https://github.com/maximhq/bifrost).]]>
            </summary>
            <updated>2026-10-15T12:09:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13849</id>
            <title type="text"><![CDATA[NVIDIA Personal AI Router (PAIR)]]></title>
            <link rel="alternate" href="https://github.com/NVIDIA/Personal-AI-Router" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13849"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Router that virtually distributes inference across connected devices in the home.

NVIDIA Personal AI Router (PAIR) is a local inference router for a group of compatible computers on the same network. It discovers participating nodes, manages supported inference engines, and presents Ollama-compatible and OpenAI-compatible proxy endpoints to applications and agents. Independent requests can be routed to eligible nodes according to engine availability, model availability, and current workload.

PAIR is useful for concurrent local workloads such as multi-agent applications. Prompts and responses are intended to remain on the local network when every configured client, model source, engine, and node is local.]]>
            </summary>
            <updated>2026-09-08T12:31:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13640</id>
            <title type="text"><![CDATA[Switchyard]]></title>
            <link rel="alternate" href="https://github.com/NVIDIA-NeMo/Switchyard" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13640"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Switchyard is a Rust proxy and library for LLM traffic. It routes requests across providers, translates between OpenAI and Anthropic APIs, records operational metrics, and provides typed, composable routing algorithms.

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.]]>
            </summary>
            <updated>2026-08-14T12:49:58+00:00</updated>
        </entry>
    </feed>
