[HN Gopher] Nexus: An Open-Source AI Router for Governance, Cont...
___________________________________________________________________
Nexus: An Open-Source AI Router for Governance, Control and
Observability
Author : mitchwainer
Score : 69 points
Date : 2025-08-12 14:41 UTC (8 hours ago)
(HTM) web link (nexusrouter.com)
(TXT) w3m dump (nexusrouter.com)
| mitchwainer wrote:
| Grafbase just launched Nexus, an open-source AI Router that
| unifies MCP servers and LLMs through a single endpoint. Designed
| for enterprise-grade governance, control, and observability,
| Nexus helps teams manage AI complexity, enforce policies, and
| monitor performance across their entire stack. Built to work with
| any MCP server or LLM provider out-of-the-box, Nexus is designed
| for developers who want to integrate AI with the same rigor as
| production APIs.
| CptanPanic wrote:
| Sounds like litellm which I use, I wonder how it compares?
| vid wrote:
| There is also https://github.com/maximhq/bifrost which
| apparently overcomes some performance issues of litellm and
| is easy to get going.
| tomhoule wrote:
| Yeah they definitely belong in the same space. Nexus is an
| LLM Gateway, but early on, the focus has been on MCP:
| aggregation, authentication, and a smart approach to tool
| selection. There is that paper, and a lot of anecdotal
| evidence, pointing to LLMs not coping well with a selection
| of tools that is too large:
| https://arxiv.org/html/2411.09613v1
|
| So Nexus takes a tool search based approach to solving
| that, among other cool things.
|
| Disclaimer: I don't work on Nexus directly, but I do work
| at Grafbase.
| fbjork wrote:
| Founder of Grafbase here.
|
| Here are a few key differentiators vs LiteLLM today:
|
| - Nexus does MCP server aggregation and LLM routing - LiteLLM
| only does LLM routing
|
| - The Nexus router is a standalone binary that can run with
| minimal TOML configuration and optionally Redis - LiteLLM is
| a whole package with dashboard, database etc.
|
| - Nexus is written in Rust - LiteLLM is written in Python
|
| That said, LiteLLM is an impressive project, but we're just
| getting started with Nexus so stay tuned for a steady barrage
| of feature launches the coming months:)
| SparkyMcUnicorn wrote:
| What's the difference between "MCP Server Aggregation" and
| the litellm_proxy endpoint described here?
|
| https://docs.litellm.ai/docs/mcp
| tomhoule wrote:
| The main difference is that while you can get Nexus to
| list all tools, by default the LLM accesses tools by
| semantic search -- Nexus returns only the relevant tools
| for the what the LLM is trying to accomplish. Also, Nexus
| speaks MCP to the LLM, it doesn't translate like
| litellm_proxy seems to do (I wasn't familiar with it
| previously).
| evolve2k wrote:
| As in Torment Nexus? Wow.
| fbjork wrote:
| Ha
| bentogrizz wrote:
| This is cool
| fbjork wrote:
| What are you building?
| mbrumlow wrote:
| I thought it was a phone :/, for developers.
| fbjork wrote:
| That phone was discontinued:)
| owenthejumper wrote:
| Another proxy?
| fbjork wrote:
| MCP aggregation is one of the big differentiators
| makita34 wrote:
| Seems quite similar to the commercial nexos.ai platform, which
| also focuses on routing, governance, and observability for AI
| workloads, but as a proprietary solution rather than open source
| fbjork wrote:
| From what I can tell they don't offer a self-hosted router?
___________________________________________________________________
(page generated 2025-08-12 23:01 UTC)