Skip to content
Back to the index

TokenRouter

github.ioInfrastructure

No liveness check has reached it yet; it is registered on GitHub and has been in the index since 9 Oct 2026. How this is checked

TokenRouter is a serving engine for token-level routing across language models. It provides request-centric programming, asynchronous model-centric execution, retained state, and delayed batching for researchers and engineers building adaptive LLM inference systems.

Inferred · not functionally tested

WebCLISelf-hostedAPI
TokenRouter preview
Visit github.io
18stars
9features
2026since

Overview

6 features

Purpose: Serving responses that dynamically route tokens across multiple language models without sacrificing throughput.

Inferred · not functionally tested

Audience: machine learning researchers and inference engineers

Inferred · not functionally tested

Functions: Unknown

Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: unknown · license: Proprietary · platforms: CLI, WEB · deployment: browser, cli, self_hosted, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: fuvty.github.io · github.com. These links do not verify the individual claims.

In the Inference & model serving space, TokenRouter takes a focused approach. Inferred · not functionally tested: It focuses on serving responses that dynamically route tokens across multiple language models without sacrificing throughput. Inferred · not functionally tested: TokenRouter is an open-source project aimed at machine learning researchers and inference engineers. Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.

Fuvty builds and maintains TokenRouter, and it first shipped in 2026. Development happens publicly on GitHub with 18 stars and 2 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include token routing, model subservers, and retained state.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Token routing
  • Model subservers
  • Retained state
  • Route interface
  • Send interface
  • Receive interface

Topics: Inferred · not functionally tested

Tags
token-level-routingllm-servingdelayed-batchingmulti-model-inference
AI capabilities
Text
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Framework
FastAPI
AI providers
meta_llama
Runs on
BrowserCLISelf-hostedAPI-only
Detected from
meta_llama
llama- in the HTML

Trust & compliance

Public signals
HTTPSGitHub · ★ 18Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed9 Oct · 09:31 UTC
    TokenRouter: A serving engine for token-level LLM routing seen via Hacker News firehose (Algolia)
    Source: Hacker News firehose (Algolia) · Open

Frequently asked questions about TokenRouter

What is TokenRouter?
Inferred · not functionally tested: TokenRouter focuses on serving responses that dynamically route tokens across multiple language models without sacrificing throughput. It is catalogued under Inference & model serving on PulseGate.
Who should use TokenRouter?
Inferred · not functionally tested: TokenRouter is an open-source project built for machine learning researchers and inference engineers.
What platforms does TokenRouter run on?
Basis unknown · not verified: TokenRouter runs on the web, the command line, and API. It can also be self-hosted.
Is TokenRouter still maintained?
The GitHub repository shows 2 commits in the last 90 days.
Who develops TokenRouter?
TokenRouter is developed by Fuvty.
How long has TokenRouter been around?
TokenRouter first shipped in 2026.
Is TokenRouter open source?
Basis unknown · not verified: TokenRouter has a public GitHub repository.

Similar projects

Closest matches by what these projects do