NierRouter

Created by team Nier_Classification on July 07, 2026
GemmaAgentOpsAMD ROCmAntigravityAnthropic ClaudeChatGPTClaude CodeCodexDeepSeek V3Gemini 3 proHuggingFace SpacesQwen3Qwen3-Coder
Hybrid Token-Efficient Routing Agent

This project is a highly optimized, dual-tier task evaluation pipeline designed specifically to operate under strict hackathon hardware constraints, including a hard ceiling of 4GB RAM and 2 vCPUs. At its core, the system utilizes a zero-token semantic router built on all-MiniLM-L6-v2 to intelligently classify incoming tasks—ranging from code debugging and named entity recognition to complex math execution and logical puzzles. Instead of relying purely on expensive API calls, the primary inference engine is a locally hosted, 4-bit quantized Qwen2.5-Coder-1.5B model. By eagerly loading the models into memory at startup and implementing strict concurrency locks, the pipeline completely avoids Out-Of-Memory (OOM) crashes and thread collisions. The local model handles the vast majority of operations, ensuring fast execution

Category tags:
GithubPresentationDemo
Explore more applications

Thymus

Thymus is a lightweight hybrid token-efficient router designed to maximize accuracy while minimizing token costs in multi‑task LLM pipelines. It dynamically routes user queries across local and remote models on LLM providers.

The Disappointer

HuggingFace HubLLaMAAMD Developer Cloud
Vercel
application badge

AI Classroom Edge Intelligence

A privacy-first classroom AI platform that routes sensitive work to local edge systems and eligible anonymized analysis to Fireworks AI, helping teachers make faster, safer instructional decisions even with unreliable internet.

AI Classroom Edge

AMD Developer CloudQwen3rest apiGithub CopilotCodexChatGPT

Taskly: Smart Multi-Model Task Router

Taskly classifies incoming tasks into 8 categories (QA, math, code, NLP) and routes each to the optimal Fireworks AI model with a tuned prompt — maximizing accuracy while minimizing token usage in a fully Dockerized pipeline.

RuntimeTerror

AMD Developer CloudAMD ROCm
Streamlit
application badge

router_007_v3

router_007_v2 is a Track 1 agent that records **zero billable tokens**: every answer is computed inside the container by a Qwen2.5-7B-Instruct model bundled in the Docker image and served in-process with llama-cpp-python

roc_auc_half

Claude CodeChatGPTAMD ROCmAMD Developer CloudCodexGemmaGPT-5NVIDIAQwen3

Lexyprep

Agent knows how to make thorough legal research based on my experience of winning legal cases. It understands your issue and advises on procedure

Lexyprep - Do you have a case

AMD Developer CloudAMD ROCmCodexGemma