TriageAI — AI-Powered Email Triage for SMBs

Vercel
application badge
Created by team TriageAI on July 09, 2026
AMD ROCmGemmaGemini 3 Flash
Unicorn Track

TriageAI is an AI-powered customer support assistant built for small businesses that can't afford a dedicated support team but can't afford slow replies either. It connects to a shared support inbox (Gmail), ingests every incoming email, and runs a LangChain StateGraph triage workflow: classify intent via Gemma 4 26B on Fireworks AI, generate customer embeddings via AMD ROCm on an AMD Instinct GPU for similarity search, and either auto-reply or escalate with full reasoning. Key features: - Google OAuth via Convex Auth - 8-category email classification (Gemma 4 26B on Fireworks AI with on-demand H100) - 3-tier LLM fallback: Fireworks Gemma 4 → Google Gemma 4 API → GPT-OSS 120B - Auto-reply drafting with configurable tone (Professional / Friendly / Casual / Enthusiastic) - AMD ROCm embedding generation (e5-large-v2 on AMD Instinct GPU via Developer Cloud) - Custom escalation rules with priority levels - Real-time triage feed with Convex reactive queries - Dashboard with stats, charts (recharts), and activity feed - PostHog analytics throughout

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