Skip to content

gosarmarcel7-creator/traxon

Repository files navigation

Traxon — AI Agent Observability

Full visibility into every AI agent session. Monitor costs, replay sessions, catch failures before they cost you.

Deploy with Vercel

What is Traxon?

Traxon is an observability platform purpose-built for teams running AI agents in production. Whether you're orchestrating Claude, GPT-4o, Gemini, or custom LLMs, Traxon gives you the visibility you need:

  • Session Replay — Watch every tool call, message, and decision step by step
  • Cost Explorer — Break down spend by agent, project, and time period
  • Real-time Logs — Stream live events with powerful filtering and search
  • Smart Alerts — Set budget limits and failure thresholds with instant notifications
  • Multi-Provider — Works with Anthropic, OpenAI, Gemini, and any OpenAI-compatible API
  • Team Collaboration — Share sessions, annotate findings, manage access

Tech Stack

  • Framework: Next.js 15 (App Router)
  • Language: TypeScript
  • Styling: Tailwind CSS + custom design system
  • Database: Supabase (PostgreSQL + Auth + RLS)
  • Charts: Recharts
  • Deployment: Vercel

Getting Started

1. Clone & Install

git clone https://github.com/gosarmarcel7-creator/traxon.git
cd traxon
npm install

2. Set up Supabase

  1. Create a project at supabase.com
  2. Run the migration in supabase/migrations/20260530_init_traxon.sql in your Supabase SQL editor
  3. Copy your project URL and anon key

3. Configure Environment

cp .env.example .env.local

Fill in your Supabase credentials in .env.local.

4. Run Locally

npm run dev

Open http://localhost:3000

Demo Mode: By default, the app runs with hardcoded demo data. Set NEXT_PUBLIC_DEMO_MODE=false in .env.local to use real Supabase data.

Deploying to Vercel

The easiest way is to connect your GitHub repo directly in vercel.com:

  1. Import the traxon repo
  2. Add your environment variables in the Vercel project settings
  3. Deploy

Or use the CLI:

vercel --prod

SDK Integration (Coming Soon)

import { Traxon } from '@traxon/sdk';

const traxon = new Traxon({ apiKey: 'trx_live_...' });
const agent = traxon.wrap(yourLLMCall);

Project Structure

traxon/
├── src/
│   ├── app/
│   │   ├── (app)/          # Authenticated app pages (with sidebar)
│   │   │   ├── dashboard/
│   │   │   ├── agents/
│   │   │   ├── sessions/
│   │   │   ├── cost/
│   │   │   ├── logs/
│   │   │   ├── alerts/
│   │   │   └── settings/
│   │   ├── login/
│   │   ├── signup/
│   │   ├── globals.css     # Design system
│   │   └── layout.tsx
│   ├── components/
│   │   ├── Sidebar.tsx
│   │   └── TopBar.tsx
│   └── lib/
│       ├── demo-data.ts    # Realistic demo data
│       └── utils.ts        # Utility functions
├── supabase/
│   └── migrations/
│       └── 20260530_init_traxon.sql
└── vercel.json

License

MIT

About

AI Agent Observability — Monitor, replay, and track every agent session

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors