Skip to content
View Turbo31150's full-sized avatar
3 followers · 4 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Turbo31150

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Turbo31150/README.md
T Turbo31150 Franc Delmas · Toulouse, France AI Systems GPU Clusters Trading AI Voice Platforms Automation 22 repos · JARVIS·OS · JARVIS·TURBO · TRADEORACLE·AI · LUMEN·TRANSCRIBE · MIT



Python TypeScript CSharp GPU JARVIS Repos

À propos

Développeur et architecte systèmes IA basé à Toulouse, France. Je construis des infrastructures IA distribuées, des systèmes de trading algorithmique autonomes, et des plateformes voix temps réel.

Mon infrastructure principale — JARVIS — est un écosystème dual : JARVIS·OS (Linux, cluster 4 nœuds, deepseek-r1 + qwen3, 850+ commandes vocales) et JARVIS·TURBO (Windows, 3 machines, 10 GPUs, 78GB VRAM, React 19 + Electron dashboard).

Stack principale

Python 3.11 · TypeScript · C# .NET 8 · Node.js
SQLite3 · Docker · systemd · n8n
Whisper CUDA · LM Studio · Claude API · Gemini API
MEXC Futures API · Telegram Bot API · Twilio
React 19 · Vite 6 · Electron · WebSocket

Projets phares

Projet Description Stack
JARVIS·OS OS cognitif Linux — cluster 4 nœuds, 600+ MCP handlers, 850+ voice cmds Python · TypeScript · Docker
JARVIS·TURBO Orchestrateur Windows multi-agents — 10 GPUs, React 19 dashboard, DERNI trading Python · React 19 · Electron
TRADEORACLE·AI Agent trading autonome — Gemini 3, 800+ paires MEXC, Domino Pipeline Python · Gemini API
LUMEN·TRANSCRIBE Transcription multilingue temps réel — 30+ langues, Whisper CUDA TypeScript · React
WHISPERFLOW·CUDA Pipeline voix CUDA < 300ms — large-v3, JARVIS voice layer Python · CUDA
PROMPT·VAULT 300+ prompts optimisés — 5 IAs, Claude/GPT/Gemini/Perplexity HTML · JSON
GITFLOW·AI Automation GitHub IA — scan, Comet bridge, multi-publish, profile score JavaScript · Node.js
ARIA·SENTINEL 10 agents IA treasury risk — Monte Carlo, HITL — Airia Hackathon 2026 Python · FastAPI

Infrastructure

JARVIS·OS (Linux cluster)
  Node-1 (Master)  · Node-2  · Node-3  · Cloud
  deepseek-r1      · qwen3   · compute · failover
  850+ voice cmds  · 600+ MCP handlers · WS:9742

JARVIS·TURBO (Windows)
  M1: Ryzen 7 5700X3D · 46GB · 6 GPUs (34GB VRAM)
  M2: LM Studio · qwen3-30b · deepseek-r1
  M3: 45GB RAM · 3× Quadro GPU (20GB+ VRAM)
  Dashboard: React 19 / Vite 6 / Electron
  Agents: OpenClaw 96 patterns · Whisperflow CUDA
  Trading: DERNI ULTIMATE n8n (32 nodes, MEXC)

Hackathons

Hackathon Projet Technologie
Google Cloud ADK TRADEORACLE·AI Gemini 3 · MCP
Google Cloud ADK GEMINI·LIVE·TRADER Gemini Live API
Google Cloud ADK GEMINI·STORYTELLER Imagen 3 + Voice
Google Cloud ADK GEMINI·UI·NAVIGATOR Vision + Playwright
Airia AI Agents ARIA·SENTINEL 10 agents + Monte Carlo
Agent Builder 2026 NEXUS·ELASTIC Elasticsearch + Gemini
Hex 2026 CRYPTOTIME·AI Data correlation

Contact

  • GitHub : github.com/Turbo31150
  • Localisation : Toulouse, France
  • Stack : Python · TypeScript · C# · GPU · IA

Franc Delmas (Turbo31150) · Toulouse · MIT · Propulsé par JARVIS

Pinned Loading

  1. Performance Analyzer - Hardware + Fi... Performance Analyzer - Hardware + FileSystem + Multi-IA Integration - MEGA_ORGANIZED method
    1 
    # ═══════════════════════════════════════════════════════════════════════════════
    2 
    # PERFORMANCE ANALYZER - Analyse + Maintenance + Optimisation
    3 
    # ═══════════════════════════════════════════════════════════════════════════════
    4 
    # Intégré au système Multi-IA
    5 
    # Scan méthode MEGA_ORGANIZED
  2. APPEL API - UTILISATION MODEL SELECT... APPEL API - UTILISATION MODEL SELECTIONNEE ET OPTIONS ENTREE/SORTIE - Logique complète avec exemples OpenAI et Perplexity
    1 
    # APPEL API - UTILISATION MODEL SELECTIONNEE ET OPTIONS ENTREE/SORTIE
    2 
    
              
    
              
    
                3
                
    ## LOGIQUE D'UTILISATION - GUIDE COMPLET
    
              
    
              
    
                4
                
    
              
    
              
    
                5
                
    Ce document presente la logique complete pour utiliser les APIs OpenAI et Perplexity avec selection de modele et gestion des entrees/sorties.
    
              
    
          
    
    
    
  
    

    3. 

      

  3. 
  
    
    
    
      
    
        
        Ponderation Dynamique Multi-IA V2 - ...  Ponderation Dynamique Multi-IA V2 - Formules Auto-Optimisees      
    

          
    
              
    
                1
                
    # PONDERATION DYNAMIQUE ENRICHIE
    
              
    
              
    
                2
                
    ## Formules Auto-Optimisees Multi-IA
    
              
    
              
    
                3
                
    
              
    
              
    
                4
                
    ---
    
              
    
              
    
                5
                
    
              
    
          
    
    
    
  
    

    4. 

      

  4. 
  
    
    
    
      
    
        
        Machine Orchestrator - Auto-detect h...  Machine Orchestrator - Auto-detect hardware, adaptive allocation, performance optimization      
    

          
    
              
    
                1
                
    # ═══════════════════════════════════════════════════════════════════════════════
    
              
    
              
    
                2
                
    # ORCHESTRATOR - Analyse Materiel + Adaptation Automatique
    
              
    
              
    
                3
                
    # ═══════════════════════════════════════════════════════════════════════════════
    
              
    
              
    
                4
                
    # Detecte automatiquement: RAM, GPU, CPU
    
              
    
              
    
                5
                
    # Calcule allocations optimales
    
              
    
          
    
    
    
  
    

    5. 

      

  5. 
  
    
    
    
      
    
        
        Script Test Distribution Massive Mul...  Script Test Distribution Massive Multi-IA      
    

          
    
              
    
                1
                
    #!/usr/bin/env python3
    
              
    
              
    
                2
                
    """
    
              
    
              
    
                3
                
    TEST DISTRIBUTION MASSIVE MULTI-IA
    
              
    
              
    
                4
                
    Mesure performances reelles et enrichit ponderations
    
              
    
              
    
                5
                
    """
    
              
    
          
    
    
    
  
    

    6. 

      

  6. 
  
    
    
    
      
    
        
        Resultats Tests Massifs Distribution...  Resultats Tests Massifs Distribution Multi-IA      
    

          
    
              
    
                1
                
    
              
    
              
    
                2
                
    # PONDERATION ENRICHIE - RESULTATS TESTS MASSIFS
    
              
    
              
    
                3
                
    # Date: 2025-11-27 19:07
    
              
    
              
    
                4
                
    # Tests: 8 executes
    
              
    
              
    
                5
                
    
              
    
          
    
    
    
  
    

    7.