Askube — GenAI content-repurposing SaaS, live in production, built solo

• One video → LinkedIn posts, X threads, auto-captioned clips & newsletters in the creator's brand voice, in ~58s
• Full pipeline end-to-end: transcription, LLM generation, clip detection, video chat (RAG), subscription billing, publishing to 5+ platforms
• Python FastAPI LLM pipeline Docker

blackbox — fully local flight recorder for dev work

• Records terminal commands, AI-agent sessions & git commits into local semantic memory — ask "what broke the deploy" in plain English, get cited answers; drafts standups & RCAs with a local LLM
• ⚡ flashback: when a failure repeats, the fix that worked last time appears right under the failed command
• 100% local & private (secrets redacted before ingestion) · 50 unit tests + autonomous e2e harness · npm releases via OIDC trusted-publishing CI with SLSA provenance
• Node.js zsh hooks Supermemory Local Ollama

MindFlayer — RL environment for emergent LLM deception 🏆 Top 100 / 31,000 teams

• A trainable LLM agent (Qwen2.5-0.5B) learns to deceive three fixed GPT-4o-mini investigators, scored by an LLM judge on a Theory-of-Mind taxonomy
• SFT warmup + 500-step GRPO · ToM score 0.041 → 0.103 · anti-reward-hacking penalties converged to zero
• Live on Hugging Face Spaces · PyTorch GRPO TRL OpenEnv

Kneedle — on-device health AI for osteoarthritis patients

• Offline-first gait analysis + Gemma-powered conversational AI (Google Gemma 4 Good Hackathon)
• Gemma on-device inference

prithidevghosh@gmail.com · LinkedIn · X/Twitter · getaskube.com