Skip to content
View PeakScripter's full-sized avatar
8 followers · 10 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Block or report PeakScripter

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
PeakScripter/README.md

hey, i'm Yashvardhan Gulyani 👋

building intelligent systems & high‑impact web experiences

portfolio • x / twitter • email

👨‍💻 about me

  • 🔭 crafting ai‑native products, automation workflows & real‑time dashboards
  • 🧠 obsessed with ml, generative ai, multi‑agent systems & system design
  • 🛠️ love shipping: from idea → prototype → production (vercel / gcp / docker)
  • 🎧 either coding, tuning models or binge‑watching web series in the background
  • 💬 ask me about: llm apps, rag, workflow automation, event‑driven backends, realtime analytics

⚙️ tech i play with

python javascript typescript cplusplus react nextjs nodejs express tensorflow pytorch mongodb postgresql gcp docker git

🚀 what i'm building

  • 🧠 Agentic AI Workflows – multi‑agent LLM pipelines for automation, research and content ops
  • 📊 Realtime Analytics Dashboards – event‑driven backends with websockets, streaming & live UI
  • 🤖 ML / GenAI Experiments – finetuning, RAG, evaluation harnesses and small‑model optimizations
  • 🛠️ Developer Tools – CLIs, internal tools and micro‑services that speed up iteration

Pinned Loading

  1. dscurator dscurator Public

    Generate domain-specific synthetic datasets (Q&A, corpus, chain-of-thought, agent trajectories) using LLMs via LiteLLM. Supports BFS, random walk, Markov chain, and graph-based prompt expansion wit…

    Python

  2. Finetuning-Forge Finetuning-Forge Public

    Local-first LLM fine-tuning workstation with a modern UI — supports Unsloth, Axolotl, and Torchtune backends with real-time GPU telemetry, live loss curves, and VRAM pre-flight checks.

    TypeScript

  3. Multi-Agent-Research-System Multi-Agent-Research-System Public

    A LangGraph-powered multi-agent research system (MARS) that orchestrates five specialized AI agents (Planner, Researcher, Writer, Critic, Word) using Google Gemini to produce polished research repo…

    Python

  4. Neural-Visualizer Neural-Visualizer Public

    Interactive web app to explore and understand neural networks — build ANN, CNN, RNN, LSTM, GAN, Transformer, and Diffusion models, then visualize their architecture, forward/backward propagation, d…

    TypeScript 4 2

  5. ewproj ewproj Public

    Agentic content generation platform with RAG, pgvector search, multi-LLM orchestration, and streaming pipelines.

    Python

  6. claw-review claw-review Public

    🦞 AI-powered, read-only code review agent. Reads code, runs analyzers, emits structured findings , never mutates your source. Ships as a CLI + GitHub Action.

    Python