Arnav

obsidian-wiki. Framework for AI agents to build and maintain a digital brain through Obsidian wiki using Karpathy's LLM Wiki pattern

PaperOrchestra. An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

gemini-nano-chrome. Using Gemini Nano through Chrome's built-in Prompt API, with scripts to automate setup and verification

transformer-nmt-chatbot. Python

agent-manual. The manual for AI coding agent hooks, configs, PreToolUse/PostToolUse, MCP, and skills - covering Claude Code, Copilot, Cursor, Codex, Gemini CLI, and more.

AgentTower. A real-time web UI for monitoring, searching, and controlling Claude Code and Codex CLI sessions

fast-is-english-word. Blazingly fast English word lookup. ~42M ops/s, 270 KB, zero dependencies. Uses xor filters.

gepa-tuned-sql-agent. Self-debugging SQL agent with GEPA evolutionary prompt optimization — no fine-tuning, just context engineering

daily-research-papers. One AI paper per day - summaries and coding-agent skills

mlx-lm-server. OpenAI-compatible LLM, image generation, and audio inference on Apple Silicon — Rust + PyO3 + MLX

human-fight-rl. JavaScript

Portraitor. Potrait Mode using single camera as in Google Pixel using Image Segmentation and Machine Learning

Question-Generation. Python

Feature-Extraction-from-Facial-Images. Querying Facial Images using Deep Learning – On Python feature extraction with Keras using model Resnet and building a facial feature detection model to retrieve images for multiple queries

xrcc-hackathon. TypeScript

game-exa. The AI-native game engine — describe your game, get a complete playable Phaser 3 title with GPT Image 2 art, levels, code, QA, and multiplayer.