A library for mechanistic interpretability of GPT-style language models

Centaur is frontier, agentic infrastructure that you own. Centaur is like Claude Tag, but open source and on steroids.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Class materials for a distributed systems lecture series

Learning materials for UCB CS186: Introduction to Database System

Reference Implementation for ERC-8004 Trustless Agents, a trust layer for the open agent economy.

A payments protocol for the internet. Built on HTTP.

A framework for few-shot evaluation of language models.

Every AI Agent deserves a wallet.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Open protocol for tokenizing physical agricultural commodity deposits on Stellar. Soroban smart contracts, token metadata standard, and SDK for warehouse receipt tokenization across Nigerian agricu…

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

An Open Source implementation of Notebook LM with more flexibility and features

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Xmem is a India's First open source multi-modal, multi-agentic long‑term memory layer for AI agents.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Ultimate AI Engineer Roadmap 2026 - built specifically for your context as an AI Architect building PrinceSinghAI, PrinceSinghDev, Multi-LLM orchestration, RoadmapAI, CodeLLM, and AskAI, Global AI …

Build your own AI SRE agents. The open source toolkit for the AI era.

Your Cheat Sheet for AI Engineering Interview – Questions and Answers.

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

Learn it. Build it. Ship it for others.

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

Train the smallest LM you can that fits in 16MB. Best model wins!

🚀 Metadata tracking and UI service for Metaflow!

Skills for Real Engineers. Straight from my .agents directory.