Beads - A memory upgrade for your coding agent

Agent Protocol SDK

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

LLM Council works together to answer your hardest questions

Analyzing Hacker News discussions from a decade ago in hindsight with LLMs

Artificial Life simulator using canvas. Based on https://github.com/karpathy/scriptsbots

Persistent dict, backed by sqlite3 and pickle, multithread-safe.

A numeric optimization package for Torch.

my blog

The best ChatGPT that $100 can buy.

A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development tool for…

The missing tiktoken training code

Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views

The CLI for the Claude API

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Report issues related to MCP integration with Claude here.

Terragrunt is a flexible orchestration tool that allows Infrastructure as Code written in OpenTofu/Terraform to scale.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Vectors analytics and search library using dispersion models. Provides graph analysis, vector search and a energy-distribution stats for your vectors in one package.

Real-time monitoring for Proxmox, Docker, and Kubernetes with AI-powered insights, smart alerts, and a beautiful unified dashboard

Memory library for building stateful agents

Multi-agent code review CLI using NVIDIA Nemotron 3 Super

list of skills that folks talked about on the stage at the coding agent conference March 3rd

A Unified MCP Server Management App (MCP Manager).

Manage your dotfiles across multiple diverse machines, securely.

The home of the CUE language! Validate and define text-based and dynamic configuration

Rapidly build modern applications with advanced configuration management

AI agents running research on single-GPU nanochat training automatically