Learn Claude Code is a minimal agent harness implementation that recreates the core loop of Claude Code from zero. Built primarily in Python and Bash, it demonstrates the fundamental architecture of coding agents: tool registration, conversation loops, model routing, and skill execution. With 66K+ GitHub stars, it serves as the most popular educational resource for developers who want to understand agent internals rather than just use them as black boxes.
Builder.io's open-source framework for building agent-native applications — shared actions, SQL-backed state, identity, tools, skills, jobs, observability, and UI surfaces that all work together.
Persistent memory layer for AI coding agents — benchmark-backed (95.2% on LongMemEval-S), 92% fewer tokens per session vs full-context pasting, zero manual memory.add() calls.
Open-source AI pair programming tool that works in your terminal to edit code across your entire repository.