learn-claude-code and liteagents
About learn-claude-code
shareAI-lab/learn-claude-code
Bash is all you need - A nano Claude Code–like agent, built from 0 to 1
Implements a minimal Claude-powered coding agent through direct model integration rather than prompt orchestration, emphasizing tool access (shell, file I/O, API calls) and dynamic knowledge retrieval as the core "harness" architecture. The project deliberately rejects framework-heavy approaches, instead teaching how to build lightweight execution environments that let LLMs autonomously reason and act—applicable across any domain requiring perception, reasoning, and action loops. Core technical patterns cover tool composition, context management, and subagent isolation to keep the model's decision-making clean and scalable.
About liteagents
hamr0/liteagents
Comprehensive AI liteagents kit (subagents, skills/commands) for Claude Code, Opencode, Ampcode, and Droid
Provides 11 specialized agents spanning product management (PRD generation, task breakdown, execution tracking) and technical domains (architecture, QA, UI design), with auto-triggering skills for test-driven development and verification in Claude Code. Features a lightweight "Hot Memory" pipeline (`/stash → /friction → /remember`) that accumulates project-local learnings across sessions via markdown-based context without external databases.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work