CS329A: Self-Improving AI Agents. Stanford University Course

A Stanford course gathers lectures and materials on self-improving AI agents, along with a collection of recent scientific publications.
CS329A is a Stanford University course focused on self-improving AI agents. It collects lectures and useful materials for studying this topic.
Additional resources:
Why it matters
AnalysisIt provides a structured entry point to research on autonomous agents and self-improvement, and links to up-to-date papers in the field.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Claude Code Projects: How a Single AI Orchestrates a Team of Autonomous Agents
A deep dive into Claude Code Projects: Coordinator and Threads architecture, parallel branches, shared memory via MEMORY.md, and cloud agent management.
AI Agents (Autonomous Agents)
Software systems based on LLMs that can autonomously perceive the state of the environment, decompose complex goals, invoke external tools, and iteratively correct their own mistakes.
Codync: open-source Rust tool turns AI agents into chatbots
Codync is a free Rust project that wraps more than 40 local AI agents into chatbots, enabling control from iPhone, Mac, Windows, Linux, or the terminal.
Free tool turns any website into a brand kit for AI agents
A new free service generates DESIGN.md, BRAND.md, and SKILL.md files so Claude, ChatGPT, and Cursor can use a brand’s visual identity.