Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
- official
- workshops
- anthropic
- managed-agents
A complete open guide plus vault template and agent skills: let an AI agent build and maintain a linked markdown knowledge base for you, in files you own.
AI Second Brain hands the boring filing work to an agent so the system stays alive: everything you read, watch and save becomes linked wiki pages connected to everything already there, and you can ask it questions. The repo is the full version of the guide — concepts, setup walkthroughs, the Obsidian vault template, the agent skills, the scripts and every vetted resource. Quick start is two cp -r commands (vault template to ~/brain, skills into its .claude directory), then open the folder as an Obsidian vault; an optional MCP setup lets the agent reach the vault from anywhere. Free, no signup, nothing to install beyond Obsidian and an agent. The premise is honest about why your past systems died: humans stop filing and linking after two weeks — an agent doesn't. MIT, with a searchable web edition on GitHub Pages.
Rebuilding a personal knowledge base that actually compounds — bookmarks, videos and read-later queues turned into linked pages an agent maintains and you can interrogate.
git clone https://github.com/undefined-ui/second-brain-os.git # copy the starter vault, skills, commands and agents: cp -r second-brain-os/vault-template ~/brain cp -r second-brain-os/skills ~/brain/.claude/skills # install Obsidian, then open ~/brain with "Open folder as vault"
Assumes Obsidian and a capable agent — the guide is the product, so expect reading and setup time rather than a one-click app. Vault quality follows your input habits: an agent maintains the links, but it can only file what you actually feed it.
Repository
undefined-ui/second-brain-osCharted
Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
Anthropic's announcement of Fable 5.1 and Mythos 5.1 — one base model, two guardrail postures.
Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.